Agenda

Predictive Analytics World London
etc.venues, 200 Aldersgate, 12-13 October, 2016


Workshops – Tuesday – 11 October, 2016

9.00 am

How to Avoid the Pitfalls of Moderated User Testing

Karl Gilis, Co-founder, AGConsult (@AGConsult)

Els Aerts, Co-founder and Managing Partner, AGConsult

4.30 pm

End of Workshops


Predictive Analytics World for Business - London - Day 1 - Wednesday, October 12th, 2016

8:00 am
Registration
9:15 am
Room: Impressive Suite
Social Networking Pass
The Session Description will be available shortly.
More Information
Speaker
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
9:30 am
Room: Impressive Suite
Social Networking Pass
Keynote:
Predictive Analytics is so powerful and so useful – everywhere – we are astonished that its widespread adoption has taken so long. Its modest risk and phenomenal return should lead rational actors to cooperatively pool technical and domain expertise to tweak production processes to the benefit of all. And yet, most early projects fail to be implemented – felled by fear, pride, and ignorance. But we can anticipate those foes! Recall that success requires solving three serious challenges: 1) Convincing experts that their ways can be improved, 2) Discovering new breakthroughs, and 3) Getting front-line users to completely change the way they work. No wonder there is resistance at every stage! John argues that it’s helpful to have a mental model of the human brain as not optimized for success in our modern life of safety and abundance, but for survival within a small tribal society. And that with this model we can better anticipate – and escape - the traps that we idealistic techno-nerds tend to blunder into as we try to bring life-changing fire into the tribal circle.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
John ElderElder Research
Founder & Chair
Elder Research
10:25 am
Room: Impressive Suite
Social Networking Pass
Sponsored Session:
In this session we will present a short demo from a real use case to illustrate how RAYS platform takes advantage of the Cloud elasticity, a Multi-langages Framework and Automation to reduce the technological barrier and improve access to Big Data Analytics. In just one click you can scale up/down your environment according to your needs, gather, classify and use external data (IoT, Internet, Social Media, API,s, etc.), create and re-use original algorithms, to finally test the value of algorithmic business cases from massive and multi-structured data. In summary, we will present how machine learning and data science has been made accessible in an intuitive and graphical workflow designer crafted to suit your skills to accelerate your analytical journey by accessing a rich library of reusable apps as building blocks to build end-to-end Data Intelligence projects.
More Information
Sponsored by
Keyrus
Speaker
Santiago CastroKeyrus
Head of Strategy and Portfolio
10:30 am
Coffee Break
10:55 am
Room: Impressive Suite
Track 1
Being able to predict customer demand for a particular product and have that product available for sale when required is a fundamental get right for any supply chain. But what if everything we try doesn’t work, and in many cases appears to make the forecast work? Alex gives an account from Shell’s Lubricants Supply Chain on the journey taken by the newly formed Central Forecasting Team in an effort to turn-around and improve a failing metric (Forecast Accuracy) that was being blamed for a wide range of organisational pain. Alex touches on the various ideas that didn’t work (from flat targets, to simply manipulating the data) and the affect these had, before moving on to the later ideas, and career risk, that began to move the needle in the right direction. Key take always include plenty of things to avoid, some useful tools such as segmentation, and the simple question to ask when nothing else works.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Alex HancockShell Oil Company
Head of Treasury Analytics
Shell Oil Company
Room: Innovative Suite
Track 2
At Reed Exhibitions, world’s largest event organizer, being data-driven and serving customers across 5 continents and 44 industries cannot be about sophistication and confusion. In this talk, Salman sheds light on how predictive analytics is used to develop data-driven capabilities that accelerate, enhance, and in some cases even automate next generation customer retention and renewal strategies.
More Information
Moderator
Chris TurnerStrataBridge
Co-Founder
StrataBridge
Speaker
Salman Taherian
Global Head of Data Innovation
Reed Exhibitions Ltd.
