Conference Day 1: Tuesday, June 9, 2015
Registration & Networking Breakfast
Conference Chair Welcome Remarks
Predictive Analytics World
UPS Analytics – The Road to Optimization
Turning data into a business advantage through optimization is the goal of most organizations. The ever growing availability of data, along with expanding computing power and tools, opens the door to businesses gaining competitive advantage through analytical processes and skill.
Jack Levis, senior director of process management at UPS, will share his experiences and best practices to compete with analytics, requiring organizational support in the form of data, tools and senior management commitment. Analytics takes the general forms of:
- Descriptive analytics – Analysis of historical data
- Predictive analytics – Prediction of probabilities of future trends
- Prescriptive analytics – Evaluate new ways to operate
UPS has gone through a long evolution in moving up this analytical hierarchy which required organizational commitment and significant process change. While many lessons were learned along the way, the end result has been reduced cost, improved service to customers, and a data driven architecture for the future.
This presentation will show how UPS built upon a culture of engineering and quantitative analysis. Those core competencies are the foundation of systems reengineering efforts that use advanced analytics and connected devices. Examples of the changed processes will be presented as well as lessons learned from the journey.
Senior Director, Process Management
9:40-10:00am • Room: Salon A5
Diamond Sponsor Presentation
Analytics Everywhere and For Everyone
Over the past 5 years we have seen the redefinition of the economics of storing data, the proliferation of self-service data preparation and visualization and now we are starting to see the beginnings of automated analytics and the Internet of Things. Certainly there are many converging trends and numerous buzzwords to accompany and lead those trends. We will discuss all of these and how you can play a role in a making sense of them, leveraging them to your benefit and how analytics can help drive effectiveness and efficiency in your operations, marketing, manufacturing, governance, logistics and more.
General Manager for Advanced Analytics
Exhibits & Morning Coffee Break
Forrester's Review Of 12+ Predictive Analytics Tools
There is no "best" tool for predictive analytics. It depends on the skill level of the data scientist (or business analyst) and the breadth and depth of business use cases. In fact, data scientists often draw from multiple tools depending upon the job at hand. In this session, Forrester analysts Mike Gualtieri and Rowan Curran will present their in-depth analysis of more than 12 predictive analytics tools including: Alpine Data Labs, Alteryx, Angoss, Dell (Statistica), FICO, IBM, Knime, Microsoft (Azure Machine Learning), Oracle, RapidMiner, SAP, SAS, and others. Attend this session to understand the sweetspot for each of these tools and how to evaluate and choose the best tools for your situation and needs.
10:30-11:15am • Room: Salon A5
Track 2: Online Marketing
Case Study: SmarterHQ
The Revolution in Retail Customer Intelligence
In this new era of Big Data, retailers collect data in ever-increasing volume and variety. In the midst of Big Data, a revolution is taking place in how retailers gain insights about customers, whether they interact with the brand online, in stores, or both. This session will describe the transition from reporting to data-driven decisions using predictive analytics. Success requires collecting the right data, creating informative derived attributes, making this data accessible in a timely manner, and building predictive models. Examples, drawn from real-world retailers, will include shopping cart funnel management, shopping cart abandonment, marketing attribution, churn, and purchase propensity.
Also sign up for a one-day workshop by Dean Abbott:
Advanced Methods Hands-on: Predictive Modeling Techniques
Supercharging Prediction: Hands-On with Ensemble Models
Co-Founder and Chief Data Scientist
10:30-10:50am • Room: Mobley
Track 3: Sales Management
Case Study: Paychex
Shaping Sales Strategy with Predictive Analytics
Predictive modeling brings art and science together and without it many strategic decisions are left to instinct. This can lead to missed opportunities in the age of big data. Paychex leveraged expertise in Predictive Analytics to add an empirical layer to sales strategy decisions. With the addition of models to predict likely sales units and establish a yardstick to measure sales value by zip code, sales management became statistically informed as they made decisions regarding quota setting, territory alignment and market expansion. This session describes how Predictive Analytics at Paychex was granted a seat at the strategic table.
