Research Article Pengelolaan Portoflio Investasi dengan Penerapan LSTM pada Sektor Strategis Indonesia dengan Evaluasi Sharpe Ratio dan Mean Variance
Kata Kunci:
Portfolio Management Long Short-Term Memory (LSTM) Sharpe Ratio Mean-Variance Optimization Stock PredictionAbstrak
Dalam teori portofolio modern, pemilihandandiversifikasi portofolio dilakukandenganasumsi investor rasional tanpa mempertimbangkan pandangan subjektif terhadap investasi. Perkembangan teknologi machine learning dan kecerdasan buatan memungkinkan analisis kondisi pasar secara lebih adaptif, sehingga mendukung pengambilan keputusan investasi yang selaras dengan preferensi investor. Penelitian ini membahas penerapan metode Long Short-Term Memory (LSTM) untuk menentukan alokasi portofolio saham di Bursa Efek Indonesia (IDX) yang mencakup berbagai sektor, berdasarkan ukuran Sharpe ratio dan mean-variance portofolio. Dua pendekatan LSTM digunakan: LSTM single input yang hanya memanfaatkan data historis harga aset, dan LSTM dengan faktor eksogen yang menggabungkan variabel eksternal sebagai prediktor tambahan. Kinerja keduanya dibandingkan dengan model Autoregressive Integrated Moving Average (ARIMA) sebagai representasi model deret waktu murni. Evaluasi dilakukan menggunakan metrik prediksi dan hasil simulasi portofolio investasi melalui nilai return dan resiko portofolio. Hasil penelitian menunjukkan bahwa, berdasarkan prediksi rasio Sharpe untuk setiap komponen portofolio, LSTM single input memiliki kinerja lebih baik dibandingkan LSTM dengan faktor eksogen maupun model ARIMA. Kedua pendekatan LSTM secara konsisten menunjukkan bahwa pengambilan keputusan investasi yang lebih sering (periode pendek) menghasilkan akumulasi return lebih tinggi dibandingkan strategi jangka panjang. Secara khusus, LSTM single input memberikan performa prediksi yang baik serta pembobotan portofolio optimal untuk investasi bulanan dan jangka pendek.
Kata kunci— LSTM (Long-Short Term Memory), Diversifikasi Portfolio, Faktor Eksogen, ARIMA
Referensi
P. Singh, M. Jha, M. Sharaf, M. A. El-Meligy, and T. R. Gadekallu, “Harnessing a Hybrid CNN-LSTM Model for Portfolio Performance: A Case Study on Stock Selection and Optimization,” IEEE Access, vol. 11, pp. 104000–104015, 2023, doi: 10.1109/ACCESS.2023.3317953.
B. Gülmez, “Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm,” Expert Syst Appl, vol. 227, Oct. 2023, doi: 10.1016/j.eswa.2023.120346.
A. M. Rather, “LSTM-based Deep Learning Model for Stock Prediction and Predictive Optimization Model,” EURO Journal on Decision Processes, vol. 9, Jan. 2021, doi: 10.1016/j.ejdp.2021.100001.
J. Michańków, P. Sakowski, and R. Ślepaczuk, “LSTM in Algorithmic Investment Strategies on BTC and S&P500 Index,” Sensors, vol. 22, no. 3, Feb. 2022, doi: 10.3390/s22030917.
C. H. Wang, Y. Zeng, and J. Yuan, “Two-stage stock portfolio optimization based on AI-powered price prediction and mean-CVaR models,” Expert Syst Appl, vol. 255, Dec. 2024, doi: 10.1016/j.eswa.2024.124555.
Y. Ma, R. Han, and W. Wang, “Portfolio optimization with return prediction using deep learning and machine learning,” Expert Syst Appl, vol. 165, Mar. 2021, doi: 10.1016/j.eswa.2020.113973.
P. Koratamaddi, K. Wadhwani, M. Gupta, and S. G. Sanjeevi, “Market sentiment-aware deep reinforcement learning approach for stock portfolio allocation,” Engineering Science and Technology, an International Journal, vol. 24, no. 4, pp. 848–859, Aug. 2021, doi: 10.1016/j.jestch.2021.01.007.
G. W. Shin and H. M. Gordon, “Toward a portfolio theory of talent development: Insights from financial theory, illustrations from the Asia-Pacific,” World Dev, vol. 184, Dec. 2024, doi: 10.1016/j.worlddev.2024.106755.
H. Alabdulrazzaq, M. N. Alenezi, Y. Rawajfih, B. A. Alghannam, A. A. Al-Hassan, and F. S. Al-Anzi, “On the accuracy of ARIMA based prediction of COVID-19 spread,” Results Phys, vol. 27, Aug. 2021, doi: 10.1016/j.rinp.2021.104509.
A. Swaraj, K. Verma, A. Kaur, G. Singh, A. Kumar, and L. Melo de Sales, “Implementation of stacking based ARIMA model for prediction of Covid-19 cases in India,” J. Biomed Inform, vol. 121, Sep. 2021, doi: 10.1016/j.jbi.2021.103887.
S. Faridi, M. Madanchi Zaj, A. Daneshvar, S. Shahverdiani, and F. Rahnamay Roodposhti, “Portfolio rebalancing based on a combined method of ensemble machine learning and genetic algorithm,” Journal of Financial Reporting and Accounting, vol. 21, no. 1, pp. 105–125, Mar. 2023, doi: 10.1108/JFRA-11-2021-0413.
T. Salsabila, D. Saepudin, and A. A. Rohmawati, “Optimizing LQ45 Stock Portfolio To Maximize Sharpe Ratio Value Using LSTM,” Journal of Computer System and Informatics (JoSYC), vol. 4, no. 2, pp. 339–347, Feb. 2023, doi: 10.47065/josyc.v4i2.3065.
W. Febrianti, K. A. Sidarto, and N. Sumarti, “Solving Constrained Mean-Variance Portfolio Optimization Problems Using Spiral Optimization Algorithm,” International Journal of Financial Studies, vol. 11, no. 1, Mar. 2023, doi: 10.3390/ijfs11010001.
J. Du, “Mean–variance portfolio optimization with deep learning based-forecasts for cointegrated stocks,” Expert Syst Appl, vol. 201, Sep. 2022, doi: 10.1016/j.eswa.2022.117005.
