June 10-13, 2013
Chicago, IL
Delivering on the promise of data science
Click here for upcoming PAW events

Full Agenda – Chicago 2013
All level tracks Track 1 sessions are for All Levels
Track 2 sessions are Expert/Practitioner Level

Conference Day 1: Tuesday, June 11, 2013

8:00-9:00am • Room: W183

Registration & Networking Breakfast

[ Top of this page ] [ Agenda overview ]

9:00-9:05am • Room: W184 B/C

Conference Chair Welcome Remarks

Speaker: Eric Siegel, Founding Chair, Predictive Analytics World

9:05-9:25am • Room: W184 B/CAbsolutdata

Sponsor Presentation

Speaker: Guha Athreya, Sr. Manager, Analytics, AbsolutData

9:25-10:15am • Room: W184 B/C

Case Study: City of Chicago
Lessons from Year 2: Operationalizing the Principles of Predictive Analytics

Government has long lagged behind the private sector's use of data, but the new administration in Chicago is working to change that. When he came into office in 2011, Chicago Mayor Rahm Emanuel appointed Goldstein to be the nation's first municipal Chief Data Officer; as of June 2012, he now serves as both Chicago's Chief Information Officer and CDO. Beginning to use data meaningfully in Chicago has presented many challenges and opportunities. In this presentation, the CDO will discuss the tactics and tools that help bring analytics into government and will share examples of success from the first two years. Projects include: citywide data documentation, creation of a common operating platform using NoSQL geospatial capabilities, and development of a framework to predict service needs around the City.

Speaker: Brett Goldstein, Chief Data Officer, City of Chicago

10:15-10:40am • Room: W183

Exhibits & Morning Coffee Break

[ Top of this page ] [ Agenda overview ]


10:40-10:50am • Room: W184 D

Track 1:
Gold Sponsor Presentation
Driving Marketing ROI across On-Line and Off-Line Channels

During the session we will talk about an approach to maximize ROI and generate incremental business in a multi device, multi channel environment – experiences in Travel & Hospitality sector.

Speaker: Guha Athreya, Sr. Manager, Analytics, AbsolutData


10:40-10:50am • Room: W184 B/C

Track 2:
Gold Sponsor Presentation
muPDNA – Encoding Intelligence

Defining, articulating and representing business problems is a crucial first step in any analytics initiative. Getting business problem definition, analytical design and data selection right heavily influences the efficiency and efficacy of all downstream tasks along the analytics value chain. This session will briefly introduce the reason why muPDNA is "the Solution" – leading to the right design, hypotheses and representation.

Speaker: Mukund Raghunath, Geography Head, Mu Sigma

10:50-11:35am • Room: W184 D

All level tracks Track 1: Social Data
Overview: Predictive Analytics and Social Data for Marketing

This introductory session overviews the application of predictive analytics to marketing, and covers ways in which predictive analytics drives better marketing with the use of social data. Predictive analytics can use all the help -- and all the data -- it can get. No data predicts like social data: who a customer knows, what sentiment he or she expresses, and which things the customer Likes.

Speaker: Eric Siegel, Founding Chair, Predictive Analytics World

10:50-11:35am • Room: W184 B/C

Track 2: Optimizing Price Info Flow
Case Study: Orbitz Worldwide
Hotel Pricing: Survival Analysis for Cache Time-to-Live Optimization

The volume of hotel requests received by Orbitz each day is too great for supplier systems. Thus, Orbitz caches hotel rates locally. But cached information can go stale since hotel rates can change. Thus, each hotel rate in the cache is given a time-to-live (TTL) after which point it is discarded. In this session, we'll show that by using a technique known as survival analysis to model hotel rate volatility to guide our selection of TTL values, we see both a reduction in the number of requests sent to suppliers as well as the number of stale rates delivered from our cache.

Speaker: Robert Lancaster, Solution Architect, Orbitz Worldwide

[ Top of this page ] [ Agenda overview ]

11:40am-12:25pm • Room: W184 D

All level tracks Track 1: The New Digital World
Case Study: Google
Power of Prediction in an Unpredictable World

Predictive Analytics is under an assault of sorts with the disruption of change, flood of data and instantaneous decision-making required in the digital world. Google's Greg Green will share case studies of the use of real time analytics, new data sources and decision-making systems for improved media and marketing performance.

