Full Agenda – San Francisco 2012
All level tracks Track 1 sessions are for all levels.
Track 2 sessions are expert/practitioner level.

Sunday, March 4, 2012

Full-day Workshop
R for Predictive Modeling: A Hands-On Introduction

Click here for a detailed workshop description

Instructor: Max Kuhn, Director, Nonclinical Statistics, Pfizer

Monday, March 5, 2012


9:45am - 7:30pm

Exhibit Hall Open


8:00-9:00am • Room: Foyer

Registration & Breakfast

[ Top of this page ] [ Agenda overview ]


9:00-9:45am • Room: Golden Gate A

Keynote
Persuasion by the Numbers: Optimize Marketing Influence by Predicting It

Data driven marketing decisions are meant to maximize impact - right? Well, the only way to optimize marketing influence is to predict it. The analytical method to do this is called uplift modeling. This is a completely different animal from what most models predict: customer behavior. Instead, uplift models predict the influence on customer behavior gained by choosing one marketing action over another. The good news is case studies show ROI going where it has never gone before. The bad news? You need a control set... But you should have been using one anyway! The crazy part is that "marketing influence" can never be observed for any one customer, since it literally involves the inner workings of the customer's central nervous system. If influence can't be observed, how can we possibly model and predict it?

Speaker: Eric Siegel, Program Chair, Predictive Analytics World

[ Top of this page ] [ Agenda overview ]


IBM 9:45-10:05am • Room: Golden Gate A

Diamond Sponsor Presentation
Actionable Consumer Analytics: Restarting the Conversation

Today's consumers have higher expectations of personalization while leaving tremendous volumes of seemingly unrelated digital 'fingerprints' across many locations. The consumer experience lifecycle has been radically and irreversibly changed in the last five years. All organizational activity that drives the relationship such as optimizing operational costs, attracting new customers, monitoring patients, retaining students, capturing new markets, and leveraging social media will now more than ever heavily rely on coherent and agile decision and consumer experience management strategies. Predictive analytics tightly embedded within business processes increases operational agility while providing organizations with actionable consumer insights. Predictive analytics tightly embedded within customer and operational processes increases your ability to achieve that success.

Join us to learn how IBM is addressing consumer intimacy strategies by developing and implementing capabilities such as decision management, customer and social media analytics techniques leveraging business analytics technologies.

Speaker: Erick Brethenoux, Director, Predictive Analytics & Decision Management Market Strategy, IBM

[ Top of this page ] [ Agenda overview ]


Mu Sigma

10:05-10:10am • Room: Golden Gate A

Gold Sponsor Presentation

Speaker: Bhava Kompala, Director of Business Development, Mu Sigma

[ Top of this page ] [ Agenda overview ]


10:15-10:40am • Room: Exhibit Hall

Breaks / Exhibits


10:40-11:00am • Room: Salons 3-4

All level tracks Track 1: Analytics in the Cloud
Case Study
Five Growth Scenarios for Predictive Analytics in the Cloud

Predictive analytics and cloud technologies are hot topics individually, but how can you use them together? In this session industry expert James Taylor will discuss the use cases for predictive analytics in the cloud. He will show how companies at every stage of analytic sophistication can use cloud-based predictive analytic approaches, discuss the value propositions of the different use cases, outline the pros and cons of predictive analytics in the cloud, and present results from a recent survey on people's attitudes to these exciting technologies.

Speaker: James Taylor, CEO, Decision Management Solutions


10:40-11:25am • Room: Golden Gate A

Track 2: HR Analytics
Case Study: U.S. Special Forces
Hiring and Selecting Key Personnel Using Predictive Analytics

Hiring and selection of personnel in specialized work environments incurs huge direct and opportunity costs for organizations. One of the largest challenges is that the selection process is often left in the hands of those with either high experience in the domain area but little experience in selection or vice versa.

Predictive Analytics and statistics can play a critical role in formalizing and automating much of the selection process. This session provides an overview of the selection processes using both measures of skills and psychological measures to quantify IQ, domain knowledge, grit, and determination. Examples will be drawn from hiring practices for Special Forces (such as Army Rangers and Navy SEALs) and predictive analytics teams.

