A Machine Learning Approach to Research Curation for Investment Process
Sonya Cates, Stephen Lawrence, Carla Penedo and Viktoriia Samatova
Many investment professionals consider academic research instrumental in improving the quality of the investment process. However, it is hard to extract investment insights from the vast and rapidly expanding research corpus, which requires a large amount of time and human effort in order to absorb. We offer a novel solution to this problem by introducing a machine learning approach to research curation. By comparing the performance and accuracy of humans and machines, we show that a machine learning approach approximates the quality of human curation but offers the strategic benefits of scalability, efficiency and lower cost.