Speaker: Greg Green, Director of Agency Strategy, Google

11:40am-12:25pm • Room: W184 B/C

Track 2: Credit Risk
Case Study: Fifth Third Bank
Modeling Practice of Risk Parameters for Consumer Portfolio

In credit risk, three risk parameters, namely Probability of Default (PD), Exposure at Default (EAD), and Loss Given Default (LGD), are key components of Expected Losses (EL) calculation, which is essential in estimating Economic Capital, Basel Accords Regulatory Capital Requirement, and Risk Adjusted Return on Capital. In our presentation, the modeling methodology employed to estimate each risk parameter will be demonstrated from the practitioner's point of view, including the Through-The-Cycle (TTC) PD estimation with panel data, EAD estimation for revolving exposures through EADF / LEQ / CCF, LGD estimation by the regression model on Recovery Rate (RR).

Speakers: Kelly Zhao, Credit Risk Analytics Manager, Fifth Third Bank

[ Top of this page ] [ Agenda overview ]

12:25-1:30pm • Room: W183

Lunch in Exhibit Hall

1:30-2:15pm • Room: W184 B/C

Putting IBM Watson to Work

IBM's cognitive system, Watson, captured the imagination of millions when it beat the all time champions of the US quiz show, Jeopardy!. To do so, it overcame traditional limitations of computers by communicating in natural human language, churning through 200 million pages of unstructured data to find answers in three seconds, and learning from each experience to improve performance over time. But as impressive as this accomplishment was, it was only the beginning. IBM is working closely with leading organizations in a variety of industries to put Watson to work. The possibilities are endless! Join Stephen Gold, Director in IBM's Watson Solutions Group, in an engaging discussion of ways that Watson is using predictive models to potentially change the way our world thinks, acts and operates.

Speaker: Stephen Gold, VP of Worldwide Marketing, IBM

[ Top of this page ] [ Agenda overview ]

2:15-2:30pm • Room: W184 B/C

Vendor Elevator Pitches

Absolutdata    Statsoft    Forum Analytics     Mu Sigma        

2:35-3:20pm • Room: W184 D

All level tracks Track 1: Comparison of Analytics Solutions
Big Data Predictive Analytics Solutions

Predictive analytics is hard to do, especially given the increasing challenge of storing, processing, and accessing big data. It can get a lot easier when you use the right tools and technologies. In Forrester's 51-criteria evaluation of big data predictive analytics solution vendors, we evaluated 10 vendor solutions. Join Forrester Principal Analyst Mike Gualtieri to learn about the results of the Wave and his analysis of the market including Angoss Software, IBM, KXEN, Oracle, Revolution Analytics, Salford Systems, SAP, SAS, StatSoft, Tibco Software, and others.

Speaker: Mike Gualtieri, Principal Analyst, Forrester Research

2:35-2:55pm • Room: W184 B/C

Track 2: Advanced Methods
Graph Theoretic Ensemble Method for Targeted Advertising Revenue Maximization

Ensemble methods have proven successful in the prediction of complex phenomenon across numerous domains. Recommendation systems in social media and tracking and detection systems in defense applications are prime examples. Graph-theoretic frameworks have been particularly useful in the modeling of complex interactions in economic and social networking systems. In this work, a KNN model and a SM model are used in an ensemble within a graph-theoretic framework. The ensemble model is used to predict conversion probabilities of a particular user for a particular advertisement, which are then applied to display advertisements in a way to maximize revenue over all users.

Speaker: Jim Tesiero, Principal Mathematician, Head of Data Science, Zeeto Media

3:00-3:20pm • Room: W184 B/C

Track 2: Healthcare Analytics
Predicting Provider Reimbursements

Using actual data, we will predict ICD-10 Reimbursements, utilizing best practices in coding and the map to Medicare Reimbursements.

Speaker: Stephen Omans, CEO and Founder, Deal Me Health

[ Top of this page ] [ Agenda overview ]

3:20-3:50pm • Room: W183

Exhibits & Afternoon Break

3:50-4:35pm • Room: W184 D

All level tracks Track 1: Healthcare Analytics
Leveraging Disparate Data Sources to Drive Business Decisions

Disparate data sources, including claims data, EMR data and consumer/demographic data, can identify and inform actionable business decisions. Based on her extensive experience in the healthcare informatics industry, Swati Abbott, CEO of Blue Health Intelligence® (BHI®), will discuss the use of these disparate data sources to analyze the cost and quality of healthcare. This includes trends and benchmarks, consumer segmentation, risk adjustment and care management.

