Published Online:January 2026
Product Name:The IUP Journal of Accounting Research & Audit Practices
Product Type:Article
Product Code:IJARAP100126
DOI:10.71329/IUPJARAP/2026.25.1.211-230
Author Name:Upelina Bina Murmu and Dushyant Ashok Mahadik
Availability:YES
Subject/Domain:Finance
Download Format:PDF
Pages:211-230
Lack of quality, consistent, and timely data hinders the smooth functioning of risk assessment and claim settlement, which has an impact on the accurate pricing of insurance premia and farmers’ satisfaction. The present paper addresses these challenges by integrating high-resolution remote sensing data, specifically the Normalized Difference Vegetation Index (NDVI) and temperature, into a Bayesian regression framework for crop yield estimation. The proposed method captures the relationship between yield and remote sensing indicators while accounting for uncertainty in both the data and model parameters. In 16 wheat-growing districts of northern India, the Bayesian model demonstrates improved predictive accuracy compared to traditional linear regression. These findings highlight the potential of probabilistic modeling to enhance transparency and adaptability in crop insurance pricing.
The development of an effective financial market is crucial to protect farmers, particularly the small-scale farmers of developing countries who lack access to financial instruments. An effective insurance market is capable of transferring high-magnitude risk to protect vulnerable farmers from financial shock. In India, 38.22 million hectares of land are insured, which accounts for approximately 23.86% of the total cropped area (MSPI, 2023). The numbers indicate great potential for developing the country’s crop insurance market. In the absence of a suitable insurance market, financial services and insurance products, farmers are forced to rely on personal finance and moneylenders (Cole et al., 2017). Initiatives for introducing new insurance products that are better priced need to be taken.