San Francisco • Chicago • New York City
Berlin • Washington DC • London
Delivering on the promise of data science
Click here for upcoming PAW events

Full Agenda – Boston 2014
All level tracks Track 1 sessions are for All Levels
Track 2 sessions are Expert/Practitioner Level

Conference Day 1: Monday, October 6, 2014

8:00-9:00am • Room: Commonwealth Hall

Registration & Networking Breakfast


9:00-9:10am • Room: Amphitheater

Conference Chair Welcome

Eric Siegel Eric Siegel
Founding Chair
Predictive Analytics World

9:10-10:00am • Room: Amphitheater

Keynote
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!

Eric Siegel Sameer Chopra
GVP of Advanced Analytics
Orbitz Worldwide

[ Top of this page ] [ Agenda overview ]


10:00-10:30am • Room: Commonwealth Hall

Exhibits & Morning Coffee Break


10:30-11:15am • Room: Back Bay

All level tracks Track 1: Churn Modeling
Case Study: nTelos Wireless
Improving Customer Retention & Profitability

Churn Analytics helps companies identify and retain their best customers. See how one regional telecom used churn analytics, text analytics, and a test and learn strategy to achieve a return on their analytics investment of 653%, grow their core business, and compete against national wireless carriers.

John Ainsworth John Ainsworth
Senior Data Scientist
Elder Research, Inc.

Belinda RushingBelinda Rushing
Director of Customer Care
nTelos Wireless

10:30-11:15am • Room: Amphitheater

Track 2: Persuasion Modeling (aka Uplift Modeling)
Pinpointing the Persuadables: Convincing the Right Customers and the Right Voters

Marketing, political campaigning, and healthcare have one major thing in common: millions of per-person treatment decisions must be selected in order to drive positive outcomes. Prior to President Obama's reelection campaign, standard practices for persuading voters—that is, changing their minds—were unscientific and driven by long-standing assumptions and hunches. This mirrors outreach efforts by other companies and organizations, which know that a certain percentage of their marketing efforts will inevitably be wasted on people who are not going to be receptive to it. Daniel Porter of BlueLabs, who served as the Director of Statistical Modeling for the Obama Campaign, will discuss his experience using the results from a large-scale randomized, controlled experiment to target persuadable voters for the Obama Campaign, as well as ways these cutting edge statistical modeling techniques can be applied to influencing behavior in realms ranging from health outcomes to customer retention.

Daniel Porter Daniel Porter
Co-Founder
BlueLabs

11:20-11:40am • Room: Back Bay

All level tracks Track 1: Churn Modeling
Case Study: Paychex
Combat Client Churn with Predictive Analytics

In economic conditions such as this, it's critical for businesses to have a stronghold on their client retention efforts. Historically, it has been shown that businesses that excel in this arena are often better positioned for long-term success and possess a competitive advantage. To optimize the value of retained customers it's essential to understand which clients are a fit for retention campaigns so that the loss of time and resources is minimized. In this session, we examine how Paychex leveraged two existing models, Paychex Attrition Model and a custom built Lifetime Value Model, to create a Retention Tracking program.

Philip O'Brien Philip O'Brien
MIS and Portfolio Manager
Paychex


11:20am–12:05pm • Room: Amphitheater

Track 2: Uplift Modeling
Case Study: Fidelity
Uplift Modeling: Introduction, Applications, Comparisons, and Latest Developments

Uplift modeling is a method to find individuals who would be most positively influenced by a treatment (marketing, medical, social, etc.) while traditional methods may find those who would respond naturally without the treatment. It has become a key method for marketing, political election and personalized medicine, and has wide applications in other areas. This session will review the concept, applications and existing techniques, propose new cutting-edge techniques, and compare various techniques on actual data. Practical guidance will be given. Extension to non-randomized experiments or observational data and its link to the field of causal inference will also be discussed.

Victor Lo Victor Lo
Fidelity Investments
Bentley University

[ Top of this page ] [ Agenda overview ]


11:45am–12:05pm • Room: Back Bay

All level tracks Track 1: Customer Satisfaction & Retention
Case Study: Citrix
Predicting Customer Experience Risk in B2B World

Big Data and Data Science have become the new black in recent years, and the use cases for business-to-consumer companies, marketing teams, and sales teams are growing exponentially. At Citrix, we have been investing in Big Data technologies and Data Science methodologies with a business-to-business focus. How can we predict at risk customers and then leverage those insights to recommend actions that drive better customer experiences while also improving internal operational efficiencies? In this session, we'll discuss findings from our journey of predicting customer experience risk.

