Michael Davy

Bio

Currently a Principal Data Scientist at Kobalt Music. Previously, Data Science & Engineering Manager of the Audience Targeting Engine team at Schibsted, Staff Data Scientist at Schibsted, Senior Modelling Scientist at Quantcast and a Scientific Engineer at Struq.

My career is focused on the application of machine learning at scale to automate and improve performance. I have worked in the advertising, media and financial industries employing a range of machine learning techniques to solve complex business challenges.

Education

• Ph.D. in Computer Science from Trinity College Dublin in 2008 in the area of Artificial Intelligence. My research was funded through the Embark Initiative scholarship from the Irish Research Council for Science Engineering and Technology.

• M.Sc. in Computer Science (Networks and Distributed Systems) from Trinity College Dublin

• B.Sc. (Hons) in Computer Applications (Software Engineering) at Dublin City University

Thesis

My thesis investigated History-Based query selection strategies for Active Learning contributing novel and efficient query selection algorithms that leveraged information from classification predictions given in previous iterations. Other directions included unsupervised dimensionality reduction techniques specifically for text-based domain in an active learning setting and a reinforcement learning technique to dynamically switch among a number of alternative query selection strategies based on their relative performance.

Research Interests

• Natural Language Processing (NLP)

• Deep Learning

• Machine Learning

• Recommender Systems

• Active Learning

• Sentiment Analysis

• Reinforcement Learning