Full Machine Learning Week 7-Track Agenda 2022 – Detailed Session Descriptions
Predictive Analytics World
June 18-22, 2023 l Red Rock Casino Resort & Spa, Las Vegas
See the full 7-track agenda for the six co-located conferences at Machine Learning Week. A Machine Learning Week Ticket is required for full access. To view the agenda for one individual conference, click here: PAW Business, PAW Financial, PAW Industry 4.0, PAW Climate, PAW Healthcare, or Deep Learning World.
Session Levels:
Blue circle sessions are for All Levels
Red triangle sessions are Expert/Practitioner Level
Workshops - Sunday, June 18th, 2023
Full-day: 8:30am – 4:30pm PDT
This one day workshop reviews major big data success stories that have transformed businesses and created new markets.
Full-day: 8:30am – 4:30pm PDT
Gain experience driving R for predictive modeling across real examples and data sets. Survey the pertinent modeling packages.
Workshops - Monday, June 19th, 2023
Full-day: 8:30am – 4:30pm PDT
This workshop dives into the key ensemble approaches, including Bagging, Random Forests, and Stochastic Gradient Boosting.
Full-day: 8:30am – 4:30pm PDT
This one-day session surveys standard and advanced methods for predictive modeling (aka machine learning).
Full-day: 8:30am – 4:30pm PDT
Machine learning improves operations only when its predictive models are deployed, integrated and acted upon – that is, only when you operationalize it.
Full-day: 8:30am – 4:30pm PDT
This one-day introductory workshop dives deep. You will explore deep neural classification, LSTM time series analysis, convolutional image classification, advanced data clustering, bandit algorithms, and reinforcement learning.
Machine Learning Week - Las Vegas - Day 1 - Tuesday, June 20th, 2023
Machine Learning Week Founder Eric Siegel will welcome you to the event and kick things off.
Machine Learning Week Founder Eric Siegel will welcome you to the event and kick things off.
Machine Learning Week Founder Eric Siegel will welcome you to the event and kick things off.
Machine Learning Week Founder Eric Siegel will welcome you to the event and kick things off.
Machine Learning Week Founder Eric Siegel will welcome you to the event and kick things off.
In this informal but informative presentation, Dr. James McCaffrey – who leads Microsoft Research’s CEO-mandated initiative to transfer deep learning intelligence into all products, services, and supporting systems across the enterprise – will describe six of the latest trends in machine learning and deep neural systems. Today's hottest trends include the deployment of generative AI systems like GPT-x/ChatGPT, Codex, Copilot, and DALL-E – yet they also include innovative deployments of more classical ML methods. The emphasis will be on information that is practical and can drive revenue, not theoretical ideas filled with math equations and Greek letters. Particular emphasis will be given to explaining the difference between systems that require massive resources or expensive licensing, and systems that can be successfully implemented by organizations with a limited budget.
In this informal but informative presentation, Dr. James McCaffrey – who leads Microsoft Research’s CEO-mandated initiative to transfer deep learning intelligence into all products, services, and supporting systems across the enterprise – will describe six of the latest trends in machine learning and deep neural systems. Today's hottest trends include the deployment of generative AI systems like GPT-x/ChatGPT, Codex, Copilot, and DALL-E – yet they also include innovative deployments of more classical ML methods. The emphasis will be on information that is practical and can drive revenue, not theoretical ideas filled with math equations and Greek letters. Particular emphasis will be given to explaining the difference between systems that require massive resources or expensive licensing, and systems that can be successfully implemented by organizations with a limited budget.
In this informal but informative presentation, Dr. James McCaffrey – who leads Microsoft Research’s CEO-mandated initiative to transfer deep learning intelligence into all products, services, and supporting systems across the enterprise – will describe six of the latest trends in machine learning and deep neural systems. Today's hottest trends include the deployment of generative AI systems like GPT-x/ChatGPT, Codex, Copilot, and DALL-E – yet they also include innovative deployments of more classical ML methods. The emphasis will be on information that is practical and can drive revenue, not theoretical ideas filled with math equations and Greek letters. Particular emphasis will be given to explaining the difference between systems that require massive resources or expensive licensing, and systems that can be successfully implemented by organizations with a limited budget
In this informal but informative presentation, Dr. James McCaffrey – who leads Microsoft Research’s CEO-mandated initiative to transfer deep learning intelligence into all products, services, and supporting systems across the enterprise – will describe six of the latest trends in machine learning and deep neural systems. Today's hottest trends include the deployment of generative AI systems like GPT-x/ChatGPT, Codex, Copilot, and DALL-E – yet they also include innovative deployments of more classical ML methods. The emphasis will be on information that is practical and can drive revenue, not theoretical ideas filled with math equations and Greek letters. Particular emphasis will be given to explaining the difference between systems that require massive resources or expensive licensing, and systems that can be successfully implemented by organizations with a limited budget.
In this informal but informative presentation, Dr. James McCaffrey – who leads Microsoft Research’s CEO-mandated initiative to transfer deep learning intelligence into all products, services, and supporting systems across the enterprise – will describe six of the latest trends in machine learning and deep neural systems. Today's hottest trends include the deployment of generative AI systems like GPT-x/ChatGPT, Codex, Copilot, and DALL-E – yet they also include innovative deployments of more classical ML methods. The emphasis will be on information that is practical and can drive revenue, not theoretical ideas filled with math equations and Greek letters. Particular emphasis will be given to explaining the difference between systems that require massive resources or expensive licensing, and systems that can be successfully implemented by organizations with a limited budget.
Google continues to take a bold and responsible approach to developing and deploying AI through the company’s infrastructure, tools, products, and services. Google brought further AI breakthroughs into the real world through Google Cloud’s launch of the next wave of generative AI across core areas of their business, and new partnerships and programs grounded in Google’s commitment to an open AI ecosystem. At the same time, AI, as a still-emerging technology, poses complexities and risks; and the development and use of AI must address these risks in a structured, transparent, and accountable way. A robust governance structure – and rigorous testing and ethics reviews — is necessary to put responsible AI principles into practice. And with AI regulation coming soon, Jen will share learnings, challenges, and practical tips on how Google is maturing its responsible AI practices, processes, and tools in advance of greater regulatory, global standards, and consumer expectations.
Google continues to take a bold and responsible approach to developing and deploying AI through the company’s infrastructure, tools, products, and services. Google brought further AI breakthroughs into the real world through Google Cloud’s launch of the next wave of generative AI across core areas of their business, and new partnerships and programs grounded in Google’s commitment to an open AI ecosystem. At the same time, AI, as a still-emerging technology, poses complexities and risks; and the development and use of AI must address these risks in a structured, transparent, and accountable way. A robust governance structure – and rigorous testing and ethics reviews — is necessary to put responsible AI principles into practice. And with AI regulation coming soon, Jen will share learnings, challenges, and practical tips on how Google is maturing its responsible AI practices, processes, and tools in advance of greater regulatory, global standards, and consumer expectations.