Speaker: Dean Abbott, President, Abbott Analytics

[ Top of this page ] [ Agenda overview ]


11:05-11:25am • Room: Salons 3-4

All level tracks Track 1: Crowdsourcing Predictive Analytics
Case Study: Wikipedia
Solving the Last Mile: Focusing Global Intelligence on Your Data

As companies gather and collect more and more data across their organizations, the "last mile" of actionable insights based on that data has become increasingly crucial to success. Public contests provide a potent, rapidly expanded means to facilitate vastly better predictions for your companies, by accessing over 16,000 leading data scientists around the world who compete to produce the best results for any given data problem. By correcting the existing mismatch between companies needing better predictions and data scientists wanting access to the most challenging problems and real world data, public competition proves over and over to be a "win-win-win".

Speaker: Karthik Sethuraman, Director of Analytic Solutions, Kaggle & Diederik Van Liere, Product Manager Analytics, Wikimedia Foundation

11:30am-12:15pm • Room: Golden Gate A

Special Plenary Session - Case Studies: Anheuser-Busch, Dept. Homeland Security, & US Postal Service Office of Inspector General
Becoming an Ace with a Robot as your Wingman

Humans and computers have strengths that are more complementary than alike to the point where a sophisticated algorithm may be the best "2nd person" to put on a complex task. By contrasting natural and artificial intelligence we will explore how to optimize the man/machine partnership.

Speaker: John Elder, CEO & Founder, Elder Research, Inc.

[ Top of this page ] [ Agenda overview ]


JMP

12:15-12:25pm • Room: Golden Gate A

Gold Sponsor Presentation
Discovering Fashionable Relationships

Speaker: James Steck, Advanced Analytics, Nordstrom, Inc.

[ Top of this page ] [ Agenda overview ]


12:25-12:40pm • Room: Golden Gate A

Lightning Round of 2-Minute Sponsor Presentations

                

[ Top of this page ] [ Agenda overview ]


Lunch sponsored by:
JMP

12:40-1:40pm • Room: Exhibit Hall

Birds of a Feather Lunch / Exhibits

[ Top of this page ] [ Agenda overview ]


1:40-2:25pm • Room: Golden Gate A

Special Plenary Session - Consumer Applications
Identity Wars: The Battle to Control Personal Data

Personal data is the doppelganger of the consumer, her very identity as a commercial being. Open the floodgates, as most of the vast quantities of enterprise data generated each day is - one way or another personal; data that's transactional, social, local, mobile and on and on.

As the leading players jockey for position, control is the name of the game, and the stakes couldn't be higher. We are early in the process of establishing a consumer identity ecosystem, standing on the cusp of major developments. New paradigms will be established and astounding enterprise power stands to be gained. Does anyone own consumer identity data? What precisely does "ownership" of personal data mean? In any case, the objective is not to own the transaction but to control the data it generates. Facebook and Google are central, but dozens of established enterprises and innovative startups are in the game.

In this special plenary session, Dr. Andreas Weigend will illuminate where identity data is, where it's going, and how to leverage it.

Speaker: Andreas Weigend, weigend.com, Former Chief Scientist, Amazon.com

[ Top of this page ] [ Agenda overview ]


Deloitte 2:25-2:35pm • Room: Golden Gate A

Platinum Sponsor Presentation
Predictive Analytics and Risk Ranking: Prioritizing the Investigation of Anti-Money Laundering Alerts

One of the biggest challenges a financial institution faces during AML transaction monitoring analysis is understanding how to prioritize its investigation efforts. More specifically, how does the financial institution identify alerted activity that may be more likely to contain AML violations? In this session, we will talk about the concept of risk triaging, or 'scoring' of AML alerts, which utilizes the predictive analysis of various transaction attributes and 3rd party data sources to assign a score, or a probability, to each alert to determine which may be likely to contain suspicious activity.

Speaker: Jeb Breese, Manager, Deloitte Financial Advisory Services LLP

[ Top of this page ] [ Agenda overview ]


Deloitte 2:35-2:45pm • Room: Golden Gate A

Platinum Sponsor Presentation
Managing Forward: Analytics For Today's Multi-Channel, Multi-Device Consumer

When done right, customer satisfaction measurement can yield more than just insights into how well your company, brand, or channel (e.g., web, mobile, store) is performing today. It can also predict the likelihood of customers to engage in critical future behaviors. However, not all methodologies are created equal. They must answer three essential questions of management while demonstrating success not only in theory but in the marketplace.

