APPLICATION OF MACHINE LEARNING IN PREDICTING HUMAN LIFE EXPE-CTANCY BASED ON SOCIO-ECONOMIC AND DEMOGRAPHIC CHARACTERISTICS
DOI:
https://doi.org/10.24867/30BE31AleksicKeywords:
HALE, semi-supervised learning, WHO-datasetAbstract
This paper analyzes the application of various machine learning methods in predicting human life expectancy using socio-economic and demographic characteristics. Through data processing from the 'World Health Statistics 2020' dataset, models have been developed using algorithms such as Decision Tree, XGBoost, Random Forest, and neural networks. The paper describes the data preprocessing process, model training, and performance evaluation, with a particular focus on the use of Python libraries such as NumPy, Pandas, TensorFlow, and Scikit-learn for implementing the solutions.
References
[1] Wolfson, M.C., 1996. Health-adjusted life expectancy. Health Reports-Statistics Canada, 8, pp.41-45.
[2] Luy, M., Di Giulio, P., Di Lego, V., Lazarevič, P. and Sauerberg, M., 2020. Life expectancy: frequently used, but hardly understood. Gerontology, 66(1), pp.95-104.
[3] Tanha, J., Van Someren, M. and Afsarmanesh, H., 2017. Semi-supervised self-training for decision tree classifiers. International Journal of Machine Learning and Cybernetics, 8, pp.355 370.
[4] Hill, K. and Choi, Y., 2006. Neonatal mortality in the developing world.Demographic research, 14, pp.429-452.
[2] Luy, M., Di Giulio, P., Di Lego, V., Lazarevič, P. and Sauerberg, M., 2020. Life expectancy: frequently used, but hardly understood. Gerontology, 66(1), pp.95-104.
[3] Tanha, J., Van Someren, M. and Afsarmanesh, H., 2017. Semi-supervised self-training for decision tree classifiers. International Journal of Machine Learning and Cybernetics, 8, pp.355 370.
[4] Hill, K. and Choi, Y., 2006. Neonatal mortality in the developing world.Demographic research, 14, pp.429-452.
Downloads
Published
2025-04-04
Issue
Section
Electrotechnical and Computer Engineering