MIS and Portfolio Manager
10:55-11:15am • Room: Mobley
Track 3: Credit Scoring
Case Study: Mimoni (Latin America lender)
Using Predictive Models to Provide More Favorable Short-Term Credit Solutions for the Unbanked
For the millions of Latin Americans lacking a bank account, credit card, or significant credit history, fulfilling urgent credit needs often requires the use of pawn shops and very high-interest payroll deduction loans. Launched in Mexico in late 2013, Mimoni has used repayment, operations, and customer communication data to successfully develop predictive models of consumer behavior and repayment, helping them become the leading online lender for the unbanked in Latin America. In this session, we review Mimoni\'s application of predictive analytics in different aspects of the business, and their evolution going forward.
Head of Analytics and Software Development
Track 1: Political Campaigning
Case Study: Bruning for Governor Campaign
Campaigning with Predictive Analytics
Using Predictive Analytics and Data Science, we are going to show you how to help political campaigns win their race by providing campaigns information at the individual level using models that predict voter turnout, issue support, and candidate support.
Our case study for this session is a recent Nebraska Gubernatorial primary race where we were able to predict overall voter turnout to within 0.2% (637 votes) and the final voter count for our candidate to within 2% (1,676 votes).
Contemporary Analysis Inc. (CAN)
Track 2: Workforce Analytics
Case Study: An Organization's Sales Force
Time Series Clustering to Predict Sales Representative Growth, Performance, and Gaming
In the search for quality sales representatives, it is tempting to think that there is one successful "type" of rep. In fact, the data in this study suggest that there are multiple pathways of sales achievement. In this study we put aside simple aggregations to do it the "hard way" - by modeling low-level sales transactions. Using big data technologies, we analyzed millions of geo-located sales records for thousands of national sales reps. The analysis revealed several well-traveled pathways - some hit the ground running, some were gradual learners but eventually excelled, some gamed the system to win, many others failed.
Co-Founder and Chief Scientist
Talent Analytics, Corp.
Track 3: Customer Experience Management and Risk Mitigation
Case Studies: CFPB, CapOne, Citibank, and BoA
Fortune Tellers Need Not Apply: Leveraging Predictive Analytics and Big Data to Mitigate Emerging Risks and Improve Customer Experience
Across all of today's various business industries, data continues to play an increasingly important role in driving educated decisions, improving customer experience and maintaining success. The question plaguing many businesses, however, is how to use available data to mitigate emerging risks and customer complaints. Based on continual in-depth analyses of the CFPB's consumer complaint database, Steven Ramirez, CEO of Beyond the Arc, will discuss:
- How to utilize big data to predict customer issues
- The risks and threats of ignoring complaints
- Best practices for analyzing social media and customer feedback to identify and address potential issues
Beyond the Arc
Lunch in Exhibit Hall
The Balance Between Science and Practical Decision Making
As companies embrace the possibility of mounds of data turning into nuggets of gold- like diamonds in a coal mine- they face practical issues in extracting value out of powerful scientific theories. Data scientists by training often live in a world of facts, black and white and espouse a paradigm that is often not shared by business leaders that have grown up in a data and fact starved world. How does one make the transition from pure science to practical value in a way that drives sustainable transformation across a business and beyond the narrow confines of predictive analytics groups. How do you influence the current culture in a way that is both productive and empowering? This session focuses on the journey towards sustainable transformation with practical learning's and insights that are valuable to both the practitioner and aspiring leaders.
Senior Vice President
2:40-3:00pm • Room: Salon A2
Track 1: Data Asset Management
Strategies for Monetizing Big Data through Digital Platforms
We will examine how leading firms are developing dominant digital platforms for the creation of data assets. In many ways, the formation of data assets is a byproduct of other businesses. A car manufacture, for instance, installs a computer in a car to make it operate better, but the data generated by the computer on performance and use of the car is valuable to insurers and even municipalities. It creates opportunities, possibly, to sell or trade the data, which this session will explore.
Clinical Associate Professor
Kellogg School of Management
2:40-3:25pm • Room: Salon A5
Track 2: Hiring and Recruiting
Case Study: The Data Incubator
Data-Driven Hiring of Data Scientists
Hiring- even for data scientists- is often not very data driven. At The Data Incubator, we run a fellowship to train and place data scientists in industry, regularly receiving over 1000 applications per session. To cope, we rely on robust analytics and machine-learning for our admissions process to ensure we are finding the best talent for our hiring partner companies. We'll explain why most traditional keyword-driven screening processes do not work for finding data science talent and how to both streamline and build an automated data-driven screening processes that filters for skills and talent, not keywords and hype.
