Methods in handling issues of massive data imbalance and correlation

Speakers: George Vafiadis & Hao Sky Zhou is a leading price comparison site that hold massive amount of web-traffic and demographic data. Our aim as data scientists and data engineer are to identify opportunities to help potential customers save money across a diverse range of products, from car and home insurance; to energy; to personal finances, such as credit cards and loans through the use of these data. We will be sharing our newly developed methods in dealing with both data imbalance and correlation among target responses issues within the work. One can modify and implement these methods to solve similar problems during their data science projects.

Bio: George Vafiadis, is a senior software engineer responsible for the design and implementation of BigData Platforms at CompareTheMarket. He has MSc in Communications Systems and Signal Processing from University of Bristol and BEng in Information and Communication Systems Engineering from University of the Aegean.

Bio: Hao Sky Zhou, obtained a MSc Statistics from University of Warwick 2009 and a PhD in Econometrics and Statistics in 2012 from University of Leicester worked as senior data scientist at Sky Betting and Gaming before joining in 2016.