Google continues to take a bold and responsible approach to developing and deploying AI through the company’s infrastructure, tools, products, and services. Google brought further AI breakthroughs into the real world through Google Cloud’s launch of the next wave of generative AI across core areas of their business, and new partnerships and programs grounded in Google’s commitment to an open AI ecosystem. At the same time, AI, as a still-emerging technology, poses complexities and risks; and the development and use of AI must address these risks in a structured, transparent, and accountable way. A robust governance structure – and rigorous testing and ethics reviews — is necessary to put responsible AI principles into practice. And with AI regulation coming soon, Jen will share learnings, challenges, and practical tips on how Google is maturing its responsible AI practices, processes, and tools in advance of greater regulatory, global standards, and consumer expectations.
Google continues to take a bold and responsible approach to developing and deploying AI through the company’s infrastructure, tools, products, and services. Google brought further AI breakthroughs into the real world through Google Cloud’s launch of the next wave of generative AI across core areas of their business, and new partnerships and programs grounded in Google’s commitment to an open AI ecosystem. At the same time, AI, as a still-emerging technology, poses complexities and risks; and the development and use of AI must address these risks in a structured, transparent, and accountable way. A robust governance structure – and rigorous testing and ethics reviews — is necessary to put responsible AI principles into practice. And with AI regulation coming soon, Jen will share learnings, challenges, and practical tips on how Google is maturing its responsible AI practices, processes, and tools in advance of greater regulatory, global standards, and consumer expectations.
Google continues to take a bold and responsible approach to developing and deploying AI through the company’s infrastructure, tools, products, and services. Google brought further AI breakthroughs into the real world through Google Cloud’s launch of the next wave of generative AI across core areas of their business, and new partnerships and programs grounded in Google’s commitment to an open AI ecosystem. At the same time, AI, as a still-emerging technology, poses complexities and risks; and the development and use of AI must address these risks in a structured, transparent, and accountable way. A robust governance structure – and rigorous testing and ethics reviews — is necessary to put responsible AI principles into practice. And with AI regulation coming soon, Jen will share learnings, challenges, and practical tips on how Google is maturing its responsible AI practices, processes, and tools in advance of greater regulatory, global standards, and consumer expectations.
ML and AI projects are technology-heavy, data-rich and rely on increasingly large teams with deep technical skills and expertise. As more companies make larger investments in ML and AI, the pressure to succeed in these complex projects is increasing. Still, many of these projects fail. They fail not because the technology fails, not because the data is poor or because the team lacks skill but because they were not set up for success. The way the project was conceived, framed and begun destined them for failure. In this session to kick off the business track, you'll learn how to set ML and AI projects up for success by getting that first step right. You'll see how to frame the problem correctly, learn why step 1 has to be business-led and understand why deployment and operationalization depend on getting step 1 right.
Predictive modelers love building the models and then comparing them to determine the best model to deliver to the stakeholder. For Regression, the common metrics are R^2, mean squared error, root mean squared error, or mean absolute error. For classification, we usually see the confusion matrix as the basis for accuracy: Precision/Recall, Specificity/Sensitivity, and percent correct classification. These all have their place in our toolbox.
However, in many projects, if not in the majority of products, the business doesn’t care about any of these. The model is intended to increase revenue or minimize churn. If the analyst uses a standard metric, that modeler may optimize the standard metric but miss out on better models for the business. In this talk, alternative metrics will be explored that improve the effectiveness of the models operationally for the business.
The cruise industry is an ideal crucible for enterprise applications of data science and machine learning. Its ships are veritable mobile cities on the water, powered by full-blown industrial operations. Pricing and revenue management are driven by complex stochastic optimizations, demand forecasting, and price-response predictions. Marketing & eCommerce activities target guests globally with mixes of message, promotions and recommendations. And a portfolio of hotels and global supply chain must be managed to provide millions of guests all that they need locally on the ship. This session will cover case studies for how we leverage math and data to make this work, and in particular how we restarted from 18 months of essentially zero data (aka the pandemic).
Machine models are the most powerful predictors, but they are often black-box models and incorporate uncertainty by nature. Quantifying the ML uncertainty is critical for adding confidence to ML adoptions. Based on reliable uncertainty estimators, risks of ML underperformance can also be quantified and transferred through insurance solutions. We will demonstrate this application through real case studies of collaborations between ML providers and the insurance industry.
Inside healthcare, data science teams often solve each project as an independent solution. While they are able to produce significant value, project timelines can be extensive and the slow time to value impedes organization knowledge gain. In this session, I’ll show how our team has incorporated standard project structures, solution templates, supportive automations and a focus on generalized solution design to significantly decrease our time to value.
Understanding how to evaluate the performance of a model is fundamental to the work of Decision Science professionals. Often, metrics used to evaluate model performance are deployed based on theory and that might not, necessarily, holistically explain the models applied benefit, or lack thereof, to the business. This session will evaluate the trade off between model performance metrics and making business impact. What is good enough?
As DoorDash business grows, the online ML prediction volume grows exponentially to support the various Machine Learning use cases, such as the ETA predictions, the Dasher assignments, the personalized restaurants and menu items recommendations, and the ranking of the large volume of search queries. In this session, we will share our journey of building and scaling our Machine Learning platform to meet the DoorDash business growth. In addition, we will share a few of lessons learned while optimizing the prediction service and how we measure success.
Organizations must continually reimagine products and services to stay competitive. Technological acceleration of AI and data makes innovation more complex, creating a need for continual upskilling and reskilling. In this talk, Kian Katanforoosh, CEO of Workera, explores how people are at the center of successful skills transformation. He’ll share how the best organizations undergoing an AI transformation are evolving, how their workforce is gaining skills, how they use skills data to power talent strategies, and what the future of work looks like for today’s enterprise.
While machine learning algorithms can produce valuable results, evaluating the performance of the resulting exercise can be a bit confusing - to the layman, that is. Often the recipient of the results will hear about Receiver Operator Characteristic curves or a KS statistic or a means squared error, or confusion matrices or some other foreign associated term. Frequently, managers and other users of predictive algorithms are not fluent in these concepts, and they might find themselves as confused as a confusion matrix might be to them. This session will focus on practical measures of performance evaluation designed for the non-quantitative executive, as well as the data scientist who needs to present the results of his efforts to less analytically inclined audiences. The end results are a simple scorecard measuring the ML algorithm performance.
- Developing a universal ML workflow to process any type of users data (image and text)
- Experimentation techniques with ML models that improved performance and helped to achieve 85% accuracy on users’ data
- Instrumentation and feedback collection that will help drive future improvements by using incremental learning techniques
- Best practices in applying ML for optimizing the user experience working with Autodesk product
International students, DACA, immigrants, and other new Americans represent 13% of the US population and are growing. However, a lack of existing credit history prevents this population from accessing affordable loans. In this case study, we’ll share how MPOWER Financing – a large provider of financing to international and DACA students – uses an innovative, forward-looking credit model based on alternative data and new modeling techniques to provide affordable education financing to people with no or limited credit history.