The Data Incubator
2:40-3:00pm • Room: Mobley
Track 3: Marketing; Advanced Methods
Case Study: A Financial Creditor
What Landing a Rover on Mars Taught us about Optimization of Marketing Strategies for Loan Portfolios
Analytical Mechanics Associates delivers big data analysis and predictive modeling for NASA to optimize trajectories and fuel consumption during flight. The chief constraint is mission success in all atmospheric and interplanetary conditions. The techniques developed and used by aerospace engineers (a.k.a. rocket scientists) are used by businesses to optimize marketing decisions with the chief constraint of being profitable in all economic and market conditions. In this presentation, AMA personnel will describe the work they do in big data, predictive modeling, simulation and optimization and talk about the similarities between landing a rover on mars and developing profitable marketing strategies for loan portfolios.
V.P., Modeling and Simulation
Analytical Mechanics Associates, Inc.
3:05-3:25pm • Room: Salon A2
Track 1: Digital Marketing
Case Studies: Cisco
Building a Digital Marketing Data Science Discipline at Cisco: Experiments to Excellence
Cisco's numerous business and operations centers have been aware of the power found within data for decades. But applying sustainable modern data science practices within the digital marketing organization remained a challenge. Bringing together the necessary leadership, collaboration and skills, Cisco's Digital Strategy team jump-started the organization to a path of sustained data science excellence. Learn the process, projects and organizational change required at Cisco that allowed it to make data science part of its DNA.
Senior Program Manager, Analytics
Digital Marketing Analytics Team Lead
3:05-3:25pm • Room: Mobley
Track 3: U.S. Federal Law Enforcement Agency
Case Study: Credit Card Fraud
21st Century Fraud Analytics (Detection) in a Predictive Analytics World
21st Century Fraud Analytics in a Predictive Analytics World will present an effective approach to fraud detection that discovers unusual patterns, identifies masses of red flags and aligns trends. Fraud/Predictive Analytics allows the capability of detecting duplicate payments, establishing patterns of fraudulent activities defined in insurance fraud claims, credit card fraud and mortgage fraud.
Fraud/Predictive Analytics confirms that fraud is always changing; therefore, methods should as well. In essence, fraud analytics has become the emerging tool of the 21st Century. It has aligned itself with more than one way to detect and deter.
Fraud Analytics Expert
United States Government Agency
Exhibits & Afternoon Break
3:55-4:40pm • Room: Salon A2
Track 1: Churn Modeling
Case Study: The Leading Cable Provider in South Africa
Improving Customer Payment Behavior Using Default Predictive Modeling
We present a case study driving subscriber payment behavior using default predictive modeling. We show how a formal approach using controls, allied with integrated operational deployment and enthusiastic business engagement led to a 45% improvement in revenue collection. We include a detailed look at uplift modeling and its utility in operational decision-making.
3:55-4:40pm • Room: Salon A5
Track 2: IT Workload Management
Case Study: IBM
Applied Predictive Analytics to Workload Automation
Managing workload is a challenge for IT administrators today, because it's not like some years ago when the most of the workload was managed in batch. Today, workload can be generated by mobile transactions, credit card payments, online purchases, etc. Predictive analytics can help to tame the unpredictability of the workload by identifying patterns and trends, providing hints for adequate sizing of the processing environments. The session reveals example where analytics can help.
IBM Workload Automation Chief Architect
3:55-4:15pm • Room: Mobley
Track 3: Insurance; Unique Data Assets
Case Study: TransUnion
What Unique Data Assets Reveal about Auto Insurance Shopping and Consumers
Distinctive data offers new and unique perspectives around auto insurance shopping and consumers. In this session, we'll discuss an in-depth analysis of personal passenger auto insurance shopping levels and trends and how credit data and shopping activity are combined with demographic data. We'll also test some commonly-held assumptions and surprising results. Finally, we'll share perspectives on who is on top of mind with auto shoppers, and look at details of trends and cyclicality in insurance risk.
