Southampton, 3 - 4 July, 2017
Marios Michailidis is
Research data scientist at H2O.ai
and part-time PhD in machine learning at University College London (UCL) with a focus on
ensemble modelling. He has worked in both marketing and credit
sectors in the UK Market and has led many analytics projects with
various themes including: Acquisition, Retention, Uplift, fraud
detection, portfolio optimization and more. In his spare time he has
created KazAnova, a GUI for credit scoring 100% made in Java as well
as is the creator of StackNet Meta-Modelling Framework. In his spare
time he loves competing on data science challenges and was ranked
1st out of 500,000 members in the popular Kaggle.com data
competition platform. Here
you can find a blog about Marios being ranked top in kaggle out of
470,000 data scientist sharing knowledge tricks and ideas. Finally,
Marios' website can be found here,
with more info on other related (free) software he has developed in
the past for predictive analytics.
TITLE OF TALK: Become Kaggle Number #1 using StackNet
ABSTRACT: The StackNet is a computational,
scalable and analytical, metamodeling framework implemented in Java
that resembles a feedforward neural network and uses Wolpert’s
stacked generalization on multiple levels to improve accuracy in
machine learning predictive problems. Kaggle.com is the word’s
biggest predictive modelling platform with over half a million
members that hosts machine learning competitions on which companies
and researchers post their data and data scientists from all over
the world compete to produce the best models. The talk will expand
on what is StackNet , what has been the inspirations behind it, how
it works and how it has been used to win multiple online modelling
competitions and become #1 in kaggle with specific use cases.
StackNet's official Repo is
here: Find here
a blog of StackNet methodology winning a popular data science
(kaggle) competition.