This team's solution write-up was originally published here by Daniel Hammack and cross-posted on No Free Hunch with their permission. Julian and I independently wrote summaries of our solution to the 2017 Data Science Bowl. What is below is my (Daniel's) summary. For the other half of the story, see Julian's post here. Julian is a freelance software/machine learning engineer so check out his site and work if you are looking to apply machine intelligence to your work. He won 3rd in last year's Data Science Bowl too! This blog post describes the story behind my contribution to the 2nd place solution to the 2017 Data Science Bowl. I will try to describe here why and when I did certain things but avoid the deep details on exactly how everything works. For those details see my technical report which has more of an academic flavor.

Ultimately I built two'ensembles' of models. The first ensemble I built really in an ad-hoc manner - during the process of tuning my neural net structure I trained a bunch of models. Many of them turned out to have similar performance, so I threw them all into an ensemble. This ensemble had a CV score of 0.41 (remember the prior best was 0.433 - averaging helps!). The second ensemble was more systematic (described below).

Julian and I independently wrote summaries of our solution to the 2017 Data Science Bowl. What is below is my (Daniel's) summary. For the other half of the story, see Julian's post here. Julian is a freelance software/machine learning engineer so check out his site and work if you are looking to apply machine intelligence to your work. He won 3rd in last year's Data Science Bowl too!