Abstract: The increasing importance of quantitative investment strategies has been a focal development in the hedge fund industry over the past few years. The high volume and availability of data have driven quantitative firms to take their efforts to a new level, while more traditional firms have been gradually incorporating quantitative approaches to investment decisions. Data science and analytics are at the center of this development, where computing power, financial markets technologies and access to data have combined to create an emerging and powerful branch in the financial landscape. In this talk I will discuss data science and machine learning applications to building quantitative investment strategies. More specifically, I will demonstrate the pros and cons of different algorithms, from simple regression to decision tree-based approaches. This will be illustrated through an investment strategy that gains form out of the money put options written on stocks with the worst predicted performance, using a combination of security-specific attributes as well as information from company fundamentals.