A STUDY AGRICULTURAL BONUS IN BANK OF MAHARASHTA

Abstract

The agricultural sector in India has historically been a cornerstone of its economic structure, contributing significantly to GDP and employment. Despite numerous policy interventions and banking support mechanisms, rural farmers continue to face challenges related to credit availability, delayed financial assistance, and inadequate incentives. The concept of an Agricultural Bonus, specifically within the Bank of Maharashtra, serves as a timely intervention designed to motivate timely loan repayments, support investment in agricultural inputs, and enhance crop yields. This study aims to delve deep into the practical structure, outreach, challenges, and impact of such bonus schemes. However, manual identification of eligible beneficiaries often leads to inefficiencies, delays, and unequal benefit distribution. To address this, the study explores machine learning (ML) integration into the scheme, where historical data patterns are leveraged to build intelligent prediction models. Algorithms such as Decision Trees, Random Forests, SVM, and XGBoost are used to model the behavior of farmers and assess bonus eligibility. By combining economic policy analysis with software technology, the study brings a fresh interdisciplinary approach. It not only provides insights into the current agricultural bonus scheme in Bank of Maharashtra but also proposes a predictive MLbased decision support system that can revolutionize financial inclusion in rural areas. This innovation will ensure better targeting, timely disbursement, and increased agricultural productivity.