Advancing Oligopoly Pricing Predictions through Machine Learning within the Indian Telecommunication Industry

Abstract

This paper looks at how machine learning can be used to predict revenue in the Indian

telecommunication industry, which is mainly controlled by Reliance Jio, Bharti Airtel and

Vodafone Idea. Quarterly data on subscriber numbers and average revenue per user was

collected from company reports. Three models were tested: Linear Regression, Decision Tree

Regression and Random Forest Regression. The data was divided into a training set and a test

set using a 70 to 30 ratio. Model accuracy was measured using Mean Squared Error and Mean

Absolute Error. The results showed that Random Forest gave the best predictions, followed by

Decision Tree and then Linear Regression. The study shows that machine learning can help

companies make better pricing and planning decisions in a competitive market. It also suggests

that future research could use more advanced models and include outside factors like

government policies or economic changes to improve predictions further.