IoT sensors are commonly used to monitor the environment inside shipping containers. Such monitoring provides valuable insights on the condition of cargo in real time. In many situations, however, guidance on preventive action (packaging, desiccant quantity etc.) is desired in the planning phase, i.e., before the first shipment has departed. In such situations, we can use the itinerary and weather data to model the climate inside the container. One key challenge in such modeling arises from unknowns. For example, an exposed container's climate is different from one stacked below others. Mapping weather + itinerary data to container climate is a representation learning problem, where the representation signifies the container's journey. Statistical characterization of container representations can inform the shipment planning process.
Given ML is here to stay, and growing in complexity by the day, it has become now critical that we think deeply about how to properly align our models with human interests. Doing this correctly requires a cultural shift in the way most organizations approach the model development process. Traditional metrics like F1, accuracy, or ROC on held-out test sets are woefully inadequate indicators of alignment when considered on their own. However, with the right tooling and a clear alignment framework, if we apply the principles of TDD (test-driven development) in a collaborative and transparent manner to ML development, we can not only build more performant models with greater velocity, but also instill far greater confidence in the models we are integrating into human lives.
To deliver world-class results while growing and retaining talent, the proper foundation of tools, practices, and leadership will be required. Brandon Southern has architected analytics environments for multiple organizations throughout his career and shows how and why it is important to incorporate standard software development, quality assurance, and project management practices into the analytics landscape.
In this keynote session, Brandon Southern discusses:- Architecting the analytics environment using a proven framework
- Educating and enabling analysts with the proper tools and training
- Structuring teams with a focus on elevating and retaining talent
Risk takes on many forms in the insurance industry, Underwriting Risk, Investment Risk, Operational Risk including Reputational Risk, Legal Risk Information Technology Risk & Process Risk. Predictive analytics can be used in almost all aspects of the company to help improve outcomes and reduce the associated risk.
In a post-pandemic world, technology is helping improve health outcomes, reduce costs, and streamline the administration of health benefits. Craig Kurtzweil, who oversees the use of data for the nation’s largest health care company, will outline how technology is changing when, where, and how people access the health system, to help improve health equity, better address social determinants of health and help prevent disease before it starts, resulting in higher satisfaction rates and lower costs.
During the identification of a problem and root cause analysis, traditional approaches include employing statistical design of experiments (DOE). In this presentation, the limitations of DOE will be compared to the advantages of utilizing "Big Data" and machine learning to find solutions. A case study from a manufacturing process using synthetic data highlights the ability to find "hidden variables" that lead to better solutions. By examining data from a whole process rather a narrow band available through DOE, the investigation is more effective with better results. The benefits of machine learning and model tournaments are highlighted.
While there is a lot of talk about the need to train AI models that are safe, robust, unbiased, and equitable - few tools have been available to data scientists to meet these goals. This session describes new open-source libraries & tools that address three aspects of Responsible AI. The first is automatically measuring a model's bias towards a specific gender, age group, or ethnicity. The second is measuring for labeling errors - i.e. mistakes, noise, or intentional errors in training data. The third is measuring how fragile a model is to minor changes in the data or questions fed to it. Best practices and tools for automatically correcting some of these issues will be presented as well, along with real-world examples of projects that have put these tools for use, focused on the medical domain where the human cost of unsafe models can be unacceptably high.
Despite the rapid evolution of AI, projects still fail at a disappointingly high rate. In the past, capturing data at scale and building models was the challenge, but today we're confronted with the issue of making AI more robust while avoiding the risk of unintended consequences. While the tools are new, many challenges remain the same.
In this talk, I will share by way of real-world examples improving business processes at a tier 1 trauma hospital that demonstrate:
- How to build the business case for an AI project (and get buy-in)
- Navigating AI project management to prevent failure
- How to mitigate the risks of unintended consequences from using AI
Product recommendation is at the heart of Personalization group’s efforts to help Albertsons customers. Deep Learning has become the go-to approach for recommendation. Therefore, the group has begun to put efforts into applying Deep Learning to enhance new product recommendations. First, leveraging transaction data and product catalog, we built Customer DNA and Product DNA models. Customer DNA model captures customer characteristics such as purchase behavioral pattern, dietary preference, e-com affinity, customer location, etc. and embeds into a list (vector) of numbers. Similarly, Product DNA model captures product characteristics (e.g., is product organic and/or sugar-free?) and product-product associations—e.g., bread and peanut butter are usually purchased together. Second, we leverage these models to build a next generation recommendation system—inspired by the Wide and Deep recommendation model architecture. Our experiments building the framework have generated favorable results and we will share our journey from model conception to putting it in production to better serve our customers.
In this session we will explore the various considerations and challenges associated with AI projects. Interactive case studies will be utilized to provide participants with a "hands-on" experience to convey a deeper understanding of the day-to-day decisions required to drive a project from idea to success.
Machine Learning (ML) models are quickly becoming ubiquitous and widely applied in banking. However, the use for high risk applications such as credit underwriting demands higher requirements in terms of model explainability and testing beyond performance evaluation. In this talk, I am going to share how we approach model interpretability without the potential pitfall of post-hoc explainers by employing inherently interpretable machine learning. Beyond interpretability, comprehensive testing to ensure model robustness and resilience are required for high risk applications. I'm going to discuss our approach illustrated by a tool that we recently released, PiML (Python Interpretable Machine Learning), an integrated environment to develop and validate machine learning models for high risk applications.
The massive dimensionality of genomic data combined with the lack of knowledge of gene function have been major barriers to the use of Artificial Intelligence (AI) in genomics. The number of population sequencing initiatives is rapidly increasing. As these large genomic datasets grow and become more widely available, the prospect of using artificial intelligence to gain insights from this data becomes more tangible and the use of such technology becomes even more important. In this session we review the current state and future directions of using AI with genomic data.
As Industrial organizations adventure in their advance analytics and AI journey to gain more insights from their data, organizations need to evolve and mature in the way they can interact and leverage data. These organizations need to deploy individuals who can provide the vision for this journey and lead their organizations how navigate it.
This is where the Analytic Translator role is essential to an organization's success. They are the visionary and guide to create a path from being overwhelmed by ineffective data and metrics within undefined business processes to effectively "organizing information" to inform key business decisions. This talk will discuss the role of the Analytic Translator to enable the advance analytics and AI journey, what skills are needed, and how they can lead their organizations effectively to secure the desired competitive advantage.
