Stock market price prediction using time series models

Ramteke, Manasi (2020) Stock market price prediction using time series models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (905kB) | Preview

Abstract

Stock market prediction is a very mysterious job for traders in stock market. Investors are risking their funds to gain the profit. Even so, they do sometimes face losses because of the incorrect stock index forecast. India has fifth largest economy by nominal GDP in the world. The time series prediction can be particularly be applied in financial matters. In this paper, the time series models such as PROPHET, KERAS with LSTM and ARIMA are used to forecast the stock market for four popular Indian banks. Data gathered from yahoo finance over the last 10 years was used to create required models. To find the best time series model, the RSME value of each model has been drawn. Model with lowest value of RSME will be considered as a best model. At last, the web application has been developed which will help users to provide the predicted values of the some future which will help in lowering the risk of losing the money.
Keywords: PROPHET, ARIMA, KERAS, LSTM.

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 H Social Sciences > HG Finance > Investment
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	20 Jan 2021 18:13
Last Modified:	20 Jan 2021 18:13
URI:	https://norma.ncirl.ie/id/eprint/4412

Actions (login required)

View Item