2024 · 11 citations · 10 references
ComputingHealth InformaticsInsuranceHealth InsuranceMachine LearningPredictive AnalyticsDecision TreesEnsemble LearningEnsemble MethodsOverfittingPredictive Health ModelingRisk PredictionBenchmark DatasetsK-nearest NeighborsMachine Learning For InsuranceMachine Learning Prediction ModelsRandom Forest ClassificationRandom ForestsRegression TreesXgboost
The use of machine learning algorithms for health insurance is a key area that aims to improve the accuracy and efficacy of these processes. This field focuses on anomaly detection and predictive modeling using a range of techniques, such as XGB regressors, random forest regressors, decision tree regressors, and k-neighbors regressors. Applications of decision tree regression are well recognized for their interpretability and simplicity of usage. An individual may successfully pinpoint the insurance system's shortcomings with a performance score of 0.85. In addition, the random forest regressor works wonderfully, this regressor is well-known for its capacity to manage complex datasets and reduce overfitting. The use of comparable machine learning algorithms in health insurance ensures accurate diagnosis of medical conditions, whilst error detection in insurance systems protects against errors and inconsistencies. Decision Tree (0.85), KNN (0.67), Random Forest (0.83), and XGB (0.70). XGB and KNN regressors are outperformed by Decision Tree and Random Forest models in terms of accuracy in predicting. In terms of overall R2 score, Decision Tree Regressor performs best, demonstrating its ability to accurately capture the variance of the target variable.
10
Disease Prediction by Machine Learning Over Big Data From Healthcare Communities
Min Chen, Yixue Hao, Kai Hwang et al. · IEEE Access · 2017 · 1.3K citations · Full text
S. Chowdhury, P. Mayilvahanan, Ramya Govindaraj · International Journal of Computers and Applications · 2020 · 93 citations