Speaker: Larry Freed, President & CEO, ForeSee

[ Top of this page ] [ Agenda overview ]


2:50-3:10pm • Room: Salons 3-4

All level tracks Track 1: Thought Leadership
Case Study: CA General Underwriters Insurance
Seize the Competitive Future through a Shared Vision for Value Creation, Quality Management & Collaboration

Predictive Analytics facilitates "anticipating future needs so we can actively create the future" (Drucker). Enrich it and your organization by creating more value from predictions, managing prediction quality and genuine collaboration among stakeholder teams. Stakeholders include your prediction financers, owners and users plus analytics developers, implementers and insurers. Explore "what to do and how to do it" for collaboration, quality management and value creation plus appreciate Drucker's Philosphies, Deming's Principles, Juran's Processes and Ackoff's Pitfalls. Tribal cultures and their immune systems are primary inhibitors of collaboration. To ensure competitive future success of Predictive Analytics, we need to selectively relax them.

Speakers: Arnold Goodman Arnold Goodman, Founder & Principal, Collaborative Data Solutions & Stephanie Behnke, President, California General Underwriters Insurance Company


2:50-3:10pm • Room: Golden Gate A

Track 2: Real Estate Market Scoring
Case Study: Altos Research
There & Back Again: Model Interpretability in Real Estate Market Scoring

Seasoned predictive analytics practitioners understand that simple "accuracy" is the beginning of model validation not the end. Perfect accuracy on your own training data is trivial. How confident are we in our predictions during truly unprecedented scenarios? The business builds confidence and optimizes "variance" by involving itself in the gritty modeling process. Black boxes are difficult for the business to interpret so improving robustness often means going back to more transparent models. Ben will present a case study in local residential real estate market scoring when non-parametric ensemble methods were left behind for marginally less accurate but interpretable linear models.

Speaker: Ben Gimpert, Chief Technology Officer, Altos Research

[ Top of this page ] [ Agenda overview ]


3:15-3:35pm • Room: Salons 3-4

All level tracks Track 1: Insurance
Case Study: Alberta Motor Association
Insurance Pricing Models using Predictive Analytics

The use of predictive analytics solutions as a pricing tool for insurance is a very recent phenomenon amongst actuaries. This case study examines what tools were used in the past and what has led to the adoption of predictive analytics solutions within the actuarial discipline. Particular emphasis is devoted to the significant data challenges which are unique to the insurance pricing sector. At the same time, attendees will learn the process that was adopted in building these tools. More importantly, attendees will understand how to demonstrate the value or benefit of predictive analytics solutions over existing actuarial tools.

Speaker: Richard Boire, Partner, Boire Filler Group


3:15-3:35pm • Room: Golden Gate A
Track 2: Branch Location Assessment
Case Study: YMCA Using Probabilistic Computing to Optimize YMCA Branch Site Locations

The YMCA operates a network of 2000+ branches, each of which is a $10M+ special-purpose investment. Predicting viability of new branch sites and benchmarking performance potential of existing sites is a high-value challenge which Seer Analytics has worked closely with the YMCA to tackle.

Seer recently evaluated probabilistic computing models for retail site location analysis. Seer's probabilistic models were developed in a week and were as predictive as a dedicated suite of logistic regression models developed over 18 months for the YMCA. The probabilistic models also generated per-estimate confidence intervals, offering unique insight into the risk associated with each prediction.

Speaker: Bill Lazarus, President & CEO, SeerAnalytics

[ Top of this page ] [ Agenda overview ]


3:40-4:00pm • Room: Salons 3-4

All level tracks Track 1: Insurance
Case Study: Broadspire
The First 24 Hours: Understanding New Claims

Broadspire, a claim administrator, gets thousands of new workers' compensation claims every week. Our internal methodology uses an expert research database, an intelligent interview process, and a sophisticated scoring tool to predict outcomes and resource needs for these claims as we conduct our three point interviews within 24 hours of the first report. We will present the high dollar business problem that this method addresses, examine the development of the system through five years of real world use, and show the ways in which it has improved the claim handling process and the bottom line for Broadspire and its clients.

Speakers: Gary Anderberg, Practice Leader of Analytics & Outcomes, Broadspire, Bangalore Gunashakar, Senior Technical Consultant, Broadspire & Sergo Grigalashvili, Vice President of Architecture, Analytics, Information & Communication Technology, Crawford & Company


KNIME 3:40-4:00pm • Room: Golden Gate A

Track 2: Sponsored Lab
Lab Session: Live Topical Demo
Heterogeneous Social Media Analysis: Network Analytics meets Text Mining with KNIME

Text mining social media data is slowly gaining in relevance and ease of use. At the same time, network analytic techniques are emerging that provide new analytic perspectives to social media data. This paper shows how combining text mining and network mining can reveal new heterogeneous insights into customer behavior in social media that were not detectable using either technique alone. Sentiment analysis from online forum posts together with reference structures from the quotation network allows not only the detection of negative or positive influencers but the relative weighting of those influencers in the underlying discussion forum. Originally performed for a major European telco, the techniques and methods presented here use publicly available data and the KNIME open source data mining platform to demonstrate the procedures and benefits of the analysis approach for social media. A conclusion is drawn about the relevance and practicalities of this new approach along with a recommendation for next steps.