4:20-4:40pm • Room: Mobley
Track 3: Insurance
Case Study: Risk Transfer (Insurance Agency)
Laying the Groundwork to Predict Risk Trends around Worker's Compensation Insurance
Risk Transfer is a leading provider of customized insurance solutions for the Professional Employer Organization (PEO), Temporary Staffing, and healthcare industries. Managing the various risk trends in these markets is not unlike managing a portfolio of stocks - the goal is to accurately balance, assess and predict risk in order to optimize on your business opportunities. This case study will highlight Risk Transfer's journey from simply getting data into a usable format to actually using it for data-driven decision-making. We will highlight key insights and lessons learned from laying the groundwork for future predictive analytics.
Director of Consulting
4:45-5:30pm • Room: Salon A2
Track 1: Hadoop for Predictive Analytics
Case Study: Financial Services and Online Advertising
Predictive Analytics: Best Practices for Generating Business Advantage
Reducing costs and increasing revenue are top of mind today. Predictive analytics has emerged as a primary use case for Hadoop to leverage various Machine Learning techniques. We will provide real-world financial services, online advertising, and retail use cases focused on utilization of predictive analytics to generate business advantage. We will discuss best practices for implementing predictive analytics with Hadoop -- data preparation and feature engineering -- to learning and making real-time predictions. We will discuss Mahout and Solr to deliver batch and real-time solutions. We will cover key operational considerations for effective model training and long-term business benefits.
4:45-5:30pm • Room: Salon A5
Track 2: Best Practices
Q&A: Ask Dean and Steven Anything (about Best Practices)
Preeminent consultant, author and instructor Dean Abbott, along with Beyond the Arc CEO Steven Ramirez, field questions from an audience of predictive analytics practitioners about their work, best practices, and other tips and pointers.
Co-Founder and Chief Data Scientist
Beyond the Arc
4:45-5:30pm • Room: Mobley
Track 3: Insurance; Churn Modeling
Case Study: A Fortune 100 Health Insurance Company
Journey: Customer Retention From the Bricks of Data to the Dome of a Model
An exciting journey of going from large amounts of customer data to a Cox Hazard Proportion Model to customer retention at a large healthcare organization. The session will focus on the approach from data gathering, enrichment to model selection and model building. We will discuss specifics around data gathering techniques, enrichment using Axciom and Dun & Bradstreet Data, data cleansing, creating new variables and subsequently running several algorithms and models to reduce the data and derive the insights. This very thorough approach represents a replicable process for many similar problems in the industry.
Senior Data Scientist
Conference Day 2: Wednesday, June 10, 2015
Registration & Networking Breakfast
Opening and Welcome
Diamond Sponsor Presentation
Blackjack Analytics: A Surprising Teacher from Which All Businesses Can Learn
Analysis in Blackjack (the most widely played casino game in the world) makes this game beatable. There are parallels which carry over to the application of analytics in the corporate world. Session will cover relevant case studies at Orbitz as well as general lessons from BJ that we can leverage in our work and lives. Chopra will also demystify card counting for the audience -- the goal is for the session to be fun as well as informative!
Chief Analytics Officer
Track 1: Public Health / Food Safety
Case Study: City of Chicago
Transforming Food Inspections Using Predictive Analytics
The Chicago Department of Public Health is innovating to lessen the burden on taxpayers and improve public health by engaging predictive analytics in their food safety protection program. The City of Chicago used existing data sources to develop a predictive model to forecast the critical violations of Chicago's 15,000 food establishments. The model combined data from multiple departments (previous inspections, crime, sanitation complains, business licenses, weather, and more) are inputted into a model which provides estimates on a restaurant's risk of having critical violations. The model and data are used to inform and drive business practice, leading to an increase in productivity.
Chief Data Officer, Department of Innovation and Technology
City of Chicago
Track 1: Advanced Methods
Nature Inspired Predictive Analytics Algorithms
Community Detection techniques are key in building predictive analytics model for social analytics, customer behavior analytics and fraud detection. Discovering a community in a social network is to detect a cluster of social members whose rate of interactions among those members is higher than of those outside of the social cluster. This talk will survey and highlight the present state of the art algorithms that are widely used in this space with a specific focus on biologically inspired techniques (Clustering Algorithms inspired from the natural bird flocking behavior - FlockbyLeader algorithm for community detection, and ant colonies for recommender systems) It is important to note that most of the major vendors of predictive analytics do not include biologically inspired algorithms in their suite of algorithms.