Speaker: Swati Abbott, CEO, Blue Health Intelligence

3:50-4:35pm • Room: W184 B/C

Track 2: Social Media Analytics
Case Study: Chicago Transit Authority
Quickly Identifying Incidents from Twitter Streams

Twitter streams contain a wide variety of real time data about events. Important events that impact a lot of people are relatively easy to detect quickly. On the other hand, there is a long trail of less important events that generate fewer tweets individually but stand out if appropriately aggregated. Robert Grossman will describe a framework for analyzing twitter data and building classifiers that can be used to identify interesting incidents in given categories, such as customer concerns. In this talk, we'll also illustrate the framework by identifying incidents, such as service delays, from Twitter data about the Chicago Transit Authority (CTA).

Speaker: Robert Grossman, Partner, Open Data Group

4:40-5:00pm • Room: W184 D

All level tracks Track 1: Healthcare Analytics
Case Study: New Directions Behavioral Health
Deploying Predictive Models In Virgin Waters: Predicting Behavioral Health Readmissions

Deploying predictive modeling in an organization for the first time can be difficult. This is especially true in industries like behavioral healthcare that are driven more by anecdotes than data. Getting management buy-in, convincing skeptics and producing a finished product with tangible results can be a long and trying road. However, a well thought out plan executed with precision can lead an organization skeptical of predictive modeling to embracing it. This session discusses the steps, from beginning to end, of how a project to predict inpatient readmissions drove New Directions Behavioral Health to leverage and embrace predictive modeling.

Speakers: Matt Habiger, Quantitative Analyst, New Directions Behavioral Health
Fred Grunwald, Vice President of Analytics, New Directions Behavioral Health

5:05-5:25pm • Room: W184 D

All level tracks Track 1: Healthcare Analytics
Case Study: CogCubed
Videogames for Diagnosis: Predictive Executive Functioning Models Using Interactive Devices

CogCubed has created an innovative game, built on a new interactive tangible-graphical gaming platform called Sifteo Cubes, designed to diagnose cognitive disorders like Attention Deficit Hyperactivity Disorder (ADHD), and common comorbidities like Depression and Anxiety. Through a clinical trial with analysis at the University of Minnesota, player data was tracked and stored at sub-second intervals. Traditional response measurements were captured in addition to new information, such as inter-response metrics. Novel data mining techniques were applied to build several predictive models based on the condition. The results indicate a capability to predict conditions based on player responses in the game.

Speakers: Kurt Roots, Founder & CEO, CogCubed
Monika Heller, Chief Medical Officer, CogCubed

4:40-5:25pm • Room: W184 B/C

Track 2: HR Analytics
Case Study: Los Alamos National Lab & Lawrence Livermore
National Lab

Modeling Workforce Attrition - A Comparison of Techniques

In this session, John Pantano and Bill Romine will describe two alternative methods of modeling workforce attrition and present a comparative analysis of these methods applied to the problem of predicting future trends. The methods - Regression and Classification by Trees - will be examined based on assumptions, their mathematical basis and data preparation considerations used to enhance the results. Predictive performance will be compared using data derived from workforce records of the Los Alamos and Lawrence Livermore National Laboratories. A comparative analysis will include advantages and disadvantages of each of the methods.

Speakers: John Pantano, Senior Workforce Analyst, Los Alamos National Laboratory
Bill Romine, Computer Scientist, Lawrence Livermore National Laboratory

5:30-7:00pm • Room: W183

Networking Reception/Exhibits

[ Top of this page ] [ Agenda overview ]



Conference Day 2: Wednesday, June 12, 2013

8:00-9:00am • Room: W183

Registration & Networking Breakfast

9:00-9:05am • Room: W184 B/C

Conference Chair Welcome Remarks

Speaker: Eric Siegel, Founding Chair, Predictive Analytics World

9:05-9:20am • Room: W184 B/C

Vendor Elevator Pitches


9:20-10:10am • Room: W184 B/C

Analytics and the Presidential Elections

This talk will describe how the Obama Campaign used analytics to improve decision-making in virtually every function within the organization. We'll talk about how data from a variety of sources was used to improve fundraising, volunteer recruiting and mobilization, media targeting, and optimize voter contacts. We will cover what kind of data was available to the campaign, what technologies were developed and/or used, and how the resulting products were adopted by the campaign in order to help win the presidential elections. Although the focus will be on the elections and politics, we'll also talk about lessons learned during the campaign and how some of the same techniques can be applied to other industries and organizations.