Speaker: Rosaria Silipo, KNIME

[ Top of this page ] [ Agenda overview ]


4:00-4:35pm • Room: Exhibit Hall

Break / Exhibits

[ Top of this page ] [ Agenda overview ]


4:35-4:55pm • Room: Salons 3-4

All level tracks Track 1: Econometric Indicators
Case Study: LinkedIn
Econometric Applications & Extracting Economic Insights from the LinkedIn Dataset

Using examples from the LinkedIn dataset, this talk will highlight how applied economic intuition can be a valuable tool in extracting value from big data. We will discuss how econometric techniques expand the toolkit of data scientists, especially when trying to pull causation out of correlation in observational data. For example, what site activities are predictive of future engagement? The second part of the talk will show how big data helps us understand the effects of economic events, especially with regard to the recent financial crisis. We will discuss predicting economic indicators and uncover other insights related to the economy.

Speaker: Scott Nicholson, Senior Data Scientist, LinkedIn


4:35-4:55pm • Room: Golden Gate A

Track 2: Uplift Modeling
Case Study: MarketShare
Response Modeling is the Wrong Modeling: Maximize Impact
With Net Lift Modeling

The true effectiveness of a marketing campaign isn't response rate! It's the incremental impact - that is, additional revenue directly attributable to the campaign that would not otherwise have been generated. Yet traditional targeting criteria are often designed to find clients that are interested in the product, but would have bought it whether or not they received a promotion. In such cases, the incremental impact is insignificant and the marketing dollars could have been spent elsewhere.

Net Lift Models are designed to maximize incremental impact by targeting the undecided clients that can be motivated by marketing. These "swing customers" are akin to the swing states of a presidential election; data miners could learn a lot from presidential campaigns.

Beyond targeted marketing, Net Lift methodology delivers tremendous performance improvements for deployed churn models - retaining "savables" while avoiding the adverse "reverse" affects retention outreach triggers for some customers - as well as other innovative business applications of this advanced analytical method.

This session will demonstrate how to build Net Lift Models (also referred to as Uplift or Incremental Lift) that optimize the incremental impact of marketing campaigns, discussing the pros and cons of multiple core analytical approaches.

Speaker: Kim Larsen, Vice President of Analytical Insights, MarketShare

[ Top of this page ] [ Agenda overview ]


5:00-5:20pm • Room: Salons 3-4

All level tracks Track 1: Forecasting
Case Study: Wells Fargo Securities
Macroeconomic Forecasting, Consensus & Individual Forecaster: A Real-Time Approach

This study provides a real-time short-term macroeconomic forecasting approach that offers several advantages over conventional short-term forecasting procedures. The approach produces more accurate real-time forecasts compared to those of the Bloomberg real-time consensus forecast, on average, for major macroeconomic variables.

This study sheds light on five important areas of macroeconomic forecasting.

Speaker: Azhar Iqbal, Vice President & Econometrician, Wells Fargo Securities


5:00-5:20pm • Room: Golden Gate A

Track 2: Behavior-Based Advertising
Case Study: Yahoo!
How to Get the Exact Same Online Display Advertising Results with Only 55% of the Spending

According to eMarketer, the internet's share of total media spending will continue to rise, from 15% in 2010 to 20% in 2014 and the growth in online display advertising will outpace total online ad spending through 2014. The trend indicates greater online ad competition and the weaker and slowly improving economy means more spending pressure, so how to deliver the stronger ROI becomes a key success factor for all online marketers. Today I am introducing a strategy which will let you get the exact same online display advertising results with only 55% of the spending.

Speaker: Liwei Ma, Senior Director or Analytics & Insights, Big Fish Games

[ Top of this page ] [ Agenda overview ]


5:25-5:45pm • Room: Salons 3-4

All level tracks Track 1: Social Data
Case Study: Social Media Research Foundation
Crowd Photography for Social Media

Crowds of people gather in social media around many products, services, businesses, and events but they can be difficult to see and understand. With new free and open tools, it is now possible to map and measure social media spaces, capturing the sub-groups and key people within and between them. Learn how to capture social media data and quickly generate a visual map of the crowd. With maps in hand, we will discuss ways they guide a journey to the key influencers and concepts in the crowd.

