Indonesian Stock Market Research Reveals Effective Portfolio Optimization Using Ridge Regression

Strategic Insights -

Researchers from Universitas Padjadjaran, Indonesia, have explored the potential of Ridge Regression in stock return prediction and portfolio optimization for the Indonesian banking sector. The study aims to build an integrated pipeline for portfolio prediction and optimization using Ridge Regression on Indonesian banking stocks. The research used daily closing price data of five major banking stocks for the period 2015-2025, with technical indicators of moving average and rolling standard deviation as input features. The results show that the Ridge Regression model exhibits excellent predictive performance, with an average R² of 0.9986, MAE of 0.000466, and RMSE of 0.000720.

Key Takeaways:

  • The Indonesian stock market in the banking sector is a popular investment instrument with high return potential but faces market volatility and global economic uncertainty.
  • Traditional asset allocation strategies have limitations in dynamic market conditions, while machine learning approaches, such as Ridge Regression, can provide a more effective solution.
  • The application of Ridge Regression in stock return prediction and portfolio optimization has not been widely explored in the Indonesian market.
  • The study uses daily closing price data of five major banking stocks (BBRI, BBCA, BMRI, BBNI, and BBTN) for the period 2015-2025 as input features.
  • The Ridge Regression model is trained using TimeSeriesSplit cross-validation to predict daily returns, then the prediction results are integrated into the Mean-Variance optimization framework to maximize the Sharpe ratio.
  • The Ridge Regression model shows excellent predictive performance, with an average R² of 0.9986, MAE of 0.000466, and RMSE of 0.000720.
  • The Ridge-based portfolio strategy achieves identical performance to the historical optimal strategy, with an annualized return of 10.64% and a Sharpe ratio of 0.4705.
  • The research also demonstrates a practical implementation of the Ridge-based portfolio strategy with IDR 100 million funds, showing feasible execution with less than 1% deviation from the optimal weights.

Statistics:

  • The study uses daily closing price data of five major banking stocks (BBRI, BBCA, BMRI, BBNI, and BBTN) for the period 2015-2025.
  • The Ridge Regression model exhibits an average R² of 0.9986, MAE of 0.000466, and RMSE of 0.000720.
  • The Ridge-based portfolio strategy achieves an annualized return of 10.64% and a Sharpe ratio of 0.4705.
  • The Sharpe ratio of the Ridge-based portfolio strategy is significantly higher than the equal-weight strategy (0.2562).
  • The practical implementation of the Ridge-based portfolio strategy with IDR 100 million funds shows feasible execution with less than 1% deviation from the optimal weights.

Sources:

  • Indonesian Banking Stock Portfolio Optimization Based on Ridge Regression Prediction. International Journal of Business, Economics, and Social Development, 2025,6(2):330-337.
  • DOI: 10.46336/ijbesd.v6i2.1064
  • Universitas Padjadjaran
  • Sumedang, Indonesia
  • Research Collaboration Community (RCC)
  • International Journal of Business, Economics, and Social Development