Sector-Adjusted R-vine Copula (RVMS) Extension of CAPM for Portfolio Risk Optimization

Wa Ode Intan Fully Nadya (School of Data Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia)
Retno Budiarti (School of Data Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia)
I Gusti Putu Purnaba (School of Data Science, Mathematics, and Informatics, IPB University, Bogor, Indonesia)

Zero : Jurnal Sains, Matematika, dan Terapan
Vol 10, No 2 (2026): Zero: Jurnal Sains Matematika dan Terapan

This study evaluated the R-vine Market Sector (RVMS) model, a sector-adjusted extension of the Capital Asset Pricing Model (CAPM), for portfolio risk optimization in the Indonesian stock market using 978 daily observations from 2021 to 2025. Returns were modeled using ARMA–GARCH and R-vine copulas, and portfolios were optimized under a minimum tail-risk criterion with rolling-window backtesting. The results indicated asymmetric and tail dependence, with sectoral effects contributing substantially to portfolio risk. RVMS reduced expected tail losses by approximately 12–16% relative to CAPM at standard confidence levels, although both models showed limited performance under extreme tail conditions. Economically, RVMS provided modest improvements in risk-adjusted performance and lower drawdowns, despite higher turnover. Overall, incorporating sectoral dependence improved portfolio risk modeling, although the benefits remained moderate and context-dependent.