Visiting Assistant Professor of Computer Science
George Washington University
U.S. Census Bureau
Track 2: Uplift Modeling
Case Study: Telenor
Applying Next Generation Uplift Modeling to Optimize Customer Retention Programs
Organizations must constantly work to drive greater retention and revenue whilst spending less money and using fewer resources. In this session, hear how the world's 7th largest mobile operator has applied next generation "uplift" modeling (i.e. "net lift" modeling) to optimize retention programs and seen results 36% better than those possible using traditional analytic practices. Impressively, these results were reached while, at the same time, slashing the cost of retention programs by a staggering 40% – making this an ideal fit for today's recessionary marketing requirements.
Uplift models are different from traditional modeling in that the approach measures and predicts the true incremental impact of marketing activity. Whereas traditional models only aim to predict "behavior", uplift models actually predict the incremental "change in behavior." Telenor's novel approach and application was recently featured in Forrester Research's popular new report "Optimizing Customer Retention Programs", where the approach was shown to achieve an 11-fold increase in campaign ROI when compared with existing programs.
Chief Data Scientist
Exhibits & Morning Coffee Break
Track 1: Price Prediction
Case Study: Hopper
Buy or Wait? How the Bunny Predicts When to Buy Your Plane Ticket
Buying a plane ticket is a time-consuming and frustrating process that often leaves the consumer unhappy. Flight prices are less transparent and fluctuate more than almost anything else a consumer buys, even though airfare is one of the most expensive purchases for a typical family. On average, consumers spend almost two weeks comparison shopping but end up spending nearly 5% more than when they started looking. Ironically, all the variability in prices means that there are good deals to be found, but consumers lose out because they're only spot-checking prices occasionally. By watching continuously there's often a 5-10% lower price even within 24 hours, and the potential for further savings by picking the best time to buy.
Our goal at Hopper is to bring more transparency to pricing, by giving consumers advice about where and when to fly -- and when to buy -- to save money on their air travel. We believe this helps consumers buy more quickly, with less effort, and ultimately be happier with their purchase decision. One of our key features is our "when to buy" advice: we'll watch prices for your trip continuously and alert you when we think you should buy. The question is what makes a good deal? If we're too conservative and tell you to buy too early, we risk missing out on a better deal later, but if we're too optimistic and wait too long, you could end up paying more as prices rise towards your departure date. Because prices change in unpredictable ways, at the whim of the airlines, it's impossible to know for sure. But this session will outline the predictive approaches we use to make recommendations that save about 10% on average, and up to 40% in some cases.
Chief Data Scientist
Much of the analytics literature tends to focus on math and its potential to improve modeling lift. In this session, various mathematical techniques are explored across a variety of industries ranging from financial services, insurance, etc. in order to determine if certain techniques are more appropriate under certain conditions or industries. Yet, what about data. For example, do certain categories of data yield better modeling lift in certain industries or perhaps by model type such as retention vs. acquisition? The objective of this session is to provide practitioners with insight on how to better focus their efforts on improving modeling lift.
Boire Filler Group
Lunch in Exhibit Hall
Special Plenary Session
Top Five Technical Tricks to Try when Trapped
There's no better source for tricks of the analytics trade than Dr. John Elder, the established industry leader renowned as an acclaimed training workshop instructor and author -- and well-known for his "Top 10 Data Mining Mistakes" and advanced methods like Target Shuffling. In this special plenary session, Dr. Elder, who is the CEO & Founder of Elder Research, North America's largest pure play consultancy in predictive analytics, will cover his Top Five methods for boosting your practice beyond barriers and gaining stronger results.
Also sign up for Dr. John Elder's one-day workshop, The Best and the Worst of Predictive Analytics: Predictive Modeling Methods and Common Data Mining Mistakes.
CEO & Founder
Elder Research, Inc.
2:00-2:15pm • Room: Salon A5
Self-Service Data Prep and Visual Discovery to Bridge the IT and Business Gap
Self-service data preparation tools are rapidly being recognized as a necessary element to any data discovery or advanced analytics implementation. The Datawatch Managed Analytics Platform is an enterprise solution that bridges the gap between the ease-of-use and agility that business users demand together with the scalability, automation and governance needed by IT.
Chief Marketing Officer
Education and Training Options for Predictive Analytics
While it's easy to get excited about entering the field of predictive analytics, it's not so easy to choose from the many educational paths available. And decisions about training and education can be no less challenging to managers, who face many options in how to train existing staff, as well as many factors in how to evaluate the educational background of prospective hires. With forecasts warning of an analytics talent shortage, a lot is at stake for this growing industry. Our expert panelists will explore the educational options, and discuss how they're best navigated.
