JavaScript is disabled for your browser. Some features of this site may not work without it.
Toggle navigation
Singh, Manish
DownloadThesis PDF (16.53Mb)
Lo, Andrew W.
In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/
In this thesis, titled "Data Science in Investment Management," we aim to explore the applications of data science and artificial intelligence across various dimensions of investment management, offering innovative solutions and insights to the industry. This thesis is composed of several parts, each addressing a different aspect of investment management and leveraging data science techniques to deliver valuable insights. In first part, for industries and crypto-currencies, we develop a dynamic classification system that groups stocks according to quantified similarities from a wide variety of structured and unstructured data features. With the availability of big data, we were able to use artificial intelligence (AI) methods to extract relevant information about companies from various data sources and learn about their similarity in the future, according to market perception. In second part, we study ways of creating capital and portfolio management for fusion energy and biopharmaceutical investments. By leveraging computational techniques like portfolio approach, we provide novel insights into the optimal financing strategies for high-risk, high-reward ventures like fusion research and biopharmaceutical investing. We also quantify the impact of clinical trial results on the stock prices of the companies, that can aid biopharma investors in risk management. Given the increasing interest in ESG investing, we study the excess-returns of the ESG investing. We also develop the measure of the impact on patient lives due to the products of the biopharmaceutical companies that can attract ESG funds for biopharmaceutical companies. Next part of the thesis investigates the real-time psychophysiological analysis of financial risk processing, offering a deeper understanding of human behavior in the context of investment decision-making using a data driven approach. In the next part, we focus on the use of explainable Machine Learning for an important problem of consumer credit risk. In the final part, we conclude with the discussion about the future of Artificial Intelligence and Data Science in Finance.
