Machine Learning Models for Predicting Romanian Farmers’ Purchase of Crop Insurance

Abstract

Considering the large size of the agricultural sector in Romania, increasing the crop insurance adoption rate and identifying the factors that drive adoption can present a real interest in the Romanian market. The main objective of this research was to identify the performance of machine learning (ML) models in predicting Romanian farmers’ purchase of crop insurance based on crop-level and farmer-level characteristics. The data set used contains 721 responses to a survey administered to Romanian farmers in September 2021, and includes both characteristics related to the crop as well as farmer-level socio-demographic attributes, perception about risk, perception about insurers and knowledge about agricultural insurance. Various ML algorithms have been implemented, and among the approaches developed, the Multi-Layer Perceptron Classifier (MLP) and the Linear Support Vector Classifier (SVC) outperform the other algorithms in terms of overall accuracy. Tree-based ensembles were used to identify the most prominent features, which included the farmer’s general perception of risk, their likelihood of engaging in risky behaviour, as well as their level of knowledge about crop insurance. The models implemented in this study could be a useful tool for insurers and policymakers for predicting potential crop insurance ownership.

Assessment of factors determining consumer satisfaction with crop insurance services

“…To develop a model for measuring consumer satisfaction with crop insurance services in Lithuania, one should draw on Mare et al (2022), who argue that to measure consumer satisfaction with crop insurance services adequately, it is necessary to consider the socio-demographic characteristics of consumers, which can be used to assess changes based on age, experience with insurance and farming, the area in which they work, and the size of the farm. The consumer evaluation indices show that these elements of the model are necessary to distinguish between transactional and perceived satisfaction.…”

Optimizing Pension Participation in Kenya through Predictive Modeling: A Comparative Analysis of Tree-Based Machine Learning Algorithms and Logistic Regression Classifier

“…Machine learning has been used in various financial applications, such as behavioral prediction, price modeling, algorithmic trading, portfolio management, fraud detection, customer churn, investor sentiment analysis, and credit risk prediction (Dixon et al 2020;Renault 2020;Belhadi et al 2021). Bankruptcy prediction, cryptocurrency volatility prediction, clustering causes of death in insurance-related data (Bett et al 2022), predict farmers' uptake of crop insurance (Mare et al 2022), and business sustainability have also been modeled using machine learning techniques (Bouri et al 2021a;Barboza et al 2017;Kipkogei et al 2021).…”

Towards a holistic approach to sustainable risk management in agriculture in the EU: a literature review

“…Besides deterministic approaches, Machine Learning solutions start to be applied to further understand factors affecting the adoption of RM strategies. Few applications can be retrieved from the current literature considering application of insurance contracts in Romania and Italy (Mare et al, 2022;Biagini et al, 2022a) and mutual funds for pest diseases in the North of Italy (Höschle et al, 2023).…”