11:40 am
Session Change for Combo Pass Holders
11:45 am
Room: Impressive Suite
Keynote:
Decision Tree? Neural Network? Regression? Naive Bayes? It is said that when your only tool is a hammer, every problem looks like a thumb. Modern data mining toolkits are full of tools, but how do you pick the right tool for a particular predictive analytics task? In this talk, I present several business questions that I have addressed using data mining techniques of various kinds. The emphasis is not on the answers to these questions, but on how and why I chose a particular approach. Some of the business questions I face in Tripadvisor’s Hotel Solutions group are specific to the hospitality industry, but most are similar to those I’ve seen in other B2B settings:
  • What is the proper price for a product?
  • What is the probability that an existing subscription will be renewed and how can that probability be increased?
  • What other hotels will this hotel consider to be competitors?
  • Who are the best prospects for a particular product?
  • When will product A do better than product B on a particular page?
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Michael Berry
Analytics Director
Tripadvisor Hotel Solutions
12:45 pm
Lunch Break
1:40 pm
Room: Impressive Suite
Track 1:
Part 1
AutoScout24 is one of Europe’s biggest online market places for new and used cars. With more than 2.4 million listings across Europe, AutoScout24 has access to large amounts of data about historic and current market prices and wants to use this data to empower its users to make informed decisions about selling and buying cars. A price prediction service was created based on a Random Forest model that is continuously delivered to the end user. Learn how automated verification using live test data sets in our delivery pipeline allows us to release model improvements with confidence at any time.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speakers
Christian DegerAuto Scout 24
Architect
AutoScout24
Arif WiderThoughtWorks GmbH
Consultant Developer
ThoughtWorks
Part 2
HouseMark has worked with a group of its landlord members to explore the potential to investigate patterns in large amounts of property and tenancy-related social housing data in combination with public open data.This discovery project focused on developing robust data structures and definitions that would ensure consistency and extensibility in a large data set gathered from multiple sources. Preliminary analysis then examined whether clustering techniques could reveal hitherto unrecognised groupings of similar entities within the data.Finally, the potential usefulness of the clustering to develop predictive models was demonstrated using the example of repair hotspots within social housing stock.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speakers
Grazziela Figueredo
Research Fellow
University of Nottingham
Vicki Howe
Head of Product Development
HouseMark
No session in this slot.
2:40 pm
Session Change for Combo Pass Holders
2:45 pm
Room: Impressive Suite
Track 1:
Most companies use heuristics or simplistic customer value models like RFM as a proxy for customer value. While these approaches are appreciated for their transparency and intuitive appeal, advanced models on customer ID level and clustering algorithms for value segmentation can offer new opportunities and a wider range of applications. This presentation focuses on the trade-off between black and white box approaches and discusses implementation examples that are characterized by different levels of abstraction.
More Information
Moderator
Chris TurnerStrataBridge
Co-Founder
StrataBridge
Speaker
Timo Kunz
Sr Data Scientist
YOOX NET-A-PORTER GROUP
Room: Innovative Suite
This is your chance to meet with Dr. John Elder, CEO & Founder of Elder Research and one of the world's most renowned Predictive Analytics experts. Come and bring your questions based on his keynote earlier this morning and/or your Predictive Analytics questions that have given you sleepless nights.
More Information
Speaker
John ElderElder Research
Founder & Chair
Elder Research
3:30 pm
Coffee Break
3:55 pm
Room: Impressive Suite
Track 1:
The science of (data-driven) prediction is a race between the increasing complexity of the real world and our accelerating ability to mathematically represent it by means of information-technology-related capabilities, such as neural network models.From a mathematical point of view, neural networks allow the construction of models, which are able to handle high-dimensional problems along with a high degree of nonlinearity. Our philosophy is beyond purely data-driven modeling: The application of neural networks should be based on a deep understanding of the underlying mathematics, first principles on dynamical systems as well as prior (economic) domain knowledge.The talk will introduce basic feedforward neural networks for non-linear regression tasks and time-delay recurrent neural networks for modeling dynamical systems. Examples from real-world industrial applications will be given that outline the merits of such a modeling approach. Among others we will deal with the modeling of e.g. the energy supply from renewable sources, energy load forecasting as well as the forecasting of commodity prices and the identification of features responsible for component failures
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Ralph GrothmannSiemens
Principal Consultant
Siemens AG, Corporate Technology
Room: Innovative Suite
Track 2:
Most companies have tons of data but no clue what do with it. A clearly defined data strategy is missing. But it’s important to identify concrete use cases and provide a measurable benefit for the company and it’s customers, you have to evaluate the technical requirements and business potentials and you need to define a realistic roadmap structuring the order in which the use cases should be realized. To help clients to turn their data into assets Martin developed a process called data design thinking which is based on the design thinking methodology. This session explains the process by presenting an example derived from a real client project. You will also learn how to apply the data strategy and data assets canvas, a visual collaboration tool for data strategists.
More Information
Moderator
Chris TurnerStrataBridge
Co-Founder
StrataBridge
Speaker
Martin SzugatDatentreiber GmbH
Datentreiber GmbH
4:40 pm
Session Change for Combo Pass Holders
4:45 pm
Room: Impressive Suite
Featured Session:
The buzz of the “Big Data” revolution had been unnerving CIOs for more than half a decade, when it was suddenly dropped from the Gartner hype-cycle in 2016.Sure, Businesses are still collecting more and more data these days, but is that what matters?At Predictive Analytics World we have always argued that making the right use of what Companies gather matters, and the signs indicate that they weren’t, just creating more data and complexity. Instead, they should focus on using data to make better decisions using new Analytics algorithms and new Business Applications! And it seems that Gartner finally agrees: Machine Learning, (self-service) Advanced Analytics and Neurobusiness have entered the Gartner hype-cycle, with full momentum of only 2 to 10+ years into productivity. Gartner now predicts an annual growth rate of 34 percent by 2017, with revenues projected to reach $48 billion, and venture capitalists have been eager to invest in burgeoning Predictive Analytics startups (after dropping the Big Data ones). Is this finally the rainbow on the horizon which the Analytics community has been chasing for years, possibly since before it was called Data Mining, or even Statistics? Or is it just another dot on the hype-cycle to be banished? Or is it not even real? In Predictive Analytics for Time Series (an area of Predictive Analytics growing in importance with more data gathered continuously over time), aka Forecasting, the corporate reality looks rather different.The elusive crystal ball into the future is often powered by simple and elderly algorithms, many of them around since the 1960s or earlier.Industry as software vendors are slow to adapt machine learning, or indeed even anything contemporary from the 90s. In our presentation, we show evidence from an industry survey of 200+ companies and their reality of algorithms used, and measure the substantial gap between research and practice. To contrast this, we showcase a selection of state-of-the-art algorithms available in Predictive Analytics for time series today, from Neural Networks to Support Vector Machines and from Random Forests to Boosting, and how they could be applied to time series Analytics to drive a revolution. We will give examples how these have been implemented by a few industry though-leaders, from Electricity & Utilities companies to Call-Centres, Manufacturers and Container Shipping lines, who were willing to bridge the gap and lead the hype-cycle onwards.
More Information
Speaker
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
5:45 pm
Networking Reception in the Exhibit Hall
7:00 pm
End of First Conference Day
7:00 pm
Dinner with strangers

