San Francisco • Chicago • New York City
Berlin • Washington DC • London
Delivering on the promise of data science

Full Agenda – London, UK – October 23-24, 2013

DAY 1: Wednesday October 23, 2013

8:00am-9:00am

Registration & Coffee

[ Top of this page ] [ Agenda overview ]


9:00am-9:40am

Opening Session:
How to win with Predictive Analytics

This opening session will first and foremost serve as an introduction and 'Travel Guide' to Predictive Analytics World London 2013. The program features a distinct selection of managers and experts who are currently winning with Predictive Analytics. No longer can their stories be interpreted as a series of isolated successes. An increasing number of organizations have stepped up from building first success cases to internalizing predictive analytics as a valuable and recurrent business activity. In this opening keynote, Geert Verstraeten, Program Chair of Predictive Analytics World London, will lift the veil on this year’s program, and will provide his views on how small and large organizations reap great benefits from using advanced analytics.

Speaker:
Geert Verstraeten, PhD, Program Chair Predictive Analytics World London

[ Top of this page ] [ Agenda overview ]


9:40am-10:50am

Thought Leader
Keynote:
Predictive Analytics Powered By Process Mining: It’s The Process, Stupid!

Recently, process mining emerged as a new scientific discipline on the interface between process models and event data. Conventional Business Process Management (BPM) and Workflow Management (WfM) approaches and tools are mostly model-driven with little consideration for event data. Data Mining (DM), Business Intelligence (BI), and Machine Learning (ML) focus on data without considering end-to-end process models. Process mining aims to bridge the gap between BPM and WfM on the one hand and DM, BI, and ML on the other hand. The challenge is to turn torrents of event data ("Big Data") into valuable insights related to performance and compliance. Process mining is one of the few mature approaches that can indeed be used to identify, understand, and predict bottlenecks, inefficiencies, deviations, and risks. Process mining helps organizations to "mine their own business": they are enabled to discover, monitor and improve real processes by extracting knowledge from event logs. In his talk, Wil van der Aalst will provide an overview of this exciting field. Moreover, he will focus on the predictive value of process mining. All of this will be illustrated using many real-life examples demonstrating the unique capabilities of today’s process mining tools.

Speaker:
Prof Dr Ir Wil van der Aalst, Full professor, Eindhoven University of Technology

[ Top of this page ] [ Agenda overview ]


10:50am-11:20am

Break / Exhibits

[ Top of this page ] [ Agenda overview ]


11:20am-12:00pm

Case Study: Deutsche Bank
Supporting the branch network using predictive analytics: Predicting Next Investment behavior

As a challenger in the Belgian market with a modest branch network, it is crucial for Deutsche bank to optimally allocate salesforce attention to the right clients in order to reach our commercial objectives and satisfy our client's needs. In this specific case study, predictive methods allow us to identify clients most likely to make a next investment. Results and lessons learned when implementing a recurrent commercial process based on a predictive model will be presented.

Speaker:
Matthias Meul, Customer intelligence analyst, Deutsche Bank AG, Brussels Branch

[ Top of this page ] [ Agenda overview ]


12:00pm-1:00pm

Lunch / Exhibits

[ Top of this page ] [ Agenda overview ]


1:00pm-1:40pm

Creating a Predictive Analytics Strategy

Speaker:
Tom Khabaza, Founding Chairman of the Society of Data Miners

[ Top of this page ] [ Agenda overview ]


1:40pm-2:20pm

An Implementation and Adoption Roadmap for Analytics

This session offers a step-by-step methodology on how to transform a business into an analytics driven organization. This is achieved through a 4-step process:
1. Simplifying the concept and definition of analytics (removing the confusion and mystery)
2. Using extensive predictive analytics examples from 15+ industries to show a pattern of business problems that can be tackled with predictive technology
3. Detailing a pilot and roadshow strategy to convince business executives into the power of analytics for business operations
4. Building a center of excellence for data and analytics with process, roles and responsibilities for sustained value from predictive analytics

Speaker:
Nauman Sheikh, CEO, Asrym Inc

[ Top of this page ] [ Agenda overview ]


2:20pm-2:40pm

Break / Exhibits

[ Top of this page ] [ Agenda overview ]