Session pre-study -- predictive analytics educational sources:
– PAW's popular, well-received one-day training workshops
– Complete list of degree programs in analytics, data mining, and data science
– Predictive Analytics Guide
Chief Analytics Officer
Director of Data Science
Thomas Hill, Ph.D.,
Executive Director Analytics
Dell Statistica Software, Information Management Group
Exhibits & Afternoon Break
Track 1: Market Mix Modeling
Case Study: A large soft drink manufacturer, leading OTC pharma company, and large gift based online retailer
Using Predictive Analytics to Funnel Your Way to More Profits: Marketing Mix Modeling & ROI Optimization
With the number of places to advertise growing every day, it is more important than ever to understand what works and what you should spend your advertising budget on. Because having a strong predictive analytics marketing mix can flat out improve Your marketing performance and make your company more money. Study after study has shown Predictive Analytics and Marketing Mix Modeling helps you: Drive an average 40% improvements in marketing effectiveness. We will cover a few mini-case studies, common methods for gathering and preparing data in the omni-channel world, real-world usage of algorithms, and the best outputs.
Predictive Analytics Practice Leader
Dunn Solutions Group
Track 1: Marketing
Case Study: Neustar
Using Predictive Analytics to Target with Better Precision
This session will outline how Neustar is using its own proprietary marketing analytics solutions to better understand its current customers and reach prospects with greater efficiency (in order to market analytics solutions -- this is a case of analytics "selling itself"). This includes looking across its brand awareness and demand generation campaigns to quickly get to the intelligence that matters most and make real-time decisions to deliver on key KPIs. Understanding campaign reach and frequency enables the company to fine-tune the channels that it uses (search vs. display vs. social) as well as its target audiences (based on demographics, geography, attributes, etc). In addition to using online analytics to justify digital marketing dollar spend, Neustar is leveraging predictive analytics (an essential part of the overall platform) to adjust its future media mix in order to drive higher conversions at a lower cost. The company is connecting the dots across the entire customer journey, attributing conversions, and seeing results - decreased inefficiencies of media spend along with increased reach, sales and brand value.
Sr. Director, Product Marketing
3:30-4:15pm • Room: Salon A5
Track 2: Advanced Methods
Case Study: Opera Philadelphia
Pricing and Segmentation Utilizing Menu-based Conjoint
At a time when many businesses are searching for analytics to support shift towards subscription-based models, many arts organizations, which historically rely upon season ticket holders, are looking at their business through a different lens and have yet to find a suitable analytical approach that accounts for the unique segments that exist in the market for arts. This presentation covers a quantitative survey of 2,000 individuals utilizing a menu-based conjoint design. The speaker provides an excellent discussion surrounding the integration of traditional segmentation methods (i.e., factor and cluster analysis) with one of today's most progressive pricing analytics techniques.
Track 1: Market Research
Case Study: National Consumer Panel (by Nielsen)
The Importance of an Early Win¯ in Promoting a Greater Predictive Analytics Capability
At National Consumer Panel (NCP), use of a predictive model score has enabled the organization to leverage select data to better evaluate the value of potential panelists before they are invited to join our panel, improving a number of KPI's. Success with this adopted business process has helped to lay the groundwork for building a more comprehensive database and promoting broader use of predictive analytics to generate efficiencies in additional business processes (e.g., reduce churn rates and reduce recruitment costs). Lessons learned include how to leverage an early win using PA to gain organizational acceptance and sponsorship.
Sr. Director, Measurement Science
National Consumer Panel
4:15-5:00pm • Room: Salon A5
Track 2: Unstructured data
Case Study: Next Principles
Going Beyond Numbers: Creating Business Value from Unstructured Data
A lot of unstructured data, such as text, images, speech and videos, contains quite valuable information that is not being utilized to the fullest by businesses today. In this presentation, we will discuss examples of using unstructured text data (reviews, comments, blogs, posts, articles, etc.) to develop predictive models and business insights for three use cases a look-alike modeling using social media conversations, content personalization using customer reviews, and sentiment analysis using data from blog posts and articles. We will also discuss various machine learning and big data technologies that are commonly used for analyzing large volumes of unstructured data.