Mike Stringer Mike Stringer
Group Director
Citrix Data Science

Madhav ChintaMadhav Chinta
Director, Data Science Product Development
Citrix Data Science

Jim RegetzJim Regetz
Sr. Lead, Program Manager, Customer Insights
Citrix Data Science

[ Top of this page ] [ Agenda overview ]


12:05pm–1:30pm • Room: Commonwealth Hall

Lunch in Exhibit Hall


1:30-2:15pm • Room: Amphitheater

Keynote
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.

Mike Stringer Jack Levis
Senior Director, Process Management
UPS

[ Top of this page ] [ Agenda overview ]


2:15-2:35pm • Room: Amphitheater

Vendor Elevator Pitches

            

         


2:40pm-3:00pm • Room: Back Bay

All level tracks Track 1: Analytics Strategy
Case Studies: CFPB, Capital One, Citibank & Bank of America
Spotting the Wisdom in the Noise: Using Data Science to Identify and Eradicate Consumer Concerns

Data plays a critical role in making informed decisions to increase revenue, better serve customers and ensure future success. However, overwhelming data volumes can threaten to mask valuable nuggets of information vital to making strategic decisions. How can companies unearth this information to benefit their customers and business as a whole? Based on their work across multiple industries, Beyond the Arc will provide insight on:

  • Successfully tracking and managing useable data
  • Best practices for multichannel data analysis to identify valuable information
  • Leveraging predictive analytics to anticipate emerging issues and prioritize responses
Belinda RushingBrandon Purcell
Data Science Team Lead
Beyond the Arc, Inc.

2:40pm-3:25pm • Room: Amphitheater

Track 2: Infrastructure Planning
Case Study: Facebook
Managing Large-Scale Infrastructure with Predictive Analytics

This talk focuses on the use of data science to improve decisions about large-scale infrastructure. How do you plan for heterogeneous growth? How do you prepare for new product adoption? How do you predict risks and failures? In this talk we present some of our thoughts about how to use data science to manage and improve large-scale infrastructure.

Clinton Brownley Clinton Brownley
Data Scientist
Facebook

3:05pm-3:25pm • Room: Back Bay

All level tracks Track 1: Fraud Protection; Analytics in Gaming
Case Studies: Activision
Cheating Detection in Call of Duty

Call of Duty is the #1 video game on the planet... and some people cheat. When people cheat in the game (we call it 'boosting') it ruins the playing experience for other players. It also creates issues with our leaderboards, since people who are at the top of such boards might be boosters. We developed a detection system to catch these boosters that is similar to fraud detection systems used for credit cards and insurance. The gaming industry is exploding onto the analytics scene. This is a great example of how the industry is leveraging analytics to improve their games.

Arthur Von Eschen Josh Hemann
Principal, Game Analytics
Activision

[ Top of this page ] [ Agenda overview ]


3:25-3:55pm • Room: Commonwealth Hall

Exhibits & Afternoon Break


3:55pm-4:15pm • Room: Back Bay

All level tracks Track 1: Large-Scale Continuous Learning
Case Study: eBay
Importance of Speed and Relevance to eBay and Our Big Data Strategies

The pace in which eBay runs is at the pace of our customers' continuous, 24X7, reaching billions globally. Data is a mirror reflection of our customers and their experiences both on eBay and from other social/external sites. The faster we can proactively react to "happenings"¯ that occur globally with adequate context and understanding, the better eBay can provide more relevant and meaningful experiences and services to our customers and partners. eBay has implemented technologies to extend our speed of decision making and automated analytics across all our personas. In this presentation eBay will outline the business opportunity.

Gayatri Patel Gayatri Patel
Director, Analytics Platform Strategy & PM
eBay

3:55-4:40pm • Room: Amphitheater

Track 2: Workforce Analytics - Retention
Case Study: A Major Financial Services Call Center
Data Science Approach to Reduce Call Center Employee Attrition

This case study presentation by Talent Analytics Chief Scientist Pasha Roberts will provide details of how a major financial services call center used data science to significantly reduce attrition by over 30%, yielding a multi-million dollar savings. *Analytics managers will leave this session with a concrete understanding of the business value of talent optimization, showing how correlating "raw talent" to employee attrition can yield unprecedented results.*Analytics practitioners will leave this session with a concrete understanding of the analytics approach and models used to reduce attrition.