2:40pm-3:20pm

Case Study: Belgian government
Improving Fraud Detection Techniques using Social Network Analytics for the Belgian government

The Belgian government social security institution is responsible for collecting and managing employer and employee social contributions. These contributions are collected at employer level, making this process highly sensitive for payment fraud. As fraud is often a carefully organized crime rather than a stand-alone phenomenon, traditional data mining techniques regularly fail to identify fraudulent behavior. Incorporating social interactions between companies offers new insights in the propagation of fraud through a network. Extending predictive analytics with social network knowledge does not only improve the accuracy with more than 10%, but generates more relevant and precise results.

Speaker:
Veronique Van Vlasselaer, PhD researcher, KULeuven

[ Top of this page ] [ Agenda overview ]


3:20pm-4:00pm

Break / Exhibits

[ Top of this page ] [ Agenda overview ]


4:00pm-6:00pm

Interactive Workshop
PAW Café
Organizational Development and Talent Management in Analytics

Workshop aimed to provide a structured yet open and creative conversation on Organizational Development and Talent Management in Analytics to surface collective knowledge, share ideas and insights, and gain a deeper understanding of the topic.

Moderator:
Martine George, PhD, Head of Marketing Analytics and Research, BNP Paribas Fortis

[ Top of this page ] [ Agenda overview ]


6:00pm-7:00pm

Networking Reception

[ Top of this page ] [ Agenda overview ]


DAY 2: Thursday October 24, 2013

8:00am-9:00am

Registration & Coffee

[ Top of this page ] [ Agenda overview ]


9:00am-9:50am

Thought Leader
Keynote
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:
John Elder, PhD, CEO and Founder Elder Research, Inc.

[ Top of this page ] [ Agenda overview ]


9:50am-10:20am

Sponsored Session
Insurance Fraud Detection, a predictive approach

Speaker:
Alfredo Barbieri, Principal Consultant Predictive Analytics, i4C Analytics
Alan Harton, VP International Development, i4C Analytics

[ Top of this page ] [ Agenda overview ]


10:20am-10:50am

Break / Exhibits

[ Top of this page ] [ Agenda overview ]


10:50am-11:30am

Special Featured Session
Data Science: For Fun and For Profit

Data Science is relatively new, but the ideas and techniques that form the underpinnings for this evidence-oriented discipline have a solid foundation in hundreds of years of scientific development. In order to understand the new science of data, one must first understand the science of science.

The Scientific Method, the unintended effects of repeated significance testing and Simpson's paradox: this talk will focus on the practical applications of the theoretical constructs that lie at the heart of Data Science; and expand on some potential pitfalls of statistical analysis that you are likely to encounter when venturing into the field.

Speaker:
Lukas Vermeer, Data Scientist, Booking.com

[ Top of this page ] [ Agenda overview ]


11:30am-12:10pm

Case study: BNP PARIBAS FORTIS
Client potential for a better sales force allocation in a B2B banking environment

BNP Paribas Fortis faces a fierce competition in a saturated Belgian B2B banking market. At the same time limited sales force resources need to be efficiently redirected. In this context our analytic marketing team developed a customer lifetime value to comprehensively measure the potential for its customers. Confronted with a limited client history in our data base, we applied a hierarchical Bayesian estimator. The results not only reveal the expected customer value. The approach also yields a "next product to buy", “cross-sell” and “cannibalization” effects, churn estimation... Combined with traditional propensity models it builds the base for concrete commercial actions.

Speaker:
Dr Derik Burgert, Data Mining Analyst, BNP Paribas Fortis Cognitro Analytics

[ Top of this page ] [ Agenda overview ]


12:10pm-1:10pm

Lunch / Exhibits

[ Top of this page ] [ Agenda overview ]


1:10pm-1:50pm

Case study: SEAI, Electric Ireland, Bord Gáis Energy
Combining Forecasting and Clustering on Energy Data

The hype surrounding big data is immense. But what happens when you get massive telemetry data and are able to combine forecasting with other analytical techniques like clustering? This paper uses electrical Smart Meter Data from the Sustainable Energy Authority of Ireland (SEAI), Bord Gáis Networks, Electric Ireland and Bord Gáis Energy and shows not only more accurate energy usage forecasting but reduces the data down to a series of “golden questions” that allow a new customer to be accurately categorized so that an appropriate pricing plan can be recommended. The techniques are valid for all industries with vast quantities of telemetry data. Open Source software is used throughout so that all data and examples can be shared and downloaded.

