Now that you’ve learned a lot of the theory behind alpha and risk factors, and had a chance to work through some of the important ideas and exercises, you have the opportunity to put all these ideas into practice in your final project of term one. Personally, it’s my favorite project of the term in part, because I designed it. In this project, we code up and test several alpha factors. First, we evaluate the factors to see which ones may be promising candidates to put together into a combined alpha factor. We examine them initially to check whether the alphas have predictive power in the cross-section of stocks. We calculate their Sharpe ratios, and we tried to get a sense of how much trading they would incur by a turnover analysis. Then we throw the alphas into an optimizer in order to calculate optimal portfolio weights by maximizing our predicted return via our alphas and simultaneously attempting to neutralize exposure to common risk factors, which are sources of return variance. I created this project as a fully production-ready prototype, so that you could see how industry practitioners do this in the real world. It was especially important to me that you see how ideas for alphas turned into code and how both alpha and risk factor models played distinct and equally important roles in portfolio construction. I also utilized industry-ready Python libraries that make common operations simpler and faster, so you have a chance to get familiar with these packages. I’m really excited to share this methodology with you, and I hope you enjoy the project.