Product recommendation is at the heart of Personalization group’s efforts to help Albertsons customers. Deep Learning has become the go-to approach for recommendation. Therefore, the group has begun to put efforts into applying Deep Learning to enhance new product recommendations. First, leveraging transaction data and product catalog, we built Customer DNA and Product DNA models. Customer DNA model captures customer characteristics such as purchase behavioral pattern, dietary preference, e-com affinity, customer location, etc. and embeds into a list (vector) of numbers. Similarly, Product DNA model captures product characteristics (e.g., is product organic and/or sugar-free?) and product-product associations—e.g., bread and peanut butter are usually purchased together. Second, we leverage these models to build a next generation recommendation system—inspired by the Wide and Deep recommendation model architecture. Our experiments building the framework have generated favorable results and we will share our journey from model conception to putting it in in production to better serve our customers.
This talk provides a 3-dimensional framework for understanding professional competence and career progression. The framework covers primary skills (analytics), complementary skills (oft overlooked "soft skills"), and impact (how one's work advances the mission). Once defined, the speaker provides actionable guidance on how to develop a roadmap to achieve raises, bonuses, and promotions via a one-year plan. The content is optimized for early career professionals (<5 years experience) in need of guidance on how to move up and leaders of early career professionals in need of a framework to help cultivate their talent.
As John Deere continues to evolve as a technology company we must also look at bringing along existing systems and legacy data into this new world. With a fresh slate we can re-evaluate "the way we've always done it" and look to enhance the data experience for users of all skill levels. As we embrace cloud solutions for our data we can focus on things such as who should really govern data and why, how can we enable more users to load data that's important to them, and how can we reduce the barriers to entry for employees who are new to Data and Analytics and allow them to be successful.
This case study presents how Jetson Electric (ridejetson.com) adopted analytics to become a data driven decision maker based, better understanding its customers' mindsets and producing analytical use cases focused on operational efficiency.
In late 2021, Jetson was facing challenges in its after sales operations, especially in the brick-and-mortar retail sales channel. The company decided to try to use analytics to address the challenge. There were three pitfalls to pursue this agenda: Jetson's vision of analytics was technical, lacking business insights; the data lake was nonexistent; and the data was siloed and on the retailer's websites.
The Business Challenge drove the team and the technical evolution. The project analytically redesigned Jetson relationship with retailers regarding After Sales, focusing on total P&L, evaluating root cause analysis and better negotiating chargebacks and cashflow. The team combined techniques, using descriptive analytics, regressions and machine learning to structure the recommendation models. In parallel, the analytics tech operation was evolved by adding Databricks as the collaboration layer and structuring the data lake architecture and governance.
The results were impressive: double digit cost savings in after sales, a never-before achieved comprehension of end-customer mindsets, and data much more ready to use.
Despite the rapid evolution of AI, projects still fail at a disappointingly high rate. In the past, capturing data at scale and building models was the challenge, but today we're confronted with the issue of making AI more robust while avoiding the risk of unintended consequences. While the tools are new, many challenges remain the same. In this talk, I will share by way of real-world examples improving business processes at University Hospitals, a tier 1 trauma hospital: * How to build the business case for an AI project (and get buy-in) * Navigating AI project management to prevent failure * How to mitigate the risks of unintended consequences from using A
This talk is a technical overview of DeepMind and Google's recent work on reinforcement learning for controlling commercial cooling systems. Building on expertise that began with cooling Google's data centers more efficiently, we recently conducted live experiments on two real-world facilities in partnership with a building management system provider. These live experiments had a variety of challenges in areas such as evaluation, learning from offline data, and constraint satisfaction. Our paper describes these challenges in the hope that awareness of them will benefit future applied RL work. We also describe the way we adapted our RL system to deal with these challenges, resulting in energy savings of approximately 9% and 13% respectively at the two live experiment sites.
Rexer Analytics began surveying data scientists in 2007. This year's Data Science Survey is a collaboration with "Predictive Analytics" author and conference series founder Eric Siegel. In this session, Karl and Eric will present preliminary results from this year's survey. Topics will include algorithm choices, data science job satisfaction trends, deep learning, model deployment, and deployment challenges.
At Northwestern we have developed a system that is built to consume and capitalize on IoT infrastructure by ingesting device data and employing modern machine learning approaches to infer the status of various components of the IoT system. It is built on several open source components with state-of-the-art artificial intelligence. We will discuss its distinguishing features of being Kubernetes native and by employing our work that enables features to be specified through a flexible logic which is propagated throughout the architectural components. We will discuss select use cases implemented in the platform and the underlying benefits. The audience will learn how to build or use a streaming solution based on Kubernetes and open source components.
TRACK 2: TECH - Advanced ML methods & MLOps
The foundations and best practices are pretty obvious when it comes to developing software projects. The toolbox is filled with well-known products and the methodologies are so straightforward that it's almost impossible to get lost when operating large-scale software projects. The ML world, however -- as much progress as it may have made -- is still lacking such best practices and standards when it comes to operating at scale.
ML engineers' daily operations consist of a few pain points and problems such as collaborating with a team of other ML engineers on the same project, deploying models to production at scale, or just managing the different components assembling the average ml project. Although the solutions are out there, they have yet to become broadly adopted or accepted best practices in the industry.
In this talk, we will break down the operational issues that the average ML engineer runs into on a daily basis. We will list the possible solutions and tools available today that can solve these challenges. Finally, we will list some ML operation methodologies that have the potential of becoming the next world standard when it comes to developing an ML project at scale.
Leaders are starving for data-informed decision-making to increase revenue, reduce costs and optimize processes. However, they often face steep challenges spanning organizational structures, institutionalized processes, and a plethora of never-ending technology to operationalize their data. So how do you feed this appetite? Regardless of your company size or data & analytics maturity, you need to feed it through a well-coordinated "ecosystem" of capabilities enabling value from the wisdom found in data.
Corwin will walk through how to successfully implement and mature the capabilities enabled by the people, process, and technology necessary for operationalizing data & analytics while continuing to feed leaders a steady diet of understanding of what has happened and what will happen so they can make critical business decisions today.
TRACK 3: Cross-industry applications & workforce analytics
In this talk, Target's Senior Director of AI, Subramanian Iyer, will describe the challenges faced in developing demand forecasts at scale in the retail business and in securing adoption of these forecasts as well as improving collaboration among data science, product management, and forecast user teams.
Rexer Analytics began surveying data scientists in 2007. This year's Data Science Survey is a collaboration with "Predictive Analytics" author and conference series founder Eric Siegel. In this session, Karl and Eric will present preliminary results from this year's survey. Topics will include algorithm choices, data science job satisfaction trends, deep learning, model deployment, and deployment challenges.
Often data science teams, particularly in non-academic health systems where resources are scarce, will face difficulty in securing the green light for internal predictive modeling efforts. Along with technical requirements, equally important for realizing value are the strategies in presenting the business case for internal development to executive decision-makers. This case study will cover the process of advocating for data science teams in build vs. buy discussions through deploying a custom and adjustable Target Length of Stay model within clinical workflows in partnership with end users.
