A Relational Data Matching Model for Enhancing Individual Loss Experience: An Example from Crop Insurance

The focus of this article is on predictive analytics regarding data scarcity and credibility, which are major difficulties facing the agricultural insurance sector, often due to limited loss experience data for those infrequent but extreme weather events. A new relational data matching model is presented to predict individual farmer yields in the absence of farm-level data. The relational model defines a similarity measure based on an Euclidean distance metric that considers weather information, farm size, county size, and the coefficient of variation of yield to search for the most “similar” region in a different country to borrow individual loss experience data that are otherwise not available. Detailed farm-level and county-level corn yield data in Canada and the United States are used to empirically evaluate the proposed relational model. Compared to the benchmark model, the empirical results confirm the efficiency of the proposed model in that it yields lower prediction error with smaller variation, and it recovers the actual premium rate more accurately. The proposed relational model provides a new approach for insurers, reinsurers, and governments to enhance individual loss experience, helping to overcome issues (such as data scarcity, credibility, and aggregation bias) that present substantial challenges in risk modeling, pricing, and developing new insurance programs, particularly for developing countries.