Optimizing Pension Participation in Kenya through Predictive Modeling: A Comparative Analysis of Tree-Based Machine Learning Algorithms and Logistic Regression Classifier

Abstract

Pension plans play a vital role in the economy by impacting savings, consumption, and investment allocation. Despite declining mortality rates and increasing life expectancy, pension enrollment remains low, affecting the long-term financial stability and well-being of populations. To address this issue, this study was conducted to explore the potential of predictive modeling techniques in improving pension participation. The study utilized three tree-based machine learning algorithms and a logistic regression classifier to analyze data from a nationally representative 2019 Kenya FinAccess Household Survey. The results indicated that ensemble tree-based models, particularly the random forest model, were the most effective in predicting pension enrollment. The study identified the key factors that influenced enrollment, such as National Health Insurance Fund (NHIF) usage, monthly income, and bank usage. The findings suggest that collaboration among the NHIF, banks, and pension providers is necessary to increase pension uptake, along with increased financial education for citizens. The study provides valuable insight for promoting and optimizing pension participation.

Predicting Maternal Outcomes Using Tree-based Methods in Machine Learning

“…In Figure 5, we provide a comprehensive model performance evaluation, enabling practical risk assessment and healthcare decision-making for expectant mothers through the Receiver Operating Characteristic (ROC) curve . [25] and Brrera Gerro et al [26].…”

“…Acknowledging poor performance using a single decision classifier [3] - [5], multiple tree-based methods enhance predictive accuracy, mitigate overfitting, and bolster model robustness. Kemboi Yego et al [6] recognize these methods' value in understanding the behavior of each input variable. This work aims to provide clear guidelines for clinicians to forecast maternal outcomes, accommodating diverse data types, capturing linear and non-linear influences, emphasizing key factors affecting maternal well-being, and effectively managing missing values and categorical features.…”