Speaker: Rayid Ghani, Chief Data Scientist, Obama for America

[ Top of this page ] [ Agenda overview ]

10:10-10:40am • Room: W183

Exhibits & Morning Coffee Break


10:40-10:50am • Room: W184 D

Track 1
Gold Sponsor Presentation
Leveraging 'Analytics as a Service' to develop consumer oriented market expansion strategies utilizing advanced sales forecasting models.

This session will discuss utilization of advanced sales forecasting models in conjunction with geospatially based consumer and market data to assist in market development from a strategic and tactical perspective. This session will review:

  • Defining market optimization
  • The basics of analyzing data and setting up the methodology for success
  • Dissemination of the results and interpretation of the findings
  • Deploying the results into your business
Speaker: Paul Sill, Principal and Founder of Forum Analytics, Forum Analytics

Monsanto 10:40-10:50am • Room: W184 B/C

Track 2
Gold Sponsor Presentation
Improving Agriculture with Big Data and Analytics

Produce more. Conserve more. Improve lives. That's Monsanto's vision for a better world. Our seeds, biotechnology traits and herbicides help farmers improve productivity, reduce the costs of farming, and grow better foods for consumers and better feed for animals. To increase crop yields globally, data and analytics are being leveraged at every stage of the process from discovery through optimization of product performance in farmer's fields. Our newest product platform, Integrated Farming Systems, is the latest example of how we leverage analytics: it's designed to provide farmers with a valuable new approach to boost on-farm productivity while also supporting more sustainable agricultural systems for our increasing world population.

Speaker: Nalini Polavarapu, Advanced Analytics Lead, Monsanto

10:50-11:10am • Room: W184 D

All level tracks Track 1: Collections
Case Study: Paychex
Collections: Every Penny Counts

Considering the current economy, most businesses operate under the philosophy of "every penny counts". For years, the Paychex Collections department refined processes to improve both efficiency and effectiveness, beating budgeted write-offs year in and year out. However, as the economy worsened, budgets became tighter and the collections pressure was on. The Predictive Analytics team at Paychex was brought in to analyze the situation, ultimately creating a logistic model, dubbed MARCO. MARCO prioritized clients, allowing Collections to ignore a significant portion of the transactions while sacrificing only a sliver of the dollars recovered.

Speakers: Tom Kern, Risk Modeling Analyst, Paychex
Wei Liang, Risk Modeling Analyst, Paychex

11:15-11:35am • Room: W184 D

All level tracks Track 1: Fraud Detection
Case Study: Hewlett-Packard
Predictive Modeling of Warranty Non-Compliance Detection

Research on warranty non-compliance has concluded that the proportions of fraudulent claims in the Computer / Technology sector are on the rise. Manual adjudication of claims by investigators, although thorough, is extremely resource intensive. Alternately, the logistics and resources necessary for a large scale IT solution are cost-prohibitive. This presentation provides a layered, cost effective hybrid solution to this problem. This analytical solution also utilizes semi-supervised learning techniques to identify and categorize multiple degrees of non-compliance. This maximizes the identification rate, efficiency and better business. A case study is presented that identifies, quantifies and classifies the potential non-compliant claims.

Speakers: Veronique Duverneuil, Global Brand Analytics Director, Hewlett-Packard
KV Nathan, Sr. Manager, Customer Service Analytics Delivery, Global Analytics (GLA), Hewlett-Packard

10:50-11:35am • Room: W184 B/C

Track 2: Thought Leadership
My Five Predictive Analytics Pet Peeves

Predictive Analytics (PA) has become increasingly mature as a technical discipline over the past decade in part because it stands on the shoulders of the related disciplines of data mining and machine learning. However, there are recurring themes that permeate discussion boards and conferences that have become my personal pet peeves. This talk examines five of them and why they matter to practitioners, including why we must have humility in how far data science and algorithms can take us, and the value of business objectives, measuring "success," and measuring "significance."

