Claim Missing Document
Check
Articles

Found 22 Documents
Search

ANALISIS KLASIFIKASI KUALITAS HIDUP MANUSIA ANTAR KABUPATEN/KOTA DI INDONESIA MENGGUNAKAN ALGORITMA CATBOOST CLASSIFIER DAN SHAP VALUES Ayu Sofia; Linda Rassiyanti
MATHunesa: Jurnal Ilmiah Matematika Vol. 14 No. 1 (2026)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/mathunesa.v14n1.p430-444

Abstract

Human development must go hand in hand with improving quality of life, as reflected by HDI and its influencing factors. Classifying quality of life based on HDI into developed, developing, and underdeveloped areas offers insights into the human development performance of each district/city in Indonesia. The CatBoost Classifier and SHAP values help build an accurate model while interpreting variable influences. This study analyzes human quality of life classification across districts/cities based on HDI and related factors. The CatBoost model achieved 92.23% accuracy, with the best performance in the developing class, while the underdeveloped class showed low accuracy due to data imbalance. SHAP analysis revealed that average years of schooling, per capita expenditure, and region type were key variables in the developed and developing classes, while island location and sanitation access dominated in the underdeveloped class. These findings highlight the importance of education, economic welfare, and basic infrastructure in shaping quality of life. This research also supports actuarial social risk planning, particularly in designing data- and region-based social security systems.
Actuarial Evaluation of Additional Contributions in Early Retirement Programs Using the Spreading Gains and Losses Method Mahrani, Dwi; Nazima, Miftha Ulya; Sofia, Ayu; Yulita, Tiara
ZERO: Jurnal Sains, Matematika dan Terapan Vol 10, No 1 (2026): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v10i1.28726

Abstract

This study examines the actuarial and funding implications of accelerated retirement in a defined benefit pension scheme by integrating the Projected Unit Credit (PUC) method with the Spreading Gains and Losses approach. While both methods are widely applied in pension valuation, limited empirical evidence evaluates their combined implementation under retirement age acceleration scenarios, particularly in Indonesian public sector schemes. This study addresses that gap using secondary administrative employment data of 87 female civil servants obtained from the Investment and One-Stop Integrated Services Office of Lampung Province (Dinas Penanaman Modal dan Pelayanan Terpadu Satu Pintu Provinsi Lampung), grouped into four entry-age cohorts (22–25 years). The analysis compares normal retirement at age 58 with accelerated retirement at age 50, assuming a 5% annual effective interest rate and 8% biennial salary growth. The results indicate that, at valuation age 45, actuarial liabilities increase by approximately 49.8% under retirement at age 50 relative to age 58. The shorter discounting period and earlier benefit payments outweigh the reduced contribution period, resulting in the emergence of Unfunded Actuarial Liability (UAL). The resulting Past Service Liability (PSL) is amortized over five years, requiring additional contributions ranging from IDR 27.06 million to IDR 82.05 million across entry-age groups. These findings highlight the high sensitivity of pension funding to retirement age assumptions and emphasize the importance of actuarial impact assessments prior to policy implementation. However, the deterministic framework and relatively small sample size limit broader generalization of the results.