Pasha Roberts Pasha Roberts
Chief Scientist
Talent Analytics Corp.

4:20pm-4:40pm • Room: Back Bay

All level tracks Track 1:
Embedding Predictive Analytics Within the Corporate Culture-What are the Challenges in the Big Data World?

The discipline of predictive analytics has yielded tremendous changes in virtually all business sectors. Big Data and Data Science has simply reinforced the growing demand for predictive analytics. Yet, successful organizations in our Big Data World will embed predictive analytics as part of their corporate culture. But how do organizations do this? What are the structural and staffing changes that are required to instill predictive analytics as part of their corporate DNA? More importantly, what is the approach in not only building models but to socialize them throughout the organization to further reinforce the significance of this discipline?

This session will outline the challenges many organizations face in building the right team. Beyond just building the right team, it is the mechanics of project collaboration that is also a critical requirement for success. How do stakeholders manage the deliverables and expectations of a given predictive analytics project? Using a standard four step process in both building and executing predictive analytics solutions, attendees will learn how the key stakeholders interact throughout this process to ensure that deliverables and expectations are being met. This discussion will also focus on data and more importantly when it is worthwhile to look at more data (Big Data) to improve a given solution.

Richard Boire Richard Boire
Founding Partner
Boire Filler Group

[ Top of this page ] [ Agenda overview ]


4:45-5:05pm • Room: Back Bay

All level tracks Track 1: Workforce Analytics – Workload Management
Case Study: IBM
Data-Driven Transformation in End-to-End Sales Transaction Support

Workforce analytics enables IBM to efficiently manage and plan resources for its global sales transaction support. We describe use cases that focus on predictive analytics to support decisions on workload change and the number of resources required to support the workload. This ensures that we have sufficient resources to support the vast number of deals in the sales pipeline especially at the end of month or end of quarter. The audience will hear our experiences from aligning business analytics to data elements, to process transformation, to the business objectives.

Pitipong Lin Pitipong Lin
Sr. Technical Staff, Supply Chain Analytics
IBM

Pitipong Lin Aliza Heching
Research Scientist
IBM Thomas J. Watson Research Center

4:45-5:05pm • Room: Amphitheater

Track 2:Algorithmic Trading
Predictive analytics for Asset Managers

Session description coming soon.

James ScanlonSteve Krawciw
CEO and Head of Institutional Sales
Able Markets

[ Top of this page ] [ Agenda overview ]


5:10-5:30pm • Room: Back Bay

All level tracks Track 1: Risk Detection; Government Applications
Case Study: Office of the State Auditor
Risk Analytics Engine at State Auditor's Office

The State Auditor's Office is tasked with conducting financial, performance, and technical assessments of programs, departments, agencies, authorities, contracts, and vendors. Pioneering the adoption of Big Data Analytics in Government, the Office has built a novel Risk Analytics Engine capable of scanning large amounts of structured and unstructured data, automatically flagging potential problems and issues for further investigation, dramatically improving the operational efficiency and accuracy of the investigator's efforts.

Pitipong Lin Kleber Gallardo
Consultant
Alivia Technology

5:10-5:30pm • Room: Amphitheater

Track 2: Cloud Analytics
Case Study: Verizon
Third Generation Contextual Learning as a Service and Consumer Data-Haven Practice

In this session, we present the development and implementation of the third generation of our real-time contextual cloud learning platform central to the creation of a consumer data haven practice. We cover the technical challenges and constraints the team faced and the end-to-end solution we developed as we iterated through first generation commercial, second generation home grown and third generation Open Source. Result: 90% decrease in Total Cost of Ownership for the Big Data, enterprise workflow based PMML enabled cloud Machine Learning platform that is able to learn and anonymize consumer preferences in real time.

