Marios Michailidis

Marios Michailidis

Marios Michailidis

Data Scientist

About

Recent world no.1 Kaggle Grandmaster, Marios Michailidis, is now a Research Data Scientist at H2O.ai. He is finishing his PhD in machine learning at the University College London (UCL) with a focus on ensemble modeling and his previous education entails a B.Sc in Accounting Finance from the University of Macedonia in Greece and an M.Sc. in Risk Management from the University of Southampton. He has gained exposure in marketing and credit sectors in the UK market and has successfully led multiple analytics’ projects based on a wide array of themes including: acquisition, retention, recommenders, uplift, fraud detection, portfolio optimization and more. Before H2O.ai, Marios held the position of Senior Personalization Data Scientist at dunnhumby where his main role was to improve existing algorithms, research benefits of advanced machine learning methods, and provide data insights. He created a matrix factorization library in Java along with a demo version of personalized search capability. Prior to dunnhumby, Marios has held positions of importance at iQor, Capita, British Pearl, and Ey-Zein. At a personal level, he is the creator and administrator of KazAnova, a freeware GUI for quick credit scoring and data mining which is made absolutely in Java. In addition, he is also the creator of StackNet Meta-Modelling Framework. His hobbies include competing in predictive modeling competitions and was recently ranked 1st out of 465,000 data scientists on the popular data competition platform, Kaggle.


Autokazanova42

Stacking (or stacked generalization) is a technique that allows the data scientist to combine many different machine learning models in order to make better predictions. This technique has been used to win many machine learning competitions (in kaggle). This talk will present the basic elements of stacking and a generalised framework that uses it called StackNet. StackNet is a computational, scalable and analytical framework that resembles a feedforward neural network and uses stacking in multiple levels to improve the accuracy of predictions. StackNet will be demonstrated through practical examples with tips on how to make even stronger models.

Link: Github