Predictive Analysis of Stock Market Trends: A Machine Learning Approach

Biju, Akshay Kumar (2024) Predictive Analysis of Stock Market Trends: A Machine Learning Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (708kB) | Preview

Abstract

The stock market is a vibrant but ever-fragile market in which we see the stocks being exchanged based on some pullers like the performance of the company, trends, and even macroeconomic factors. The statistical models and technical analysis that were used in traditional methods to predict stock prices have not been able to capture all the details and interrelations in the large amount of data available. To overcome these challenges of stock price prediction, this study employs three advanced algorithms namely XGBoost Regressor, LSTM, and BiLSTM to forecast Tesla (TSLA) stock prices. The dataset in this study contains historical stock prices which include Open, High, Low, Close, Adjusted Close, and Volume obtained from Yahoo Finance. To improve the quality of predictability, the data was preprocessed through feature scaling via Min-Max scaling of the data making all features consist of the same range of values. The performances of the models were assessed according to the performance metrics including MSE and RMSE and from the metrics BiLSTM had the best performance. BiLSTM being capable of capturing bidirectional dependencies over the time series, presented a high R-squared to signify it was apt for predicting Tesla’s stock prices. This work therefore points towards the possibility of using ML specifically the deep learning framework to overcome the weaknesses of the traditional Stock Price prediction models.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rifai, Hicham UNSPECIFIED
Uncontrolled Keywords:	Stock Market; Stock Price Prediction; Machine Learning; XGBoost Regressor; LSTM; BiLSTM; Time-Series Forecasting; Min-Max Scaling; Data Normalization
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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:	01 Sep 2025 15:32
Last Modified:	01 Sep 2025 15:32
URI:	https://norma.ncirl.ie/id/eprint/8684

Actions (login required)

View Item