Article citationsMore>>

Smith, T. and Johnson, D. (2023) Extreme Machine Learning for Agricultural Risk Assessment: A Case Study of Weather-Related Perils. Journal of Risk Analysis in Agriculture, 17, 201-218.

has been cited by the following article:

• TITLE: The Extreme Machine Learning Actuarial Intelligent Agricultural Insurance Based Automated Underwriting Model

  AUTHORS: Brighton Mahohoho

  KEYWORDS: Extreme Machine Learning, Actuarial Underwriting, Machine Learning, Intelligent Model, Agricultural Insurance

  JOURNAL NAME: Open Journal of Statistics, Vol.14 No.5, October 31, 2024

  ABSTRACT: The paper presents an innovative approach towards agricultural insurance underwriting and risk pricing through the development of an Extreme Machine Learning (ELM) Actuarial Intelligent Model. This model integrates diverse datasets, including climate change scenarios, crop types, farm sizes, and various risk factors, to automate underwriting decisions and estimate loss reserves in agricultural insurance. The study conducts extensive exploratory data analysis, model building, feature engineering, and validation to demonstrate the effectiveness of the proposed approach. Additionally, the paper discusses the application of robust tests, stress tests, and scenario tests to assess the model’s resilience and adaptability to changing market conditions. Overall, the research contributes to advancing actuarial science in agricultural insurance by leveraging advanced machine learning techniques for enhanced risk management and decision-making.