Predicting life expectancy using random forest based on key socioeconomic factors

View at publisher Summarise with VIRAT
Authors: Hamzah Zufarul Furqon, Mochamad Alfan Rosid, Ade Eviyanti, Yunianita Rahmawati, Avdeeva Anna Nikolaevna, Otabek Gaybullaev
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Life expectancy reflects societal well-being but varies significantly across Asia due to disparities in education, health, and socioeconomic factors. Previous studies lacked comprehensive geographic scope and advanced modeling to capture complex relationships. This study develops a predictive model for life expectancy using the Random Forest Regressor. The model achieved 96.5% accuracy and an MAE of 0.99, with key predictors being school years, HDI, and BMI. Integrating GridSearchCV, the approach ensures robust and interpretable predictions across diverse contexts. Insights support policies promoting education, human development, and health to enhance population welfare.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Insurance Mortality Demography Risk Management Data Mining and Machine Learning Applications

Publication details

Journal / source
AIP conference proceedings
Volume
3480
Pages
040010–040010
Publication date
1 January 2026
Language
EN