Remote Sensing Data in Risk Measurement Model for Crop Insurance

Abstract

Insurance pricing precision relies on the availability and quality of data. The Indian crop insurance industry requires technologically updated data and an efficient risk measurement model to better price its insurance products. In this study, we propose the incorporation of remote sensing data in the wheat crop yield prediction model to be used in crop insurance. High-frequency MODIS Terra satellite Leaf Area Index data is used in yield simulation through the Monte Carlo method. The finding of the study brings forward the overvaluation of crop insurance products in India. Loss prediction coming out of our analysis is reducing the need for loading insurance premia. The study explores the distribution appropriate for 16 North Indian wheat-producing districts, which is carried out by testing the normal distribution of a parametric method and kernel-based non-parametric method. Our proposed model caters for the need for accurate pricing of insurance in the Indian Crop insurance market