Date of Award

12-2023

Document Type

Campus Access Dissertation

Degree Name

Doctor of Philosophy (PhD)

First Advisor

Chi CW Wan

Second Advisor

Rui RL Li

Third Advisor

Farid FK Khosravikia, Safer ZY Yuksel

Abstract

I develop novel frameworks to predict future stock returns, using alternative big data sources, and various machine learning models. This research endeavor can be systematically described as a mixture of the following steps : 1) Study and quantify an alternative big data source that could potentially inform future returns. 2) Modify and utilize state-of-the-art machine learning approaches that could improve prior estimations or inferences. 3) Provide better interpretable and understandable conclusions of the driving forces in return predictability. Specifically, I present three related essays : (1) I examine the technical mechanics of machine learning models specifically suited for empirical asset pricing with an emphasis on loss function design and the subsequent effects on model behavior. (2) I examine whether temporal dependencies improve return predictions in a generalized framework that encompasses various factors; where I propose an interpretable long short-term memory (LSTM) framework. (3) We predict future returns by developing a novel dynamic framework to measure the proportional demand for tech-oriented skills in a firm hiring profile.

Comments

Free and open access to this Campus Access Thesis is made available to the UMass Boston community by ScholarWorks at UMass Boston. Those not on campus and those without a UMass Boston campus username and password may gain access to this thesis through resources like Proquest Dissertations & Theses Global (https://www.proquest.com/) or through Interlibrary Loan. If you have a UMass Boston campus username and password and would like to download this work from off-campus, click on the "Off-Campus UMass Boston Users

Download
Off-Campus UMass Boston Users

Share

COinS