Speaker: Marc Smith, Chief Social Scientist, Social Media Research Foundation


5:25-5:45pm • Room: Golden Gate A

Track 2: Behavior-Based Advertising
Case Study: CompassLabs
Prediction and Optimization Models for Online Display Advertising

A challenging task in online advertising is to identify a combination of the right advertisement to right customer on right website at right time. In this talk, I will present a data-driven approach we developed to estimate the likelihood that a user would click an online display advertisement based on a set of user and webpage characteristics. We used this model to identify the optimal campaign and its bid price for an ad space available for purchase on a real-time ad-exchange. Our model is currently being used by a startup company in providing online advertising solutions to Fortune 500 companies.

Speaker: Mahesh Kumar, CEO, Tiger Analytics

[ Top of this page ] [ Agenda overview ]


5:50-6:10pm • Room: Salons 3-4

All level tracks Track 1: Social Data
Case Study: A leading big-box retailer
Real-World Examples of How Big Social Data is Changing Traditional Business Practices

The social ecosystem has become the pulse of the world. With millions of users and billions of social activities passing through the ever-growing geo-enabled real-time social web each day, companies are reevaluating traditional business models. Through this session, participants will discover how one of the leading big-box retailer is applying insights gleaned from big social data and geography to change the way they operate. Participants will gain a understanding of how organizations can collect and apply location intelligence to their big social data to to produce results at a national and local level.

Speaker: Chris Moody, President & COO, Gnip & Bronwyn Agrios, Technical Marketing, Esri

5:50-6:10pm • Room: Golden Gate A

Track 2: Behavior-Based Advertising
Case Study: Interclick
Data, Data Everywhere: Navigating the Digital Ecosystem with Predictive Analytics

In today's digital ecosystem, the challenge marketer's face isn't access, but it is determining the application and value of data. This presentation will demonstrate how interclick has pioneered data-driven advertising technologies to find applicable online audiences to meet digital campaign goals. Our challenges are testing multiple predictive modeling techniques on Big Data to build effective audiences and making algorithms align with multiple goals.

Utilizing statistical data mining techniques such as hypothesis testing, collaborative filtering, and model ensemble, we have developed cutting-edge analytics products that recommend effective audiences with higher response rates in shorter time. Real results will be presented.

Speaker: Yuan Ren, Data Mining Scientist, Interclick

[ Top of this page ] [ Agenda overview ]


SAS

6:10-7:30pm • Room: Exhibit Hall

Reception / Exhibits

[ Top of this page ] [ Agenda overview ]


7:30-10:00pm • Room: Golden Gate A

Bay Area SAS Users Group Meeting

There's nothing ODiouS about ODS!
by Aaron Rabushka, INC Research, Inc.

SAS Marketing Automation: Application, Architecture and Security
by Sarmad Pirzada, MD, MPH

Click here for more information about this SAS User Meeting


useR Group Meeting • Room: Salons 3-4

Click here for more information about this useR Group Meeting

[ Top of this page ] [ Agenda overview ]



Tuesday, March 6, 2012

8:00-9:00am • Room: Foyer

Registration & Breakfast

[ Top of this page ] [ Agenda overview ]


9:00-9:45am • Room: Golden Gate A

Keynote
Influencers, Skeptics, and Data Geeks: Using Analytics to Drive Organizational Change

"What gets measured gets done" often is true when it comes to tactical execution. When applied to large-scale strategy, however, the implications of this adage are even more significant.

Advanced analytics can help reveal the true performance drivers in an organization. By leveraging the power of analytics in combination with the principles of change management, learn how to effectively lead your organization into a new era of operational success.

Speaker: Anne Robinson, Director of Supply Chain Strategy & Analytics, Verizon Wireless

[ Top of this page ] [ Agenda overview ]


SAS 9:45-10:05am • Room: Golden Gate A

Diamond Sponsor Presentation
Technology Strategies for Big Data Analytics

The exploding volume, complexity and velocity of big data present an increasing challenge to organizations, but also a significant opportunity to derive valuable insights. As organizations are tasked with managing massive data sets, it's clear that the value of big data will be derived from the analytics that can be performed on it. Analytics is the key to identifying patterns, managing risks and tackling previously unsolvable problems.

This presentation provides an overview of how to comprehensively address big data, including emerging strategies for information management, analytics and high-performance computing.