Speaker:
Phil Winters, Senior Managing Partner, CIAgenda

[ Top of this page ] [ Agenda overview ]


1:50pm-2:30pm

Influencing consumer acquisition and loyalty through actionable insights and targeted location-based mobile marketing.

The explosion of mobile activities offers many opportunities to obtain granular user profile data, capture online behavior and attain insight into mobile audiences. While the goals of building brand loyalty in an increasingly connected and mobile world remain the same, the tactics of achieving them are changing dramatically. In this session, we share our view on how actionable consumer insights and predictive analytics can drive precise, one-on-one location-based mobile marketing campaigns.

Speaker:
Gery Pollet, Founder & Executive Chairman, ZapFi

[ Top of this page ] [ Agenda overview ]


2:30pm-3:15pm

Panel Discussion
The Role of Ethics in Analytics

For every news story about predictive analytics and data mining, there is an article related to ethical issues and privacy concerns. Recently, however, INFORMS has established a code of ethics for analytics professionals. In his recent category bestseller on Predictive Analytics, PAW Founder Eric Siegel quotes Spider-Man’s wise uncle: “With great power comes great responsibility". It is probably a sign of domain maturity that these issues are receiving a more prominent place on the analyst's agenda. In this panel discussion, the panelists will explore the needs, scope and potential benefits of establishing a consensus on ethical topics in a domain that is developing at great speed.

Panel moderator:
Geert Verstraeten, PhD, Program Chair Predictive Analytics World London

Panelists:
Tom Khabaza, Founding Chairman of the Society of Data Miners
Gery Pollet, Founder & Executive Chairman, ZapFi
John Elder, PhD, CEO and Founder Elder Research, Inc.

[ Top of this page ] [ Agenda overview ]


3:15pm-3:45pm

Break / Exhibits

[ Top of this page ] [ Agenda overview ]


3:45pm-4:25pm

Case Study: AOL
How Much Are You Worth? - Calculating Customer Lifetime Value

How can we accurately measure how much someone who comes to your site will be worth? In order to maximize ROI and LTV, AOL Search took a step back from the complex LTV models and created a 3 pronged model that takes audience, engagement (and churn), and monetization into account to measure the value of users coming in from different properties. See how we visualize this data and how we cut the time to decisions by over 80%; allowing the company to divest from ROI negative partnerships nearly immediately, as well as invest more with partners who have optimal performance.

Speaker:
Brett Cohen, Senior Business Intelligence Analyst, AOL

[ Top of this page ] [ Agenda overview ]


4:25pm-5_05pm

Predicting online campaign effectiveness

Prediction of reach and effectiveness of online ad campaigns helps publishers and brands create strategies and achieve positive impact. Every online campaign is unique and dynamic due to the campaign goals and audience targets. Thus extrapolating from historical campaigns does not produce accurate predictions. Utilizing integrated longitudinal consumer behavior and historical campaign data we have created a campaign simulator that predicts the effectiveness of campaigns. The simulator is based on an analytics engine using Bayesian case based reasoning techniques to predict campaign effectiveness. We will present a case study with data and method details that displays the effectiveness of our approach.

Speaker:
Amit Phansalkar, Chief Data Scientist for Mass Mutual financial

[ Top of this page ] [ Agenda overview ]


5:05pm-5:25pm

Closing Remarks

Speaker:
Geert Verstraeten, PhD, Program Chair Predictive Analytics World London

[ Top of this page ] [ Agenda overview ]

Share |

Diamond Sponsor 2013

Silver Sponsor 2013

Partner 2013

Media Partners 2013

​Blog Partners​

Check out the official PAW Blog Partners
© 2017 Predictive Analytics World | Privacy

Program by: Python Predictions
Python Logo

Produced by Prediction Impact, Inc. and Rising Media, Ltd.

Predictive Analytics Company           Predictive Analytics Event Producer