Insurance fraud claims have become a major problem in the insurance industry. Several investigations have been carried out to eliminate negative impacts on the insurance industry as this immoral act has caused the loss of billions of dollars. In this paper, a comparative study was carried out to assess the performance of various classification models, namely logistic regression, neural network (NN), support vector machine (SVM), tree augmented naïve Bayes (NB), decision tree (DT), random forest (RF) and AdaBoost with different model settings for predicting automobile insurance fraud claims. Results reveal that the tree augmented NB outperformed other models based on several performance metrics with accuracy (79.35%), sensitivity (44.70%), misclassification rate (20.65%), area under curve (0.81) and Gini (0.62). In addition, the result shows that the AdaBoost algorithm can improve the classification performance of the decision tree. These findings are useful for insurance professionals to identify potential insurance fraud claim cases.

Research background: Balancing economic expansion with environmental sustainability has become a central policy challenge. Green total factor productivity (GTFP) integrates environmental constraints into productivity analysis and is increasingly used as a measure of green growth. However, evidence on how GTFP shapes macro‑level economic performance remains limited, with existing research largely confined to a small number of single‑country studies. Purpose of the article: This study aims to investigate the causal effect of GTFP on economic growth using a global sample of 150 countries. It further seeks to identify the key transmission mechanisms through which GTFP influences macroeconomic outcomes and examines the moderating role of household savings rates in this relationship. Methods: Using a macro panel dataset for 150 countries from 2014 to 2023, this study first measures GTFP with a machine learning-enhanced three-stage slack-based measure-data envelopment analysis model combined with the global Malmquist productivity index. Subsequently, a double/debiased machine learning (DDML) model is employed to estimate the causal impact of GTFP on economic growth, effectively addressing the challenges of high-dimensional confounders and nonlinearities present in the data. Findings & value added: The results demonstrate a significant and robust positive relationship between GTFP and economic growth. This effect is primarily transmitted through two channels, which are enhancing exports and increasing household consumption. Furthermore, a high household savings rate is found to amplify the positive impact of GTFP on economic growth, validating the ‘Golden Rule’ savings rate proposition. This study contributes to the literature by providing the first large-scale, global evidence on the macroeconomic benefits of improving GTFP. By identifying specific transmission pathways and moderating effects employing DDML techniques for causal inference, this study offers empirical insights for policymakers to design effective green growth policies.