Speaker: Paul Bachteal, Director, Americas Technology Practice, SAS

[ Top of this page ] [ Agenda overview ]


10:05-10:35am • Room: Exhibit Hall

Breaks / Exhibits

[ Top of this page ] [ Agenda overview ]


10:35-11:20am • Room: Golden Gate A

Expert Panel
Wise Enterprise: Best Practices for Managing Predictive Analytics

Your company is trigger-happy for predictive analytics, and there's plenty of excitement, momentum and public case studies fueling the flames. Are you destined for success or disappointment? Is it a sure-fire win to gain buy-in for a promising analytics initiative, equip your most talented practitioners with a leading solution, and pull the trigger?

This panel of leading experts will address the holistic view. What are the most poignant and telling failures in the repertoire, and where is the remedy? Beyond the management of individual analytics projects, what enterprise-wide communication processes and other best processes provide best security against project pitfalls? Stay tuned for big answers to these big questions.

Expert Panelists:
Dean Abbott, President, Abbott Analytics
Erick Brethenoux, Director, Predictive Analytics & Decision Management Market Strategy, IBM
Kathy Lange, Senior Business Director, SAS Business Analytics Practice

[ Top of this page ] [ Agenda overview ]


11:20-11:40am • Room: Golden Gate A

Lightning Round of 2-Minute Sponsor Presentations

                  

[ Top of this page ] [ Agenda overview ]


IBM 11:45-12:30pm • Room: Golden Gate A

All level tracks Sponsored Lab
Lab Session: Live Topical Demo

In this session you'll learn about techniques to convert your predictive model outputs into actionable results. This "last step" in the modeling process improves the likelihood that your models will actually be used. You will see step-by-step examples of how to select key predictive model outputs and convert them into actionable results for your internal or external clients.

Speakers: John Guerrero, Predictive Analytics Solutions Architect, IBM & David Mould, Predictive Analytics Scientist, MedeAnalytics

[ Top of this page ] [ Agenda overview ]


12:30-1:30pm • Room: Exhibit Hall

Birds of a Feather Lunch / Exhibits

[ Top of this page ] [ Agenda overview ]


1:30-2:15pm • Room: Golden Gate A

Keynote
The Five Myths of Predictive Analytics

Predictive Analytics is powerful, it can help you predict an event or a behavior at a an individual customer level. It can help you spot golden nuggets from the deep-wide-big data ocean; But is also one of the techniques which is not very well understood. With all the recent buzz about Predictive Analytics, it does seems like a new technique in the tool box. Is that so? In this keynote, we will ground ourselves in the reality of building and maintaining an impactful Predictive Model and explore questions like

  1. Is Predictive Analytics new?
  2. Is it a crystal ball?
  3. Is it perfect?
  4. Can it be built quickly and cheaply?
  5. Is it going to solve all my business problems?
  6. Does it always work?
  7. Can anybody learn how to build a model?

Speaker: Piyanka Jain, CEO, Aryng.com, Former PayPal Business Analytics Head

[ Top of this page ] [ Agenda overview ]


Acxiom

2:15-2:20pm • Room: Golden Gate A

Gold Sponsor Presentation
Creating Vision Through Insights

Speaker: Garland Bond, Vice President of Acxiom Analytics & Consumer Insights, Acxiom

[ Top of this page ] [ Agenda overview ]


Acxiom

2:20-2:25pm • Room: Golden Gate A

Gold Sponsor Presentation

[ Top of this page ] [ Agenda overview ]


2:30-2:50pm • Room: Salons 3-4

All level tracks Track 1: Sports Analytics
Case Study: Major League Baseball
MLB Pitchers: A Look at the Numbers

Baseball enthusiasts and statisticians have found common ground in the field of Sabermetrics the application of statistics to baseball. Since the installation of the PITCHf/x tracking system in major league ballparks, data has been generated on the type, velocity, and displacement for every pitch thrown in the MLB. We present the findings from an investigation focused on MLB pitchers leveraging this treasure trove of information.

In this presentation we investigate how pitchers generate value. We discuss methods that explore pitching speed and control data simultaneously. We also identify the factors that are most important in determining value generation.