Madhusudan Raman Madhusudan Raman
Innovation Incubator
Verizon

[ Top of this page ] [ Agenda overview ]


5:30-7:00pm • Room: Commonwealth Hall

Networking Reception



Conference Day 2: Tuesday, October 7, 2014

8:00-8:45am • Room: Commonwealth Hall

Registration & Networking Breakfast


8:45am-8:50am • Room: Amphitheater

Conference Chair Welcome

Eric Siegel Eric Siegel
Founding Chair
Predictive Analytics World


8:50am-9:10am • Room: Amphitheater
Dell Logo

Diamond Sponsor Presentation
Realizing competitive value in the emerging Data Economy through Big Data Analytics

There is a new economy emerging, an economy based on data. This data is being generated, stored, sold, consumed and protected at a level commonly reserved for precious metals and currency. Companies gather this data every time they interact with a customer, partner, provider or competitor. Why is this data so valuable? Because companies can use it to better understand markets, customers and competitors and therefore greatly speed their time to market and quality of delivery. However, the data being generated today flows faster and is more complex than ever. Therefore, organizations must discover and evaluate new technologies and paradigms for analyzing the data and using it to make decisions. This session will outline those key use cases and explain how big data analytics can help drive more effective strategies and decision making.

John Whittaker John Whittaker
Executive Director – Data Management, Business Intelligence & Big Data Analytics
Dell

9:10am-10:00am • Room: Amphitheater

Keynote
Problems, then Techniques, then Toys. Keeping Your Predictive Analytics Right-side Up

Too many companies buy predictive modeling tools (and hire consultants) without first defining their analytics opportunities. Like the person who buys gym equipment at New Years and yet burns out before they lose weight, so do companies often burn out having nothing to show for their efforts but tools and lots and lots of Powerpoint slides.

Truly effective analytics work is about practical service to the business first and the trappings of big data second. No one cares what tools you have if you can't help solve their problems.

MailChimp sends 8 billion emails a month for 5 million customers worldwide, and the company has embedded predictive models all throughout its business. John Foreman, author of Data Smart and Chief Scientist for MailChimp, will discuss the experience of building these models and what it means to "lead from the back" in predictive modeling.

Eric Siegel John Foreman
Chief Scientist
MailChimp

[ Top of this page ] [ Agenda overview ]


10:00-10:30am • Room: Commonwealth Hall

Exhibits & Morning Coffee Break


10:30-11:15am • Room: Back Bay

All level tracks Track 1: Project Risk Assessment
Case Study: State Street Corporation
How Can Predictive Analytics Help Avoid $1.2 Million in IT Project Development Costs?

How can predictive analytics help avoid $1.2 million in IT project development costs, show the risk associated with projects, and help determine achievable scope? How can the customer accept the risks associated with such projects when faced with a Federal Reserve mandated deadline? Drawing upon actual projects I'll show how State Street uses a predictive analytics framework consisting of empirical data, statistical analysis, and a data-driven model that understands the behavior of development projects to assess project risk and help the project team and the customer trade off scope, cost, and time to avoid cost overruns while meeting deadlines.

Scott Lancaster Scott Lancaster
VP
State Street Corp.


10:30-11:15am • Room: Amphitheater

Track 2: Data Cleansing
Data Preparation from the Trenches: 4 Approaches to Deriving Attributes

The data preparation stage of predictive modeling is often viewed and the most time-consuming, with experts describing the time expended in this stage ranging from 50% to even 90%. One of the problems modelers encounter with data preparation is that the needs and solutions for data cleaning and creation of new variables (features) changes with each project or sometimes even within a single project because there is no theory that tells us what to do. This session focuses on four key principles used in the creation of derived variables. Examples from actual modeling projects will illustrate the principles.

Scott Lancaster Dean Abbott
President
Abbott Analytics, Inc.


11:15–11:35am • Room: Back Bay

All level tracks Track 1: Big Data
Case Study: Sears Holding Corporation
Hadoop Use Cases: Speeding Up Data Workloads

One reason organizations struggle to achieve value from big data is lack of a compelling business use case. Gain insight into practical uses for Hadoop by looking at specific ways big data technologies can be leveraged to enable business analytics by speeding up data workloads, Speed up ETL processing, Speed up mainframe batch processing, Speed up pricing optimization, fraud detection, network analytics, and more...These solutions - developed within retail, finance and healthcare industries - can be used by any organization facing similar data processing challenges to identify their own big data use case and create business value.