At Northwestern we have developed a system that is built to consume and capitalize on IoT infrastructure by ingesting device data and employing modern machine learning approaches to infer the status of various components of the IoT system. It is built on several open source components with state-of-the-art artificial intelligence. We will discuss its distinguishing features of being Kubernetes native and by employing our work that enables features to be specified through a flexible logic which is propagated throughout the architectural components. We will discuss select use cases implemented in the platform and the underlying benefits. The audience will learn how to build or use a streaming solution based on Kubernetes and open source components.
At Northwestern we have developed a system that is built to consume and capitalize on IoT infrastructure by ingesting device data and employing modern machine learning approaches to infer the status of various components of the IoT system. It is built on several open source components with state-of-the-art artificial intelligence. We will discuss its distinguishing features of being Kubernetes native and by employing our work that enables features to be specified through a flexible logic which is propagated throughout the architectural components. We will discuss select use cases implemented in the platform and the underlying benefits. The audience will learn how to build or use a streaming solution based on Kubernetes and open source components.
Industry 4.0 is here. AI, big data, the cloud, robotics, and smart devices are the enablers for building next-gen businesses. We need to focus on building skills to use these technologies that can dramatically multiply any business by strategically using data's latent, transformative potential.
Join our speaker Asha Saxena, CEO at Women Leaders in Data and AI [WLDA.TECH], Adjunct Professor at Columbia University and Author of The AI Factor, as she discusses the best practices, frameworks and how-to build tangible skills as a leader in today's business world.
MLOps provides a managed and optimized workflow for training, deploying and operating machine learning models and applications. More and more, ML models are now deployed at the Edge for use cases in manufacturing, logistics, healthcare and smart homes and cities. Edge deployments bring in unique challenges like resource constraints, limited bandwidth and unreliable networks. Existing cloud & enterprise MLOps needs to be adapted for Edge to overcome these constraints and maximize efficiency. This presentation will cover the unique challenges for machine learning and inference at the Edge, techniques and processes to overcome these challenges and how the MLOps workflow can be modified to adapt them. Data Scientists, MLOps Engineers and architects will benefit from understanding the unique challenges and best practices for ML at the Edge.
TRACK 2: TECH - Advanced ML methods & MLOps
As DoorDash's business grows, the volume of online ML predictions grows exponentially to support the various Machine Learning use cases, such as the ETA predictions, the Dasher (delivery person) assignments, the personalized restaurants and menu items recommendations, and the ranking of the large volume of search queries.
In this session, we will share our journey of building and scaling our Machine Learning platform to meet the DoorDash business growth. In addition, we will share a few lessons learned while optimizing the prediction service and how we measure success.
Setting customer value goals is difficult. We may think of them as the overarching goals of the business. It might be the way in which we assist clients, resolve issues, or otherwise provide value for them. In order to ensure the continued success of the company over the long term, we should aim to achieve a specific goal that will ensure the continued demand for the product among your target market. This specific metric set development will be demonstrated in the first section.
Measure True Performance: A good report is always basic and obvious, telling a narrative without the need for explanation. An individual perusing the metrics should have the thought, "Oh, I see that the new feature we introduced had a really favorable influence on engagement, but it didn't assist us to cut churn rate. Can you think of anything more we might do to cut down on turnover? " The art of developing intermediate metrics that will help figure out the main metric drivers will be demonstrated in the second section.
Lastly, specific predictive models that could be used to predict the performance of a business metric will be demonstrated.
TRACK 3: Cross-industry applications & workforce analytics
Based on case studies drawn from three industries – utilities, smart buildings/IOT, and logistics – Steven will show how following a repeatable development process helps get models consistently into production. The key takeaways include:
- Planning an AI/ML project: from finish to start
- How to work like a consultant and detect “actionable pockets”
- Learn how accuracy, relevancy, and ease of implementation will make or break your deployment… in unexpected ways.
The session will use examples in churn modeling, NLP, and predictive optimization to illustrate key points.
Reinforcement Learning (RL) agents proved to be a force to be reckoned with in many complex games like Chess and Go. Financial firms are leveraging the power of RL, given it potential to automate all the steps involved in algorithmic trading. However, it is quite challenging to understand and interpret a RL based models.
This talk focuses on an approach to understand and interpret Reinforcement Learning (RL) based trading strategies. We first briefly introduce the concept of reinforcement learning in the context of algorithmic trading, followed by demonstration of an RL- interpretability infrastructure. We then discuss possible derived outcomes of using this infrastructure when applied to trading a market instrument.
Defining the problem to solve for, defining the desired outcomes, understanding the type of data involved, and preparing the data appropriately are the four most critical aspects of machine learning in the research space – which will be presented in this session.
Industry 4.0 is here. AI, big data, the cloud, robotics, and smart devices are the enablers for building next-gen businesses. We need to focus on building skills to use these technologies that can dramatically multiply any business by strategically using data’s latent, transformative potential.
Join our speaker Asha Saxena CEO at Women Leaders in Data and AI [WLDA.TECH], Adjunct Professor at Columbia University and Author of The AI Factor, discuss the best practices, frameworks and how-to build tangible skills as a leader in today's business world.
In fintech, it's important for companies manage their credit risk because if customers don't repay their credit, the lender loses money. In this talk, we'll explore how to prevent credit risk using a neural network model. We'll discuss not only what worked, but also what didn't work, and how the building blocks of the full machine learning system. We start with one model and discuss how to layer on more of an ensemble approach to predict risky customers and take action in a way that doesn't cause them to become even more risky business. We'll discuss features, a neural network model, evaluation, serving, monitoring, and ideas to improve.
Machine Learning Week - Las Vegas - Day 2 - Wednesday, June 21st, 2023
Enjoy some machine learning laughs with Evan Wimpey, a predictive analytics comedian (and we're not just talking about his coding skills). No data topic is off-limits, so come enjoy some of the funniest jokes ever told at a machine learning conference.*
* Note the baseline.
Enjoy some machine learning laughs with Evan Wimpey, a predictive analytics comedian (and we're not just talking about his coding skills). No data topic is off-limits, so come enjoy some of the funniest jokes ever told at a machine learning conference.*
* Note the baseline.
Join us for a dynamic and entertaining keynote session on Data Storytelling with Gulrez Khan, Data Science leader at PayPal. Gulrez is known for infusing his presentations with humor and personal stories, making the learning experience both engaging and enjoyable. You'll be inspired by Gulrez's insights and experience as he guides you through the process of turning numbers into narratives. Discover how to craft compelling stories that bring your data to life, and learn how to share your insights in a way that engages, educates, and inspires your audience.
Join us for a dynamic and entertaining keynote session on Data Storytelling with Gulrez Khan, Data Science leader at PayPal. Gulrez is known for infusing his presentations with humor and personal stories, making the learning experience both engaging and enjoyable. You'll be inspired by Gulrez's insights and experience as he guides you through the process of turning numbers into narratives. Discover how to craft compelling stories that bring your data to life, and learn how to share your insights in a way that engages, educates, and inspires your audience.
