NORMA eResearch @NCI Library

Impact Analysis of Market Sentiments, Gold and Crude oil prices on DOW30 stocks

Mehta, Yash (2020) Impact Analysis of Market Sentiments, Gold and Crude oil prices on DOW30 stocks. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

Data Analytics and AI has established its roots in stock market trading for past few years. Automated trading developed using AI is capable of taking multiple factors as input to finally predict the stock movement. But researchers are still working on defining the sum of exact factors that influences the stock market. Till date many researches have proved that human sentiments are significantly causal to stock index movement and can help to predict stock prices and trends. This research aims at developing a machine learning model to predict the future trend of DOW30 stocks using multiple factors like market sentiments from twitter and news, gold prices and crude oil prices. Datasets used in this research have been collected from various sources like Yahoo finance for stocks data, Kaggle for news sentiments data and Twitter analysis dataset collected from one of the previous research works. Granger causality test has been implemented to identify the factors that are significant in predicting future trend of stocks. Multiple machine learning models like Vector Auto Regression (VAR), SVM and kNN has been implemented. SVM and kNN’s performance has been evaluated using various factors like accuracy, precision, recall, and f1 score. Whereas, VAR’s performance has been evaluated using MAPE. The models have also been tested using transfer learning technique and the results showed that the VAR model performed more consistently.
Keywords: DOW30, Stock Market, Market Sentiments, Crude Oil and Gold prices, Forecasting, stock index prediction, kNN, VAR, SVM, Transfer Learning

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 20 Jan 2021 17:06
Last Modified: 20 Jan 2021 17:06
URI: https://norma.ncirl.ie/id/eprint/4406

Actions (login required)

View Item View Item