Speaker: Dean Abbott, President, Abbott Analytics, Inc.

[ Top of this page ] [ Agenda overview ]

11:40am-12:00pm • Room: W184 D

All level tracks Track 1: Decision Support
Case Study: Microsoft, Samsung, and bauMax
Predictions At Work: Tools for Decision Support

Interactive Decision Tools are popular and often used alongside predictive models. Marketing decision support tools have been proposed and used for resource allocation, sales force optimization, product optimization, pricing and branding decisions.
These interactive tools have several benefits including:

  • getting value out of large amounts of (Big) data
  • simulating the impact of alternative scenarios and through that, they make better decisions
  • helping decision-makers learn about their markets, consumers, and marketing and can serve as the organizational memory to keep track of the increasing volume of analytics

We will show through the presentation of several case studies, when, why and how to make sure a firm successfully adopts such interactive decision tools.

Speakers: Jeff Brazell, CEO, The Modellers
Marco Vriens, Senior Vice President, The Modellers

12:05-12:25pm • Room: W184 D

All level tracks Track 1: Reliability Modeling
Case Study: TTX (Railway Industry)
Predicting Wheel Failure Rate for Railcars

One of the biggest costs in the railcar leasing industry is the repair and maintenance of its inventory of wheels. We worked with a leading railway company to predict the failure rate of its wheels. Using 30 years of historical data, we developed survival models for wheels while incorporating factors such as anticipated mileage, wheel type, wheel size, location, etc. Effects of weather and seasonality due to transportation demand were also incorporated in the model. The model resulted in less than 1.5% of error on validation data and is being used by the customer for the planning of 2012 budget.

Speaker: Mahesh Kumar, CEO, Tiger Analytics
Robert Gottel, Reliability Centered Maintenance Manager, TTX

11:40am-12:25pm • Room: W184 B/C

Track 2: Uplift Modeling
True-Lift Modeling: Mining for the Most Truly Responsive Customers & Prospects

Stop spending direct marketing dollars on customers who would purchase anyway!

True-lift modeling can identify:

  • which customers will purchase without receiving a marketing contact
  • which customers need a direct marketing nudge to make a purchase
  • which customers have a negative reaction to marketing (and purchase less if contacted)

This discussion will describe:

  • the basic requirements needed to succeed with true-lift modeling
  • scenarios where this modeling method is most applicable
  • the pros and cons of various approaches to true-lift modeling

Speaker: Kathleen Kane, Principal Decision Scientist, Fidelity Investments

[ Top of this page ] [ Agenda overview ]

12:25-1:40pm • Room: W183

Lunch in Exhibit Hall

[ Top of this page ] [ Agenda overview ]

1:40-2:25pm • Room: W184 B/C

Special Plenary Session
General Lessons We Can Learn from Blackbox Trading

Beating the market with skill, rather than luck, is so hard that it's arguably impossible. A strong working approximation is that markets are efficient - that prices reflect available information almost instantaneously. Accordingly, we have failed often. But our success building quantitative investment systems has been great - most notably with a hedge fund that beat the S&P-500 every year for a decade, with only 2/3rds the risk (volatility). This talk will highlight key lessons learned from the long battle, and how those insights have helped solve many other predictive analytics challenges.

Speaker: Dr. John Elder, CEO and Founder, Elder Research, Inc.

2:30-3:15pm • Room: W184 B/C

Expert Panel
Big Data for Predictive Analytics

Moderator: Eric Siegel, Founding Chair, Predictive Analytics World

If Big Data begs the question, "What to do with all this data?" predictive analytics answers, "Learn from it to predict behavior." But just how much predictive payoff comes with going so big? This expert panel will address the new demands on predictive analytics solutions and best practices as data grows to enormity, and will recommend tactics to fully leverage data's growing magnitude to improve the business performance of predictive analytics initiatives.

Panelists: Paul Sill, Principal and Founder, Forum Analytics
Gary Miner, Senior Predictive Analytics Consultant
Satish Lalchand, Director, Deloitte Financial Advisory Services LLP

3:15-3:50pm • Room: W183

Exhibits & Afternoon Break

[ Top of this page ] [ Agenda overview ]

3:50-4:10pm • Room: W184 D

All level tracks Track 1: Analytics Project Management
Filling the (Other) Knowledge Gap - Helping Analysts Communicate and Senior Management Comprehend

McKinsey projects a 2018 shortfall of 1.5 million managers and analysts having the critical ability to understand and make decisions using big data analytics. Even if institutions and businesses were to train enough data scientists in the next five years, too few executives would trust or know how to use their insights. This presentation will attempt to define the educational gap in senior management's ranks and the training that data scientists need to effectively communicate their findings. It will then explore alternative models to meet these needs, based on experience building big data management training programs for a major university.

