Enhancing predictive modeling across industries with automated machine learning: applications in insurance and agriculture

This study explores the efficacy of Automated Machine Learning (AutoML) tools in enhancing linear regression models across industries, focusing on insurance and agriculture. We assessed six widely used AutoML libraries—AutoKeras, AutoGluon, Hyperopt, MLJAR, LightAutoML, and H2O—on a Kaggle-sourced insurance dataset to evaluate their performance in predictive accuracy and operational efficiency. Additionally, we employed TPOT for crop prediction using a Kaggle-based agricultural dataset, demonstrating its application in supporting Sustainable Development Goals (SDGs) related to agriculture. The results showed that AutoML tools vary in effectiveness, with AutoGluon exhibiting superior performance on the insurance dataset due to its low Mean Squared Error (MSE). Similarly, TPOT excelled in optimizing crop yield predictions by automating machine learning pipelines. These findings underscore the versatility of AutoML in handling diverse data contexts, significantly improving model accuracy and reducing manual effort through automation. This study highlights the potential of AutoML to streamline predictive analytics across sectors, enabling data-driven decision-making in industries such as insurance for risk assessment and customer segmentation, as well as in agriculture for sustainable practices and crop optimization. Using datasets from Kaggle reinforces the accessibility and replicability of this research, providing a robust framework for further exploration in diverse industry applications.