OPTIMASI PORTOFOLIO DENGAN MODIFIED RISK MEASURE MEMPERTIMBANGKAN BATASAN KARDINALITAS DAN BOBOT SAHAM
Abstract
Abstract
Modified risk measure model is a portfolio optimization model using return scenario based on the forecasting error. This model is a basic model that has not taken the real investment conditions made by investors, such as cardinality and threshold constraints. Therefore, it is necessary to develop a modified risk measure model to be more representative to investment situation and compare the performance between the basic model and the proposed model in optimization. Portfolio optimization will be applied to LQ45 stock list from April-November 2019. Optimization begins by forming 100 scenarios based on error prediction results for each stock with Moving Average methods. Portfolios will be formed at several levels of risk (15%, 20%, 25%, and 30%) to see the impact of limitations on risk and model performance based on the expected return. Optimization using new model tends to reduce the model's performance, but this model reflects the real situation faced by investors.
Keywords : modified risk measure model, cardinality, threshold constraint
Model modified risk measure merupakan salah satu model optimasi portofolio menggunakan skenario return berdasarkan error hasil prediksi. Sayangnya, model ini merupakan model yang belum mempertimbangkan keadaan investasi nyata yang dilakukan oleh investor, seperti batasan kardinalitas, dan batasan bobot saham. Oleh karena itu, perlu dilakukan pengembangan model modified risk measure agar lebih representatif terhadap keadaan investasi dan membandingkan performa antara model dasar dengan model usulan. Optimasi portofolio diterapkan pada saham yang termasuk dalam daftar LQ45 Bursa Efek Indonesia Februari 2019 untuk periode bulan April-November 2019. Optimasi diawali dengan membentuk 100 skenario berdasarkan error hasil prediksi return untuk masing-masing saham. Optimasi dilakukan menggunakan CPLEX Optimizer untuk penyelesaian model linear. Portofolio akan dibentuk pada beberapa tingkatan risiko, yaitu 15%, 20%, 25% dan 30% untuk melihat dampak adanya batasan tambahan terhadap risiko optimasi menggunakan model modified risk measure. Hasilnya adalah optimasi model dengan batasan tambahan cenderung menurunkan performa model, tetapi di sisi lain, portofolio menjadi lebih efisien dan representatif terhadap keadaan investasi.
Kata Kunci : model modified risk measure, kardinalitas, batas bobot saham
Keywords
Full Text:
PDFReferences
Amar, S., Nur A.M., Muhammad K.H., dan Andi S. 2019. Portfolio Selection Using Error Empirical Pattern and Modified Risk Measure. Gadjah Mada University. Int. Conf. of Science and Techology Conference.
Corazza, M., Giovanni F., & Riccardo G. 2012. Portofolio Selection with an Alternative Measure of Risk : Computational Perfomance of Particle Swarm Optimization and Genetic Algorithm. Mathematical and Statistical Methods for Actuarial Sciences and Finances, Springers, Italia.
Guastaroba, G., Mansini, R., & Speranze, M.G. 2009. On the Effectiveness of Scenario Generation Techniques in Single-Period Portfolio Optimization. European Journal of Operational Research, 192, pp. 500-511.
Mansini, R., Ogryczak, W., and Speranza, M.G. 2015. Linear and Mixed Integer Programming for Portfolio Optimization, Springer, Switzerland.
Mendoca, G.H.M., Fernando G.D.C., Rodrigo T.N.C., & Flavio V.C. 2020. Multi Attribute Decision Making Applied to Financial Portofolio Optimization Problem. Journal of Expert System with Application no 158.
Razak, N.B.A., Kamil, K.H., & Elias, S.M. 2014. Linear Versus Quadratic Portfolio Optimization Model with Transaction Cost. International Conference on Mathematical Sciences, vol. 3, pp.533-540.
Setiawan, E.P. & Rosadi, D. 2019. Model Pengoptimuman Portofolio Mean-Variance dan Perkembangan Praktisnya. Jurnal Optimasi Sistem Industri, 18(1), pp. 25-36.
Siew, L.W., Jaaman, S.H., and Hoe, L.W. 2019. Mathematical Modelling of Risk in Portfolio Optimization with Mean-Gini Approach, Journal of Physics: Conference Series, 1212, 012031.
Soleimani, H., Hamid Reza G., Moh. Hossein S. 2009. Markowitz-Based Portofolio Selecrion with Minimum Transaction Lots, Cardinality Constraints, and Regarding Sector Capitalization using Genetic Algorithm. Journal of Expert System with Applications, vol. 36, pp 5058-5063.
Thim, C.K., Y. V. Choong, E. Seah & S. H. Han. 2011. Optimizing Prediction and Construction using Artificial Intelligence. Int. J. Adv. Comput. Technology, vol. 3, no. 3, pp. 168–175.
Refbacks
- There are currently no refbacks.