Predicting Stock Market Trends Using Economic Variables and Machine Learning

Nidan, Niraj (2023) Predicting Stock Market Trends Using Economic Variables and Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (827kB) | Preview

Abstract

This project aims to address the challenge of predicting time series in the realm particularly for exchange rates and market indices. Advanced deep learning techniques such, as Graph Recurrent Networks (GRN) Gated Recurrent Units (GRU) and Long Short Term Memory (LSTM) models are employed to enhance forecasting models. Upon comparing the GRU and LSTM models it becomes evident that the LSTM model performs better yielding predictions. Furthermore incorporating Graph Recurrent Networks (GRN) into the research further improves performance by considering connections within data. The ensemble model, which combines estimates from GRU, LSTM and GRN together demonstrates performance with a squared error (MSE) of 0.2607. These innovative methods that leverage GRN and RNN algorithms mark progress in time series forecasting for markets. In applications these models contribute to improved accuracy, in predictions enabling professionals to manage risks and make strategic decisions. Going forward researchers may explore tuning hyperparameters and amalgamating data from diverse sources to enhance the models generality even further.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > Economics 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:	18 May 2025 14:55
Last Modified:	18 May 2025 14:55
URI:	https://norma.ncirl.ie/id/eprint/7578

Actions (login required)

View Item