Repo Rate Modelling based on Financial and Economic Factors

Rathee, Himanshu (2021) Repo Rate Modelling based on Financial and Economic Factors. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (728kB) | Preview

Abstract

Interest rate is the most important financial variable that helps in determining the macro and microeconomic policy of a country. Therefore predicting any change in the value of interest rates become crucial for the government and various other financial institutions. This research aims to forecast the interest rates for India and analyze various factors affecting the change in the interest rates for better forecasting. A novel approach of using sentiment analysis of tweets of various users about the economic situation along with various financial and economic variables that help in predicting interest rates has been used. Four machine learning models namely: Vector autoregressive model, Long short term memory, Sequential neural network, and Multilayer perceptron neural network have been compared based on evaluation metrics such as root mean square error, mean absolute error, and mean absolute error percentage. The analysis shows that the machine learning model with input as sentiment analysis along with various financial variables outperforms the models with input as various financial variables. The best model is the Multilayer perceptron neural network model trained with the novel approach and has a mean absolute error percentage of 1.76%.

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 > Economics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	14 Dec 2021 11:48
Last Modified:	14 Dec 2021 11:48
URI:	https://norma.ncirl.ie/id/eprint/5215

Actions (login required)

View Item