Dinner with strangers:
meet your fellow attendees.
See the registration desk for more information

Predictive Analytics World for Business - London - Day 2 - Thursday, October 13th, 2016

8:30 am
Registration
9:30 am
Room: Impressive Suite
When it comes to high tech, we tend to wear blinders. We rarely look around to see how others succeed. This is especially true with organizations who want to look beyond basic BI and reveal answers to questions they never thought to ask. What would demand forecasting for a CMO in media mean to a Chief Data Officer in banking? What would Proactive Customer Care in telco mean to a Chief Revenue Officer at a major retailer? Graeme will share cross industry use cases that will get you outside your comfort zone and allow you to take a different look at how applications of advanced and predictive analytics on big data can help you act on insights and transform your business.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Graeme NoseworthyIBM
Senior Content Marketing Manager
IBM
10:30 am
Coffee Break
10:55 am
Room: Impressive Suite
Track 1:
The explosion of sensor-enabled data collection offers a chance for transportation companies to improve how they manage the multiple challenges affecting their operations. For operators it is possible to improve asset availability and generate more value from their assets.With the data transmitted from rail vehicles and rail infrastructure, it is possible to predict component failures, analyze conditions of vehicles and infrastructure and reduce lifecycle cost significantly. This presentation will show how to make this happen with a large data analytics platform, a team of data scientists and a set of data analytics assets specific for rail topics.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Gerhard Kress
Director Data Services
Siemens AG
Room: Innovative Suite
Track 2:
With the widening of anonymised access to public health care data, a study of the total population with the help of Big Data analytics is within our remit. In his presentation, Athula will focus on a pharmaceutical industry based case study on systematic statistical landscaping of actionable clinical outcomes of patients of chronic diseases. The statistical landscaping of patient outcomes in a disease segment uses the gold standard outcome data originating from well characterised patient cohorts, randomised control trials, observational cohorts and real world evidence of public healthcare data. This analytical approach results in total evidence synthesis within the disease area and paves the way for the integration of patient level, genomic and other molecular expression data and big data data sources for wider disease, biological inference for therapeutic development and outcome interpretation. In this session you will learn about the total evidence synthesis of patient outcomes at population level using big data, the ensemble outcome modelling of efficacy and safety outcomes, the statistical landscaping of therapeutic effects, how to use the landscape for stratification of patient populations for targeted therapy and the development and (statistical) engineering of therapeutic entities.
More Information
Moderator
Alex HancockShell Oil Company
Head of Treasury Analytics
Shell Oil Company
Speaker
Athula Herath
Global Head of Real World Evidence Disease Epidemiology
Novartis
11:40 am
Session Change for Combo Pass Holders
11:45 am
Room: Impressive Suite
Featured Session:
Political bombshells, unimaginable terrorist attacks, epidemic outbreaks, natural disasters, technological disruptions, fractured markets, transitory advantages, multifarious competitors, increasingly demanding customers and fickle consumers. Thanks to the military, we have a useful descriptor for the conditions and environment these drivers create; ‘VUCA’ – Volatility, Uncertainty, Complexity and Ambiguity… a combination of the magnitude and speed of change, the lack of predictability and prospect of surprise, the multitude of forces and confounding issues, and the lack of ‘one right answer’ or single course of action. Yet against this backdrop many organisations are still carrying the early, often ill-formed, baggage of implicit promises and expectations of Big Data and Analytics, and the mindset of operating in more stable conditions. And that’s before we get to sentiment mining, machine learning, edge analytics and the like. There is no question about the power, pervasiveness, further potential and applicability of predictive analytics. But it is at the edge of this applicability that things get interesting; where a VUCA environment lays cognitive traps for those focused on ‘getting to the right answer’ rather than ‘asking the right questions’. In the context of strategy development, deployment and delivery in the real world, this edge – between prediction and insight, between extrapolation and choice, between algorithm and decision – is critical. This session explores some of the typical problems and hidden traps in creating strategy against a VUCA backdrop, considers the tensions that exist across our unavoidably uneven knowledge of the world, offers some mental models to help leaders grapple with this wicked problem, and to help you drive the most impact and value in support of your strategy.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Chris TurnerStrataBridge
Co-Founder
StrataBridge
12:30 pm
Lunch Break
1:40 pm
Room: Impressive Suite
Track 1:
ING Belgium strives to create a superior customer experience. In a world where customer is king, ING recognizes that their clients expect smooth interactions when dealing with the bank. Recently, ING applied process mining on a crucial customer-facing process to better understand and improve the end-to-end journey. The results exceeded all expectations. In this talk, we will illustrate the benefits, milestones, requirements and potential pitfalls we encountered during the project. Moreover, we will explain, step by step, exactly how attendees can engage in process mining to discover and counter process inefficiencies in their organization. We illustrate how to prepare for the analysis, which tools can be used, and which methodology we used to obtain convincing results. Moreover, we will share how we gained involvement from stakeholders, and how we convinced ING to further invest in process mining on their crucial activities.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speakers
