Coffee and Registration
Start of conference – Chairperson’s introduction and welcome
Keynote: Storytelling with Data Visualisation & Mastering Data Communications
Patrice Latinne, Executive Director, EMEIA Financial Services, Data & Analytics Advisory, Ernst & Young Special Business Services
Facts get recorded, stories get remembered... Telling a story on top of good visualization of facts allows us to send the right data-driven message through to the right audience. In this talk, Patrice will illustrate this with some famous or personal use cases.Speakers:
Deceiving Data Visualization
Leenke De Donder, Data Visualization Consultant at TriFinance
Even after meticulous data gathering, cleansing and analysing, you can still ruin your data project in the end by visualizing your data wrongly. After all your hard work, this will (intentionally or not) skew the message. Being aware of specific design pitfalls, but also of moral values, transparency and the literacy of the audience is important to avoid an inaccurate communication of data.Speakers:
Leenke De Donder
Bloomberg's Approach to Data Visualisation
Flow Bohl, UX Architect, Bloomberg New Energy Finance
♦ What is the Bloomberg approach to data visualisation?
♦ How does animation matter in data viz?
♦ How can data viz be made feasible for large scale consumption on web and video?Speakers:
Speaker Panel and Q&A Session
Seven Steps to Achieving the Ultimate BI Visual Quick Win
Nicolas Henry, Managing Director, BI Brainz Limited
Discover what you need to achieve the ultimate BI Visual Quick Win
♦ Find out where most BI visual projects fail and how to avoid it
♦ Learn how to qualify a BI Visual Quick Win, and when to say 'No'
♦ Learn what skillsets you must have to succeed, and what to do if you don't
♦ Get a peek into a real-world example of BI Visual Quick win and see why it worked!Speakers:
Case Study: Recommendation Engines: optimizing mean square error or user experience?
Kasper Van Lombeek, Data Scientist and Co-Founder, Rockestate
Since the 1 million euro contest to improve the performance of the Netflix recommendation engine, recommender algorithms are one of the hottest topics in data science today. That is why we, passionate data scientists, had to build our own recommendation engine. As young fathers with lots of friends having babies, we asked ourselves: can we build a service that finds out your taste and recommends a baby name for you? Today we have a solid website www.namesilike.com that does exactly that.
With today’s online tutorials, it is not very difficult to learn how to build a recommender system based on a dataset. Those tutorials only talk about mathematically optimizing the algorithm. But that is not what you have to optimize! You have to set up a whole process online, starting from finding out the user’s taste with the least possible effort, and ending with showing the recommendations. The difference between optimizing the accuracy versus the user experience is enormous. For example: some of the most interesting algorithms create beautiful visualizations of your products. Although you lose a bit in prediction power, the gain in user experience is enormous. In our talk we highlight some of these trade-offs. They are all real lessons learned on Names I Like, validated by thousands of user clicks.Speakers:
Kasper Van Lombeek
Winning Ways for Your Visualization Plays
Mark Grundland, Functional Elegance
What enables an effective visualization to deliver insight at a glance? This talk presents practical techniques for how information visualization design can take better account of the fundamental limitations of visual perception, exploring the design choices that determine whether a picture can communicate the data it is meant to represent.Speakers:
Speaker Panel and Q&A Session