Assessing safety and to ensure benefits outweigh risks is essential during clinical development of medicines and vaccines. Once approved and products are used more widely, healthcare provision can evolve as can the safety profile. Timely identification and monitoring of safety outcomes across multiple different types of healthcare data from around the world are crucial elements of product lifecycle management. The volume and heterogeneity of data means that quantitative approaches, including machine learning, play a critical role in sensitive, trusted, highly regulated systems to ensure patient safety. This session will describe current advanced analytics and barriers and opportunities for advances.
At the RealReal we take in between 10-20k items daily. For each item 3-6 images are taken for the item. Historically those images would be "retouched" by hand which include tasks such as aligning the mannequin, cropping at one of three fixed distances based on the length of the item, digitally removing the base of the mannequin and its shoulder seams all while providing a "luxury" feel. We've learned lots along the way to automating 87% of our supply saving 10's of millions each year.
While there is a lot of talk about the need to train AI models that are safe, robust, unbiased, and equitable - few tools have been available to data scientists to meet these goals. This session describes new open-source libraries & tools that address three aspects of Responsible AI. The first is automatically measuring a model's bias towards a specific gender, age group, or ethnicity. The second is measuring for labeling errors - i.e. mistakes, noise, or intentional errors in training data. The third is measuring how fragile a model is to minor changes in the data or questions fed to it. Best practices and tools for automatically correcting some of these issues will be presented as well, along with real-world examples of projects that have put these tools for use, focused on the medical domain where the human cost of unsafe models can be unacceptably high.
TRACK 1: BUSINESS - Analytics operationalization & leadership
Data scientists find insights that help lead to better understanding and better outcomes. When clients and managers come to us for help (and even when they don’t), we want to share our advice. While we should be free to share our recommendations, we need to be clear about what the data is telling us and what is based “only on our judgment”. Gelman, et. al. wrote “As we have learned from the replication crisis sweeping the biomedical and social sciences, it is frighteningly easy for motivated researchers working in isolation to arrive at favored conclusions—whether inadvertently or intentionally.” One senior business leader I know said, “If you have data, great; if we’re just going on intuition we can use mine.” This presentation will go through a number of examples and talk about the line between the data and judgment.
By 2025 more than 465,000 petabytes of data will be collected on a daily basis across the globe, however, only a fraction of a percent of this data is considered to be useful for analysis and models. In order to locate the most useful attributes, feature engineering is a vital skill for all data scientists and analysts. But how does a data scientist decide how to engineer the right features?
In this session, Brandon Southern explores:
- A framework for thinking like a business owner
- Developing a product and customer mindset
- Building new features that have saved millions of dollars in annual costs for top organizations
In the wake of the Pandemic, many corporations have faced unique challenges regarding employee engagement and retention. Over the past the past three years, as a society, we have witnessed mandatory work from home and lock downs, The Great Resignation and high turnover, and mandatory return to office. Each of these events have had their own consequences on employee engagement, well-being and happiness, and voluntary attrition. These events coupled with events such as mergers and acquisitions can amplify the effect of turnover in an organization. In this study we assess the internal and external factors leading up to voluntary attrition under such circumstances using predictive modeling.
In the life insurance industry, underwriting is an important process to assess the insurability of an individual. Traditional underwriting is often lengthy and expensive due to the requirement of blood and urine tests. The accelerated underwriting process replaces these lab tests with data and machine learning algorithms, thereby saving both time and money for the policyholders. The process made life insurance purchases easier and faster, thereby allowing the industry to serve a wider demographics and improve social good. This talk seeks to provide an overview of the AUW, emerging data sources, best practices, challenges, and regulatory implications.
This case study presents how Hospital Israelita Albert Einstein, leading Latam healthcare organization, utilized advanced analytics to determine the optimal layout for their new Cancer Center hospital. In 2021, as part of their expansion plan, they have decided to build a new Cancer Center in São Paulo, migrating their oncological operation to the new site.
The project for the new hospital was based on three pillars: Clinical Safety, Architecture and Operational Efficiency. The latter was the focus for the analytics’ team effort, using process mining, forecasting the future demand and optimization to generate the ideal layout to minimize movement flows.
The approach taken was based on 3 workstreams:
- Use of process mining to generate clinical pathways (CP) for all oncology patients in the current operation
- Clustering algorithms to classify the patients considering the different medical specialties used in their CPs
- An optimization model was developed, using mathematical models and metaheuristics, to receive the future demand for each CP along with resources’ requirements and generate the optimal layout suggestion
We captured impressive results: >15% reductions in movements for patients, visitors and materials and >8% for health staff, generating cost savings of approximately 3% of total operating cost.
Within the Human Resources industry there are still many challenges ahead, for example, keyword-based searches or manual resume screening could contribute to omitting valuable opportunities or lengthy hiring procedures. For this reason, we would like to present a novel Recommendation System in the field of HR, which includes a series of Natural Language Processing techniques and Deep Learning models, that allow us to achieve a fully automated process that will propose semantically related and explainable suggestions to job seekers and companies in real-time. The system architecture combines several NLP techniques, such as named entity recognition, text classification, and entity relationships based on HR data, to extract and process more than 50 different characteristics of job postings and resumes, such as occupations, skills, education, etc., with various granularity levels and multiple languages.
In this talk, we will talk through the journey of building an end-to-end forecasting platform with a focus on feature engineering, consolidation of features in a single place (feature store), and leveraging DNN techniques to solve different forecasting problems like Demand forecasting, Replenishment, Inventory optimization, etc. powered through the same platform
As part of the session, we will review the journey with the following stages :
- Feature Engineering: Experimentation to add critical features like Product Hierarchies, Price Rank Ratios, historical aggregated features, etc. along with their impact on the model accuracy
- MLOps : Use open-source Kubeflow to orchestrate and automate the data load, feature engineering, and Model training along with Model Deployment
- Decomposition of Forecast: Decompose forecast into Base & Promo forecast for What-if Simulation to identify the impact of Promos on Forecasts. Also, expanding the approach to inventory optimization.
Thought leaders in machine learning Dean, Karl and Steven, field questions from the audience about strategies for machine learning projects, best practices, and tips, drawing from their decades of experience as consultants and company executives.
Did my data change after a certain intervention? This is a common question with data observed over time. Classical statistical and engineering approaches include control charts to see if the series falls outside of the normal boundaries of expected data. A Bayesian approach to this problem calculates the probability that the data series changes at every point along the series. Bayesian change point analysis allows the analyst to evaluate a whole series and look where the highest probability of change occurred. Has the financial asset lost value after the recent financial report? Are the healthcare outcomes at this hospital better after our new process to help patients? Did the manufacturing process improve after upgrading the machinery? All these questions and more can be answered with these techniques.
People analytics lives at the intersection of statistics, behavioral science, technology, and the people strategy. To succeed in business, you have to understand and value people. All successful companies revolve around human needs. Business insights and decisions about human capital such as who to hire, what to pay them, what benefits to provide, whom to promote, and many more have a considerable unseen impact on the company's ability to meet customer needs, bottom-line performance, and reputation. Thanks to the prevalence of human resource information systems, plus the wide-scale accessibility of modern data collection, analysis, and visualization tools, human resources-related decisions can be made with data just like countless other business decisions.