Pieter DyserinckING Belgium
Project Manager Operational Excellence
ING Belgium
Pieter Van Bouwel
Senior Analyst
Python Predictions
Room: Innovative Suite
Track 2:
Part 1
Every organization wants their sales force to be more productive; but they inadvertently fail to do so. Learn how one can use predictive analytics in-house to improve their sales productivity and mine hidden gems from their EDW. This presentation proposes how one can build a self-evolving framework; starting from choosing KPI of sales productivity, identifying levers which can affect sales productivity, and most importantly quantitatively linking those levers to their organization’s sales productivity; for informed decision making. This session will show how the SVM Technology can be applied to do Regression and how Excel Solver can be used for Non-Linear Optimization. The session will conclude by giving some examples of how an organization’s sales productivity and thus revenue and/or profit can be largely impacted by its choice of doing business the traditional way or using the power of analytics for the same.
More Information
Moderator
Alex HancockShell Oil Company
Head of Treasury Analytics
Shell Oil Company
Speaker
Nishant Saxena, PMPHewlett-Packard
Analytics Delivery Manager, ES Analytics
Hewlett Packard Enterprise
Part 2
Knowing your customers is great, but knowing what they do and what they will do is even better. It is important to track your visitor’s behavior and use predictive technologies, in order to send them highly personalized emails that are so targeted and relevant, they sound like a one-on-one private conversation. As a result you will revive your open rates, boost your click throughs, make next order predictions and turn more “window shoppers” into repeat buyers. In this session Kristina will show you how to use Big Data in Email marketing to send highly personalized emails, how using predictive analytics can turn "window shoppers" to best customers (Tibiona case-study) and how to track & measure the results.
More Information
Moderator
Alex HancockShell Oil Company
Head of Treasury Analytics
Shell Oil Company
Speaker
2:40 pm
Session Change for Combo Pass Holders
2:45 pm
Room: Impressive Suite
The MS Data & Decision Sciences Group built a predictive model to identify at-risk kids lowering attrition 25% in the Tacoma Public School District and how Big Data can be used for Social Good. The goals of this project were to: Reduce the occurrence of students dropping out in the Tacoma Public School district; Ameliorate key indicators to school administrators so they could make changes real time to anticipate and address attrition; Demonstrate how Machine Learning can help create solutions such as this which can be replicated nationwide providing social and economic advantages in at-risk communities. In this session Sarmila will present the predictive model, the goals and the outcome of the project.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speaker
Sarmila Basu
Senior Director, Data & Decision Sciences Group
Microsoft Corporation
3:30 pm
Coffee Break
3:55 pm
Room: Impressive Suite
Track 1:
Common driver models solve for relative impact of brand drivers, but rarely show impact on outcome metrics, expected from brand messaging related marketing investments. Amit presents an innovative solution for modeling Visa’s brand preference based on individual-level survey data, comparing prediction strategies and showcasing an easy-to-use Excel simulator. By taking current performance into account and modeling on an individual level it is possible to show the precise impact of brand perception levers. This shifts the predictive power of the driver model into the hands of key decision makers and stakeholders, thereby creating actionable insights for marketing teams. Marketing teams therefore rely on predictive analytics to provide concise results and actionable insights.
More Information
Moderator
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Speakers
Amit DograVisa
Director, Global Product Marketing
Visa
Albrecht KüfnerFactWorks
Director
FactWorks
Room: Innovative Suite
Track 2:
In this session we will present how a combination of analytical techniques was used to drive businesses to register to provide consumer credit when the Financial Conduct Authority (FCA) took over authorisation from the Office of Fair Trade. Businesses were segmented into distinct groups to gain an understanding of the why different businesses offered credit. Response models were built to determine which businesses were most/least likely to register. Econometric models were built to understand what media worked best for each segment and how to target businesses least likely to register. Adverts were varied in each media according to the segment most likely to be consuming that media. This enabled the FCA to beats all its early estimates of businesses that would authorise for consumer credit.
More Information
Moderator
Alex HancockShell Oil Company
Head of Treasury Analytics
Shell Oil Company
Speakers
Grant Hecht
Head of Analytics
Marketing Metrix
Emma Roberts
Financial Conduct Authority (FCA)
4:40 pm
Session Change for Combo Pass Holders
4:45 pm
Room: Impressive Suite
A good recap is always necessary after two days of thought leadership, meaningful insights and tactical tips. Let our moderators guide you through what they found most valuable and help you create your own list of top takeaways, favorite speakers and sessions.
More Information
Speakers
Sven Crone Dr.Lancaster Research Centre for Forecasting
Director
Lancaster Research Centre for Forecasting
Alex HancockShell Oil Company
Head of Treasury Analytics
Shell Oil Company
Chris TurnerStrataBridge
Co-Founder
StrataBridge
5:30 pm
End of Conference
CloseSelected Tags: