Sentiment Analysis and Evolution of Cashless India: Pre-Covid, During Covid and-Post Covid

Gaikwad, Vaishnavi Sandip (2024) Sentiment Analysis and Evolution of Cashless India: Pre-Covid, During Covid and-Post Covid. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (940kB) | Preview

Abstract

The research considers the sentiments of the users and performs sentiment analysis to understand their response to the evolution of cashless payment, through Google Pay, Phone Pe, and Paytm UPI apps. The data for the same was collected by web scraping app reviews, and were then categorised as positive, negative and neutral, in the periods namely categorised as Pre-Covid, Post-Covid, and during Covid periods. Later, the study used machine learning and deep learning models, viz: LSTM (long short-term memory), ARIMA and SARIMA, to predict future transaction volumes of these apps based on empirical UPI data from the NPCI website.

The study pre-processed transaction volume data from 2017 to 2024 and forecasted usage from 2025 onwards to understand the trajectory of cashless payments in India. The models were considerably successful in predicting the transaction volumes for Google Pay, Phone Pe, and Paytm, identifying which app is will most likely be used in the future. The study provides valuable insights for industry practitioners and academic researchers into the evolution of cashless payment apps in India, wherein the models can help in providing better insights for better financial forecasting.

The findings can have a significant impact on fintech companies, for using data-driven strategies and for optimal operational efficiencies that support the global adoption and evolution of secure cashless payment systems. The effectiveness and advantages of LSTM, ARIMA, and SARIMA models is also highlighted in our research which will thereby help in forecasting UPI transaction over time, contributing to the field of financial time series analysis.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Siddig, Abubakr UNSPECIFIED
Uncontrolled Keywords:	LSTM Neural Networks; Financial Time Series Forecasting; UPI Transaction Volumes; Google Pay; Paytm; Phone Pe; Sentiment Analysis; Pre-Covid; Post-Covid; During-Covid
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Diseases > Outbreaks of disease > Epidemics > COVID-19 Pandemic, 2020- H Social Sciences > HG Finance > Banking > E-banking
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	18 Aug 2025 13:20
Last Modified:	18 Aug 2025 13:20
URI:	https://norma.ncirl.ie/id/eprint/8561

Actions (login required)

View Item