Speaker: Bartev Vartanian, Principal, Dataspora


2:30-2:50pm • Room: Golden Gate A
Track 2: Retaining Subscribers
Case Study: True-to-Life Anecdotes Based on Misc. Enterprise Successes Subscription Survival Modeling for Fun & Profit

Survival analysis started in reliability engineering and medical research. More recently it has been used by marketers to better understand customers in subscription based businesses. While the basic math doesn't change, there are practical differences when applied to marketing. First, N is huge. Secondly, there are generally many cohorts driven by marketing questions around product, offer, price, acquisition source, and various subscriber properties. In a series of case studies, you will learn the basic ideas behind subscription survival and how to calculate average lifetime, LTV, compare cohorts, and answer what-if questions. The data and code used are given to participants.

Speaker: Jim Porzak, Senior Data Scientist, Viadeo

[ Top of this page ] [ Agenda overview ]


2:55-3:15pm • Room: Salons 3-4

All level tracks Track 1:
The Potential of Text Mining

Instructor: John Elder, CEO & Founder, Elder Research, Inc.


2:55-3:15pm • Room: Golden Gate A
Track 2: HR Analytics
Case Study: An IT Support Firm & a Sales Workforce
Creating an Engaged Workforce using Statistical Learning

Top-performing organizations consider employee engagement as a key performance driver. Interviews and questionnaires are widely used to measure this engagement, yet results are often unreliable, discrete, and non-actionable. In this talk, we demonstrate how statistical learning can be used to estimate engagement from individuals' low-level activity data. Using prior knowledge and Bayesian frameworks, we have built a probabilistic model that incrementally learns every employee's true level of engagement. Results have helped organizations (an IT support firm and a sales workforce to date) to form cohesive teams that are more productive and engaged at the workplace.

Speaker: Salman Taherian, CFO & CIO, Kasra Technologies

[ Top of this page ] [ Agenda overview ]


3:15-3:55pm • Room: Exhibit Hall

Breaks / Exhibits

[ Top of this page ] [ Agenda overview ]


3:55-4:40pm • Room: Salons 3-4

All level tracks Case Study
Top 10 Data Mining Business Mistakes

Most analytics talks are technical describing algorithms, data management, software options, etc. that best extract value from data. And, great technology helps, in our experience, over 90% of projects to meet their technical goals. However, only about 65% of solutions seem to actually be deployed at the client organization. Astonishingly then, business risk has proven far greater than technical risk as an obstacle to realizing the huge ROI possible from predictive analytics.

This talk focuses on the business pitfalls of managing a data mining engagement, complementing John Elder's popular technical chapter on Top 10 Data Mining Mistakes (also covered during his post-PAW workshop). We address organizational and management mistakes commonly made by either the client or the consulting firm, and illustrate select ones with real-world examples. Anyone who is considering or actively engaged in mining data will benefit from these cautionary tales!

Speaker: Jeff Deal, Vice President of Operations, Elder Research, Inc.


3:55-4:15pm • Room: Golden Gate A

Track 2: Healthcare Analytics
Case Study: Pfizer
Right Medicine, Right Patient

Can predictive modeling improve patient care? A wealth of data exists in large healthcare databases on patient disease characteristics and their response to specific treatments. Max will discuss some of the technical and non-technical issues in providing care providers with quantitative results related to how individual patients might response to therapies.

Speaker: Max Kuhn, Director of Nonclinical Statistics, Pfizer

[ Top of this page ] [ Agenda overview ]


4:20-4:40pm • Room: Golden Gate A

Track 2: Clinical Healthcare
Case Study: Sisters of Mercy Health Systems
Framework for Detection of Clinical States & Disease Onset Using Electronic Health Record (EHR) Data

This case study describes the application of predictive analytics to the detection of disease onset and clinical states through the use of electronic health records (EHR). The framework presented here aims to improve prediction of a patient's risk for developing severe sepsis and septic shock through a risk score generated as a function of measurements of patient vitals over time. A risk score threshold of 0.71 was found to yield the highest sensitivity while minimizing false negatives in the patient database. This predictive model can also be generalized to predict outcomes of other application domains.

Speaker: Jeni Fan, Associate, Booz Allen Hamilton

[ Top of this page ] [ Agenda overview ]


4:45-5:05pm • Room: Salons 3-4

All level tracks Track 1: Agile Analytics
Case Study: Kelley Blue Book
Agile Analytics: Model Development in an Agile Environment

Technology organizations have been using Agile development for more than 10 years to promote adaptive planning, development and delivery of software. In this session, discover how the Kelley Blue Book predictive analytics organization leverages agile analytics to increase team collaboration, reduced spin and improve cross-functional communication/relationships. Agile analytics has imparted structure in a seemingly unstructured development process, improved overall model performance and increased business owner acceptance. Discussion will provide analysts and analytics leadership with an effective framework to improve model efficiency, accuracy and applicability.

Speaker: Shawn Hushman, Vice President of Advanced Analytics, Kelley Blue Book


4:45-5:05pm • Room: Golden Gate A

Track 2: Fraud Detection
Case Study: USPS Office of Inspector General
Fraud Detection: Fraught with Frightful Modeling Hurdles

Building predictive models to find fraud, waste, and abuse can be an especially tricky application of data mining. Complicating factors include: frequent lack of training cases, ever-changing patterns as fraudsters adapt their schemes, high sensitivity to false positives, and the relative rarity of fraud. We describe approaches to tackling these modeling hurdles, and highlight them with examples from our consulting projects in the commercial and government arenas.

Speaker: Antonia de Medinaceli, Director of Fraud Analytics, Elder Research, Inc.

[ Top of this page ] [ Agenda overview ]


5:10-5:30pm • Room: Salons 3-4

All level tracks Track 1: Non-Profit
Case Study: Volunteers of America, Chesapeake
Turning Operational Outcome Metrics into an Actionable Predictive Forecasting Model

Analysis of program operation/case management outcomes often involved weeks of labor to decipher relationships and identify those that had a meaningful impact on organizations financial forecast. Nimble human service non-profits and social service agencies are starting to leverage the power of open-source Analytic tools like R and the native algorithms available to build robust Predictive modeling within their budgeting process. Already committed to a cloud computing platform and having a limited budget, learn how VOA leveraged cloud services and open-source components to create a robust dashboard and reporting solution for our executive management team.

Speaker: Shyam Desigan, CFO, Volunteers of America, Chesapeake


5:10-5:30pm • Room: Golden Gate A

Track 2: Blackbox Trading
Case Study: ZZAlpha
Effective Market Forecasting in 5 Key Dimension

We demonstrate that a machine learning technique predicts relative future price in five key dimensions of the US equities market. The price forecasts answer key investment questions: In or Out of the market, Value or Growth style, Large or Small cap, Which is best sector, and What is the direction of the economic core. Forecasts are implemented using large ETFs. Returns exceed benchmarks and risk is reduced. Large Monte Carlo simulations confirm statistical confidence exceeding 3 sigma (99.7%).

Speaker: Kevin Pratt, Founder & Chief Scientist, ZZAlpha

[ Top of this page ] [ Agenda overview ]


Wednesday, March 7, 2012

Full-day Workshop
The Best & the Worst of Predictive Analytics: Predictive Modeling Methods & Common Data Mining Mistakes

Click here for a detailed workshop description

Instructor: John Elder, CEO & Founder, Elder Research, Inc.

[ Top of this page ] [ Agenda overview ]


Workshop sponsored by:
IBM

Thursday, March 8, 2012

Full-day Workshop
Advanced Methods Hands-on: Predictive Modeling Techniques

Click here for a detailed workshop description

Instructor: Dean Abbott, President, Abbott Analytics

[ Top of this page ] [ Agenda overview ]


Thursday, March 8, 2012

Full-day Workshop
Making Text Mining Work: Practical Methods and Solutions

Click here for a detailed workshop description

Instructor: Dr. Andrew Fast, Director of Research, Elder Research Inc.

[ Top of this page ] [ Agenda overview ]


Friday, March 9 & Saturday, March 10, 2012

Two-day Workshop
Net Lift Models: Optimizing the Impact of Your Marketing

Click here for a detailed workshop description

Instructor: Kim Larsen, Vice President of Analytical Insights, MarketShare

[ Top of this page ] [ Agenda overview ]

Share |


PAW Highlights Video
PAW Conference Preview

Exhibit Hours
Monday, March 5:
10:00am to 7:30pm

Tuesday, March 6:
9:45am to 4:30pm

Sponsors

IBM
SAS

deloitte
Foresee Results

acxiom
JMP
Mu Sigma
Teradata
Birst
StatSoft
SAP
StatSoft
StatSoft

FICO
Forio
Fuzzy Logix
Opera Solutions
PROS (NYSE: PRO)
Pervasive Software
Salford Systems
TIBCO

Boire Filler Group
InfoCentricity
Inside Sales
KXEN
Yottamine
Zementis

Table top Sponsor
Page One

Mobile Sponsor
SAS

Past Sponsors
Check out the official PAW Blog Partners

© 2014 Predictive Analytics World | Privacy
Produced by Prediction Impact, Inc. and Rising Media, Inc.

Predictive Analytics Company           Predictive Analytics Event Producer