Andy McNalis Andy McNalis
Sr. Manager - Big Data / Data Warehouse Administration
Sears Holdings Corporation


11:15am–12:00pm • Room: Amphitheater

Track 2: Ensemble Models
Case Study: Citi
Predicting Hard Disk Device Failure Using Random Decision Forests

Hard drives are reliable, but data loss can be catastrophic when failures occur. Even with safeguards such as RAID and backups, the loss of a "live" hard drive is problematic. Alternative methods such as systems with built-in redundancy like Hadoop diminish cluster performance when the rebuilding replication or trying to read from a failed node. Thus, predicting drive failure before it takes place would have value not just from the data integrity perspective, but from a cluster performance perspective. The model developed exceeds performance of other models in the literature for hard drive failure prediction. SDSC SMART data was used.

Chris Simokat Chris Simokat
Vice President - Lead Data Scientist - Big Data & Analytics Engineering
Citi


11:40am–12:00pm • Room: Back Bay

All level tracks Track 1: Data Privacy
Predictive Analytics and Privacy by Design

This session will explain how predictive analytics professionals can incorporate Privacy by Design into their operations. Privacy by Design is an increasingly popular concept that enables organizations to build privacy commitments into the development of their operations, products and services. Traditionally, companies have only considered privacy issues after designing their products and services. Privacy by Design, in contrast, begins at the planning stage and continues throughout the lifecycle of a product or service. PbD provides numerous operational, risk management and legal benefits. But a successful PbD program requires employees throughout the organization to change how they think about privacy.

Jeff Kosseff Jeff Kosseff
Privacy & Communications Attorney
Covington & Burling, LLP

[ Top of this page ] [ Agenda overview ]


12:00-1:30pm • Room: Commonwealth Hall

Lunch in Exhibit Hall

[ Top of this page ] [ Agenda overview ]


1:30-2:15pm • Room: Amphitheater

Special Plenary Session
The Power (and Peril) of Predictive Analytics

Learning from data is extremely powerful and its use is transforming business decision-making in multiple industries at an accelerating pace - saving money and even lives. It's an exciting time to be a Data Miner! To be excellent at the work, we need to listen well - to transform a real-world challenge into a close, but solvable problem; we need to be expert in key technological methods, and we need to be keenly aware of our weaknesses in making judgments - including cognitive biases (for us humans) and lack of any sense (for our computer allies). I will share stories of warning and of encouragement, from a life in the field.

Jeff Kosseff Dr. John Elder
CEO and Founder
Elder Research, Inc.

2:15-3:00pm • Room: Amphitheater

Expert Panel
Necessary Skills of the Quant: Finance, Fraud, and Marketing

What makes a quant a true rockstar? What kind of soft skills, what kind of tech skills and background, and what portfolio of experience? With the organizational process behind predictive analytics - across business applications such as fraud and marketing - something of an art form, the requisite skills of key analytics staff are multidimensional and often hard to nail down. This expert panel will grab a hammer and start defining exactly what's needed in this very particular workforce.

Eric SiegelModerator: Eric Siegel
Founding Chair
Predictive Analytics World

Panelists:
Eric Siegel Sameer Chopra
GVP of Advanced Analytics
Orbitz Worldwide

Mike Stringer Jack Levis
Senior Director, Process Management
UPS

Mike Stringer Thomas Hill
Executive Director Analytics
Dell Software Group / StatSoft


3:00-3:30pm • Room: Commonwealth Hall

Exhibits & Afternoon Break

[ Top of this page ] [ Agenda overview ]


3:30-3:50pm • Room: Back Bay

All level tracks Track 1: Targeting Email
Case Study: Ameublements Tanguay
Predictive Analytics to the Rescue of Email Marketing

The ubiquity of information brought by the digital age made consumers more informed and demanding. This new paradigm stresses the importance of customer retention which lies in a deep understanding of their needs and behaviours. This situation is all the more significant in Email Marketing where customer's inboxes are flooded with irrelevant offers making it increasingly difficult to catch their attention. Intema will show you how this problem can be addressed with predictive analytics by anticipating customer's behaviour in order to generate relevant content all along the customer's lifecycle.

Eric Siegel Roger Plourde
President
Intema Solutions, Inc.


3:30-4:15pm • Room: Amphitheater

Track 2: Credit Scoring
Case Study: Kabbage
Data Science Approach to Small and Medium Business Lending

Traditional credit providers have been painfully slow in making underwriting decisions due to the lack of data processing technologies that enable fully automated processes. At Kabbage, we heavily rely on advanced predictive modeling to manage a fast growing portfolio of small businesses. We collect at runtime customer specific data from various sources including bank account data, online/offline sales, Intuit accounting data, Paypal payments, and so on. We implemented technologies that automatically predict the risk characteristics and future sustainability of these businesses to make better underwriting decisions. Attend this session to learn a machine learning approach to mitigate risk.

