Determining Individual Risk Profiles for Informed Investment Decisions in the Individual Pension System

Author(s)	Bayraktar, Mehmet Yasar
Country	Turkey
Abstract	This study investigates the determinants of risk profiles among participants in the Turkish Individual Pension System (IPS) using an explainable machine learning approach. A large-scale Kaggle dataset obtained from a major private pension provider was analyzed using demographic, socioeconomic, and financial characteristics. The model achieved an overall accuracy of 87.3%. SHapley Additive exPlanations (SHAP) were employed to interpret the model and quantify the contribution of individual predictors. The results demonstrate that financial capacity and observed account behavior are the dominant determinants of pension risk profiles. Overall, explainable machine learning provides an accurate and transparent framework for pension risk profiling. The findings may support more individualized risk assessment, improved default fund allocation, and more effective participant segmentation, contributing to the long-term sustainability of pension systems in emerging economies.
Keywords	Individual Pension, Financial Security, IPS, Fund Management, Investment, Savings
Field	Computer > Data / Information
Published In	Volume 8, Issue 5, September-October 2026
Published On	2026-09-26
DOI	https://doi.org/10.36948/ijfmr.2026.v08i05.88511

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research