TRACK 3: Cross-industry applications & workforce analytics
The focus of this session is on the use of machine learning in the workplace. This session will begin with an overview of the myriad ways machine learning (ML) is used in the workplace. We will provide practical insights into how machine learning can assist employers with workforce analytics and decision-making. We will flesh out the legal challenges and potential legal risks that may be associated with using machine learning in the workplace. The speakers will also provide an overview of current and pending laws impacting the use of ML in the workplace and attendees will learn about the considerations and risks employers are weighing when deciding how to use ML in their workplace. The speakers will also highlight common themes and questions that employers raise when considering ML vendors and partners. The speakers will provide real life examples of how some employers have successfully utilized ML in legally compliant ways and the lessons learned from other employers who have seen mixed results.
Retail shops need credit to purchase inventory. Credit dependence is more prominent with small retailers (mom & pop stores). In India, most of these stores don't use digital transactions or worse, don't even have bank accounts. Due to this, they can't get loans from banks as no credit score is present. In absence of formal credit, retailers depend on distributors (businesses who supply retailers inventory) to extend them line of credit (informal credit). Most of this credit offering is based on historical relations between retailer and distributor with no scientific premise. This credit is based on personal relationships without taking into consideration the actual worth of the shop -- therefore, there are high risks of loan default.
With data access of nearly 7.5MN retailers on real time basis we have enough retail transaction level data & hyper local data to train models that can predict credit worthiness of a store without need for any banking information . In this talk, I intend to explain how we use data along with the ML models to build Credit Score for Retailers. A major financial lender use this score to extend credit to retailer achieving lowest delinquencies in the industry
This talk provides a 3-dimensional framework for understanding professional competence and career progression. The framework covers primary skills (analytics), complementary skills (oft overlooked "soft skills"), and impact (how one's work advances the mission). Once defined, the speaker provides actionable guidance on how to develop a roadmap to achieve raises, bonuses, and promotions via a one-year plan. The content is optimized for early career professionals (<5 year’s experience) in need of guidance on how to move up and leaders of early career professionals in need of a framework to help cultivate their talent.
We illustrate here a Living Digital Twin of a fleet of Electric Vehicles that gives actionable predictions of battery degradation over time. Since each vehicle takes a different route and has different charging and discharging cycles over its lifetime, the battery degradation for each vehicle will be different. We use a scalable predictive modeling framework deployed across a distributed computing architecture in the cloud to make individualized predictions for each EV battery in the fleet to reflect the degraded performance accurately. The neural network battery model is calibrated using the parameters that had the most significant impact on the output voltage through the Unscented Kalman Filter (UKF) method, which is a Bayesian technique for parameter estimation of non-linear system behavior. We simulated in-production real-world operations by having the vehicles “drive” the routes using synthetic datasets and showed how the calibrated model provide more accurate estimates of battery degradation. Using a Living Digital Twin to calculate the remaining range and battery State of Health addresses problems of range anxiety in the EV automotive industry and can drive the value of EVs in the market.
ML’s great strength is that example cases are all you need to create a predictive model. The predictions work as long as the underlying process is not tampered with. But clients usually seek more: they yearn to understand the "data-generating machinery” in order to improve the outcome that the model predicts. Yet, this is dangerous without additional external information, including the direction of influence between variables. This talk illustrates how to achieve “peak interpretability” by using influence diagrams to model causal relationships, avoid mistaking correlation for causation, and quantify how outcomes will change when we manipulate key values.
ML’s great strength is that example cases are all you need to create a predictive model. The predictions work as long as the underlying process is not tampered with. But clients usually seek more: they yearn to understand the "data-generating machinery” in order to improve the outcome that the model predicts. Yet, this is dangerous without additional external information, including the direction of influence between variables. This talk illustrates how to achieve “peak interpretability” by using influence diagrams to model causal relationships, avoid mistaking correlation for causation, and quantify how outcomes will change when we manipulate key values.
ML’s great strength is that example cases are all you need to create a predictive model. The predictions work as long as the underlying process is not tampered with. But clients usually seek more: they yearn to understand the "data-generating machinery” in order to improve the outcome that the model predicts. Yet, this is dangerous without additional external information, including the direction of influence between variables. This talk illustrates how to achieve “peak interpretability” by using influence diagrams to model causal relationships, avoid mistaking correlation for causation, and quantify how outcomes will change when we manipulate key values.
Large language models are taking the machine learning industry by storm. Amid an outpouring of new research and exciting updates is the business question of how we can actually take advantage of this cutting-edge technology in the business world. Glean, an enterprise search engine that helps people find what they need and unearth things they should know across all their apps, is one of the only companies in the enterprise world which leverages LLMs jointly with enterprise data. We'll talk about lessons learnt from doing so, and how can enterprise companies build AI teams from scratch.
Model explainability or interpretability is often demanded, posed as a requirement. But not always. Under what circumstances is it pragmatically necessary (or even legally required) -- and, when it is called for, what exactly does it mean? Would it suffice to explain each model prediction by showing what differences in inputs would have changed the prediction? Or must the model be "understood" globally? Is understanding how the model derives its predictions sufficient, even without the why -- that is, without causal explanations for the correlations it encodes?
Join this expert panel to hear seasoned experts weigh in on these tough questions.
Model explainability or interpretability is often demanded, posed as a requirement. But not always. Under what circumstances is it pragmatically necessary (or even legally required) -- and, when it is called for, what exactly does it mean? Would it suffice to explain each model prediction by showing what differences in inputs would have changed the prediction? Or must the model be "understood" globally? Is understanding how the model derives its predictions sufficient, even without the why -- that is, without causal explanations for the correlations it encodes?
Join this expert panel to hear seasoned experts weigh in on these tough questions.
The largest issue ML teams face is due to AI models that silently fail. Silent failure occurs when model performances gradually degrade over time without showing any apparent signs of failure. These signs are therefore difficult to catch in time, usually leading to sudden or abrupt drops in performance after the gradual decline. This leads to a heavy impact on not just ML or business teams but also on the customer who faces the repercussions of incorrect predictions.
Pioneering tech giants have been managing silent model failures with AI Observability, and the positive results continue to encourage the AI industry to adopt observability practices. Observable AI enables a continuous collection of data from multiple touchpoints to deliver insights for improved model performance in production. It can be broken down into three high-level components: Monitoring, Explainability, and Accountability.
In this session, you will learn how to:- automate model monitoring
- dive deeper with root cause analysis to explain model decisions
- proactively troubleshoot your models to build reliable and compliant solutions that are resistant to silent model failures
The largest issue ML teams face is due to AI models that silently fail. Silent failure occurs when model performances gradually degrade over time without showing any apparent signs of failure. These signs are therefore difficult to catch in time, usually leading to sudden or abrupt drops in performance after the gradual decline. This leads to a heavy impact on not just ML or business teams but also on the customer who faces the repercussions of incorrect predictions.
