Alan Reiner

I took 30 weeks of courses in the Advanced Machine Learning specialization on Coursera, in my spare time. This included Deep Learning, Bayesian Methods, Computer Vision, Reinforcement Learning and NLP.

I worked on more than a dozen different ML/DL projects including object detection, face recognition, segmentation, image captioning, seq2seq models, text generation and learning to play Atari games with only raw screen pixels. I also gained direct experience with VAEs, GANs, U-Nets, transfer learning, LSTMs, Deep Q-Learning, A3C, and Bayesian methods such as EM and MCMC.

I gained access to the text-file poker-hand histories of 1,500 online poker games played by a professional poker player. It used heavy feature engineering, statistics, neural networks, and SVMs to mimic that player's betting patterns for use in real-time play. The bot performed very well against other bots, though we were never able to deploy it in a real online poker site since the sites have gotten extremely good at detecting bots and confiscating funds.

LendingClub is a peer-to-peer platform to connect individual investors with borrowers who cannot get loans through a bank (or want a lower interest rate). The site has made public all the information of over one million historical loans, which makes it perfect for data mining and machine learning.

I thoroughly analyzed and produced multiple different machine learning (ML) models to try to identify high-value borrowers and created an automated system to process new borrower applications and invest if they receive a high score.