Pinar Donmez Pinar Donmez
Chief Data Scientist
Kabbage, Inc.

3:55-4:15pm • Room: Back Bay

All level tracks Track 1: Advertising Effectiveness
Case Study: Baseball Stadiums
A Fresh Look at the Effects of Promotion on Baseball Attendance Using Hierarchical Bayesian Analysis

Stadium attendance in baseball remains a valuable source of revenue and a proxy measure of popularity for most baseball organizations. A fresh-look at this data was undertaken using Hierarchical Bayesian analysis using observations across all teams for one season, which demonstrated wide variation across teams regarding effectiveness of promotions, types of promotions that worked, and the level of engagement of the fan base. The Hierarchical Bayesian also yielded credible intervals that help classify promotions into distinct tiers for each team.

Tyler Deutsch Tyler Deutsch
Graduate Student & Senior Consultant
Northwestern University & Sagence

Viswanath Srikanth Viswanath Srikanth
Graduate Student & Senior Software Engineer
Northwestern University & IBM

[ Top of this page ] [ Agenda overview ]


4:15-5:00pm • Room: Back Bay

All level tracks Track 1: Enterprise-wide Deployment
Oracle's Internal Use of Data Mining and Predictive Analytics

This presentation will present several Internal Oracle data mining and predictive analytics use cases and the results that have been achieved. Oracle uses data mining for campaigns to target customers who are most likely to buy certain Oracle products. Oracle mines customer data to predict which customers might be most likely to discontinue Oracle Service agreements. In Customer Service, Oracle monitors hosted database environments and anticipates run-time unhealthy behavior for our Database as a Service customers . Additionally, Oracle has enhanced Applications (e.g. CRM, HCM) that automate and embed pre-built predictive analytics methodologies for e.g. predicting future product purchases, predicting employee turnover, purchasing spend misclassifications, and real-time identity management. This presentation will also discuss experiences regarding the internal use of these new "predictive" applications.

Vladimir Babikov Charles Berger
Sr. Director of Product Management, for Data Mining and Advanced Analytics
Oracle

4:15-4:35pm • Room: Amphitheater

Track 2: Marketing Attribution
Case Study: LinkedIn
Increasing B2B Marketing Contribution through Optimal Marketing Attribution Analysis Techniques

In the B2B space, where the focus is on increasing revenue through sales, the role and contribution of marketing to reach the ultimate conversion is often questioned. Even if the contribution is established, it is often unclear in terms of how best to optimize the budget across the various marketing vehicles to improve conversion or accelerate the process. In this presentation, we will demonstrate how a multi-touch attribution approach was used to quantify the marketing contribution using clustering and sensitivity analysis techniques, which helps B2B marketers improve budget planning and program executions.

May Xu May Xu
Marketing Analytics Manager
LinkedIn

Neethi Mary ThomasNeethi Mary Thomas
Account Manager
Mu Sigma

Rajat MishraRajat Mishra
Regional Head
Mu Sigma

[ Top of this page ] [ Agenda overview ]


4:40-5:00pm • Room: Amphitheater

Track 2: Analytics Tools
Python for Data Science

The Python language combines human-friendly syntax, awesome libraries, and computational chops into one of the most powerful languages in the world today. I will give practical tips for how to leverage Python in your data science projects. Mostly this will be specific code tricks and libraries to use, but I will also discuss some more general principles (tradeoffs to make, code architecture, etc). To show you how this plays out 'in the wild', I will do a walk-through of a complete data science project. This talk is geared toward people who have a "hello world" familiarity with Python.

Field Cady Field Cady
Senior Data Scientist
Think Big Analytics

[ Top of this page ] [ Agenda overview ]

Share |
PAW Highlights Video

Sponsors

Talent Analytics, Corp

Boire Filler GroupExperian

Soft10
Predixion
University of California, Irvine Extension
wolfram

Wiley


DataRobot
dell


Blog Partners
© 2017 Predictive Analytics World | Privacy
Produced by Prediction Impact, Inc. and Rising Media, Inc.

Predictive Analytics Company           Predictive Analytics Event Producer