While the role of the CDAO has gained popularity and spread across industries, there still exists a lack of clear expectations as organizations struggle to deliver business value from their data investments. It is well-documented that the first 90 to 180 days is critical for any leader, and this pressure is even more acute when there’s a mismatch between organizational aspirations and reality when it comes to analytics maturity. Join Brian Sampsel, VP of Analytics Strategy at IIA, as he explores best practices for data and analytics leaders who are new in their role and practical guidance in measuring your D&A efforts beyond the honeymoon period.
TRACK 1: BUSINESS - Analytics operationalization & leadership
As more products incorporate ML, engineering leaders face a unique challenge. How do I incorporate ML experts into my organization? How can I support ML expert growth and development and drive the largest impact with my ML team?
In this talk we discuss how the most effective organizations use ML in their product development cycles. First, we discuss how business leaders can counterbalance the uncertainty of ML workflows with project management processes that maximize impact and reduce risk. Next, we explore centralized and embedded ML teams and learn how leaders can optimize the cross pollination of ML and domain expertise.
The Data-verse is an ever expanding space. It is the task of data science to explore the fundamentals of this space. The tools and techniques being employed are having incredible impact across many different business verticals. One interesting area of exploration is to take concepts from Physics and apply them to data science problems. Physics at its essence focuses on reducing the complex physical world into a set of fundamental laws or axioms that govern it. In this talk, I will explore examples from 3 different business use cases where Physics served as inspiration in solving complex problems. The first example comes from marketing and product recommendations and adopts the concept of time dilation from relativity to solve a low recommendation problem. The second comes from IOT GPS transportation devices and uses the concept of spacetime and equivalence classes to characterize motion behavior. The last concept comes from logistics and developing an estimated time of arrival model using a Gradient Boosting Regressor. This focuses on using a “predictive motion†for model convergence.
Leading healthcare experts will discuss how they see data science in healthcare evolving in the near, mid and long term future.
Supply chains have been very lean for decades, and the challenges in the last few years have led more teams to focus on resiliency. With the quantity of data available across manufacturing, shipping, stocking, and inventory, teams can turn to analytics to improve the resiliency of supply chains. This talk will highlight how analytics has helped improve supplier reliability, decrease sourcing costs, and quantify the true risk of supply chain disruption.
As more products incorporate ML, engineering leaders face a unique challenge. How do I incorporate ML experts into my organization? How can I support ML expert growth and development and drive the largest impact with my ML team?
Tata Communications is a world class leader in international wholesale telecommunications. We have built proprietary tools to manage voice and messaging transactions including routing calls/messages to our thousands of suppliers. One such tool allowed us to make better routing decisions based on ML prediction models for both incoming attempts and performance of suppliers. The tool quickly allowed Tata Communications to become an efficient and profitable wholesale provider and outperform our competitors. However, the implementation of this tool had serious hurdles to overcome, not the least of which was commercial teams' adoption. In this talk, Mike Lawrence, Director of Business Intelligence, Operations and Transformation will cover the challenges faced and how the company overcame them in gaining support from Sales and Operations teams.
Today's AI tools can produce highly accurate results, yet advanced machine learning models often remain a black box. Transparency is essential when businesses are relying on AI more than ever. Explainability needs to be part of the equation when building AI systems we can trust. Organizations should start by including explainability as one of the key principles within their responsible AI guidelines by applying FEAT (Fairness, Ethics, Accountability and Transparency) for building responsible AI products. Through this talk, I will discuss how we can benefit from AI and minimize risk by making ML models explainable for businesses.
TRACK 2: TECH - Advanced ML methods & MLOps
High-quality data is imperative for every organization. While many automation systems can cleanse data through explicit programming rules, it requires manual intervention or additional data source plug-ins to fill in data gaps. We at Tata CLiQ leveraged AI/ML algorithms on the AWS platform to develop an intelligent Data Quality management system.One of the classic use cases is around Data Completeness. Information about Gender, age, etc., is incomplete in most organizations. However, these are critical while doing Gender-based personalization, especially for businesses like Lifestyle, Beauty, and General Merchandising. We have developed a Gender Identification algorithm based on Customer name, Transaction & Browsing history using NLP and Classification algorithm on AWS sage maker, leading to a 1.5-2x increase in Click-through Rate(CTR) for personalization content.
In this presentation, Finicity lead data scientist Natesh Arunachalam will provide a brief primer to Open Banking. He'll cover why Open Banking is a crucial technology for FinTechs and Banks, why it provides more power to the digitally native consumer, data assets that Open Banking provides, and application of AI in Open Banking, including use cases in risk scoring, NLP, and computer vision.
Ask our “Rockstars” anything about predictive analytics! Curious about machine learning tips, tricks, best practices and more? This is your opportunity to hear advice directly from the experts. The hardest part of machine learning can be getting models deployed into production. Our panel has done it, and is willing to spill the tea on how to make it happen. You’ll want to stick around for this ultimate session of the conference.
At Paychex, we used big language models like SBERT to match client inputted job titles to a taxonomy of 800+ job categories provided by the US Bureau of Labor Statistics. Our multi-level architecture combines SBERT with neural network classifiers to achieve high matching accuracy. The SBERT model was fine-tuned in a Siamese network approach to improve its performance. The product will be available to our clients to recommend the best matching BLS codes for their inputted job titles. Normalizing job titles will provide Paychex clients with advanced wage or retention analytics.
Workshops - Thursday, June 22nd, 2023
Full-day: 8:30am – 4:30pm PDT
Python leads as a top machine learning solution – thanks largely to its extensive battery of powerful open source machine learning libraries. It’s also one of the most important, powerful programming languages in general.
Full-day: 8:30am – 4:30pm PDT
This one-day session reveals the subtle mistakes analytics practitioners often make when facing a new challenge (the “deadly dozen”), and clearly explains the advanced methods seasoned experts use to avoid those pitfalls and build accurate and reliable models.
Full-day: 8:30am – 4:30pm PDT
Generative AI has taken the world by storm, scaling machine learning to viably generate the written word, images, music, speech, video, and more. To the public, it is by far the most visible deployment of machine learning. To futurists, it is the most human-like. And to industry leaders, it has the widest, most untapped range of potential use cases.
In this workshop, participants will get an introduction to generative AI and its concepts and techniques. The workshop will cover different techniques for image, text, and 3D object generation, and so forth. Participants will also learn how prompts can be used to guide and generate output from generative AI models. Real-world applications of generative AI will be discussed, including image and video synthesis, text generation, and data augmentation. Ethical considerations when working with generative AI, including data privacy, bias, and fairness, will also be covered. Hands-on exercises will provide participants with practical experience using generative AI tools and techniques. By the end of the workshop, participants will have a solid understanding of generative AI and how it can be applied in various domains.