Speaker: Larry Simon, Co-Founder, Managed Analytic Services

3:50-4:10pm • Room: W184 B/C

Track 2: Customer Retention & LTV
Case Study: Service Repair Solutions
Predicting the Future Value of Automobile Service Customers

What is the future revenue potential of a customer at an automobile service center? Can we predict the likelihood that a customer will return, just with existing information about the customer and their vehicle? How can dealerships in this multi-billion dollar industry use predictive analytics to maximize their marketing resources? We have combined predictive analytics with a nationwide automobile repair database to achieve prediction return accuracies exceeding 86%. Our techniques identify at-risk customers to help dealerships target their outreach. Furthermore, using historical information, we estimate potential future revenue given the customer's previous visits and condition of their vehicle.

Speaker: John Sipple, Senior Data Scientist, Sphere of Influence

[ Top of this page ] [ Agenda overview ]

4:15-4:35pm • Room: W184 D

All level tracks Track 1: Analytics Talent
Using Analytics to Build Your Analytics Bench: Announcing 2012 Analytics Professionals Study Results

Many innovative businesses and IT organizations appreciate the competitive advantage analytics capabilities can provide and have ambitions to reach increasing levels of analytics maturity. However, the well-documented shortage of analytic talent leaves many firms without a strong analytic talent bench and little knowledge about how and where to find analytics professionals needed to get there. In this presentation, Greta Roberts will discuss results from a major 2012 Study of Analytics Professionals that crosses industries, experience and skills. Practical insights shared include key best practices, trends and correlations that lend unexpected insight into building a strong and scalable analytic talent bench.

Speaker: Greta Roberts, Faculty Member, International Institute of Analytics

4:15-4:35pm • Room: W184 B/C

Track 2: Sales Lead Scoring
Case Study: IBM
Wallet Estimation for Sales Force Optimization at IBM

In 2009, IBM was recognized as a finalist of the INFORMS Edelman competition for its initiative to improve the productivity of its global sales force having an estimated business impact of $100 million dollars. One key component is a 'wallet estimation' prediction that is used strategically to allocate sales resources based on validated analytical estimates of revenue opportunity. We cover the key elements leading to the success including the data integration, data mining and predictive modeling, solution delivery, human guided model validation, integration of the business process and we conclude with an assessment of the bottom-line business impact.

Speaker: Claudia Perlich, Chief Scientist, Media6Degrees

[ Top of this page ] [ Agenda overview ]

4:40-5:30pm • Room: W184 B/C

All level tracks Track 1:Data Privacy/Security
Compliance Issues in Real World Analytics - Security, Privacy, Regulatory Requirements and Due Diligence

Big data analytics often means centralizing massive amounts of data (either live or offline), a situation that makes lawyers, auditors, security and privacy officers and corporate regulators (like the SEC) very nervous. What steps should be taken to address these legitimate, administrative concerns? Are there specific, applicable standards or must we extrapolate from non-specific sources? What are appropriate roles for the data scientist, CIO, Security Officer, auditor and others in ensuring that the analytics process is not only accurate and meaningful, but controlled, secure and in conformity with all corporate and external policies, procedures and requirements.

Speaker: Jerrard Gaertner, President, Canadian Information Processing Society - Ontario

[ Top of this page ] [ Agenda overview ]

Share |
PAW Highlights Video

Co-located with
The eMetric Summit
Conversion Conference

Past Sponsors


AbsolutData Holdings Inc.
Forum Analytics Inc.
Mu Sigma Inc.

Decision Systems Inc
Kelley School of Business
Latent View
Managed Analytic Services Inc
Tiger Analytics
University of California, Irvine Extension

Check out the official PAW Blog Partners

© 2024 Predictive Analytics World | Privacy
Produced by Prediction Impact, Inc. and Rising Media, Inc.

Predictive Analytics Company           Predictive Analytics Event Producer