Comparative Analysis of Machine Learning Models for S&P 500 Prediction

Kanwar, Soumiya (2023) Comparative Analysis of Machine Learning Models for S&P 500 Prediction. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (620kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Three different machine learning algorithms namely Random Forest Classification, LSTM network, and Logistics regression are used to predict price changes of S&P 500 stocks. The study employs two distinct timelines for analysis: one covering from year 2000 till now and involving different markets situations, the other concentrating just in recession periods of 2007-2009.

The study starts by collecting past S&P 500 stock price and the necessary characteristics to produce an inclusive dataset. Subsequently, Random Forest Classification, LSTM, and Logistic Regression are used as predictive models, where each one possesses its distinct advantages.

The three models are subjected to comparisons by evaluating how they perform on the task of forecasting stock prices in these two periods. The aim of this study is to discover what works and does not work in each trading algorithm during both ordinary fluctuations in the market and abnormal recession period.

This project reveals a lot about machine learning’s use in financial prediction, which is of paramount importance to both investors, analysts, and researchers. The aim is to enlarge the applicability of predictive modelling regarding stock price prediction for the case study S&P 500 index through assessment of the models’ accuracy, robustness, and adaptability during both steady and turbulent conditions.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Investment Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HG Finance > Investment > Stock Exchange
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	14 May 2025 09:18
Last Modified:	14 May 2025 09:18
URI:	https://norma.ncirl.ie/id/eprint/7542

Actions (login required)

View Item