Supervisor

Vikas Tomer

Programme

MSc in Data Analytics

Abstract

This study explores the use of Long Short Term Memory (LSTM) networks, a variant of Recurrent Neural Networks (RNNs), in the context of financial forecasting, specifically oil price prediction. The research follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology and tests six different LSTM variants. The models are evaluated based on Mean Squared Error (MSE), aiming to determine the optimal parameter settings for each LSTM type. Among the variants tested, the Gated Recurrent Unit (GRU) emerged as the highest performer, achieving an MSE of 0.100. This was surprising, as simpler variants outperformed more complex ones, suggesting that simpler LSTM models may be better suited for financial time series forecasting, especially with simpler datasets.

In addition to the model experiments, primary research, including interviews with industry professionals, was conducted to validate the results and gather suggestions for improving the methodology. It was concluded that future studies could improve the reproducibility and robustness of the findings by using a random seed for model training and implementing multiple code versions to gather a distribution of results, which would enhance the general reliability of the outcomes.

Date of Award

2024

Full Publication Date

2024

Access Rights

open access

Document Type

Capstone Project

Resource Type

thesis

Share

COinS