DOI QR코드

DOI QR Code

A Study on Risk Parity Asset Allocation Model with XGBoos

XGBoost를 활용한 리스크패리티 자산배분 모형에 관한 연구

  • 김영훈 (국민대학교 비즈니스IT 전문대학원) ;
  • 최흥식 (국민대학교 비즈니스IT 전문대학원) ;
  • 김선웅 (국민대학교 비즈니스IT 전문대학원)
  • Received : 2020.02.12
  • Accepted : 2020.03.15
  • Published : 2020.03.31

Abstract

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

인공지능을 기반으로 한 다양한 연구들이 현대사회에 많은 변화를 불러일으키고 있다. 금융시장 역시 예외는 아니다. 로보어드바이저 개발이 활발하게 진행되고 있으며 전통적 방식의 단점을 보완하고 사람이 분석하기 어려운 부분을 대체하고 있다. 로보어드바이저는 인공지능 알고리즘으로 자동화된 투자 결정을 내려 다양한 자산배분 모형과 함께 활용되고 있다. 자산배분 모형 중 리스크패리티는 대표적인 위험 기반 자산배분 모형의 하나로 큰 자산을 운용하는 데 있어 안정성을 나타내고 현업에서 역시 널리 쓰이고 있다. 그리고 XGBoost 모형은 병렬화된 트리 부스팅 기법으로 제한된 메모리 환경에서도 수십억 가지의 예제로 확장이 가능할 뿐만 아니라 기존의 부스팅에 비해 학습속도가 매우 빨라 많은 분야에서 널리 활용되고 있다. 이에 본 연구에서 리스크패리티와 XGBoost를 장점을 결합한 모형을 제안하고자 한다. 기존에 널리 사용되는 최적화 자산배분 모형은 과거 데이터를 기반으로 투자 비중을 추정하기 때문에 과거와 실투자 기간 사이의 추정 오차가 발생하게 된다. 최적화 자산배분 모형은 추정 오차로 인해 포트폴리오 성과에서 악영향을 받게 된다. 본 연구는 XGBoost를 통해 실투자 기간의 변동성을 예측하여 최적화 자산배분 모형의 추정 오차를 줄여 모형의 안정성과 포트폴리오 성과를 개선하고자 한다. 본 연구에서 제시한 모형의 실증 검증을 위해 한국 주식시장의 10개 업종 지수 데이터를 활용하여 2003년부터 2019년까지 총 17년간 주가 자료를 활용하였으며 in-sample 1,000개, out-of-sample 20개씩 Moving-window 방식으로 예측 결과값을 누적하여 총 154회의 리밸런싱이 이루어진 백테스팅 결과를 도출하였다. 본 연구에서 제안한 자산배분 모형은 기계학습을 사용하지 않은 기존의 리스크패리티와 비교하였을 때 누적수익률 및 추정 오차에서 모두 개선된 성과를 보여주었다. 총 누적수익률은 45.748%로 리스크패리티 대비 약 5% 높은 결과를 보였고 추정오차 역시 10개 업종 중 9개에서 감소한 결과를 보였다. 실험 결과를 통해 최적화 자산배분 모형의 추정 오차를 감소시킴으로써 포트폴리오 성과를 개선하였다. 포트폴리오의 추정 오차를 줄이기 위해 모수 추정 방법에 관한 다양한 연구 사례들이 존재한다. 본 연구는 추정 오차를 줄이기 위한 새로운 추정방법으로 기계학습을 제시하여 최근 빠른 속도로 발전하는 금융시장에 맞는 진보된 인공지능형 자산배분 모형을 제시한 점에서 의의가 있다.

Keywords

References

  1. Black, F. and R. Litterman, "Asset allocation: Combining investor views with market equilibrium", Journal of Fixed Income, Vol1, No.2 (1991), 7-18. https://doi.org/10.3905/jfi.1991.408013
  2. Brinson, G. P., "Determinants of portfolio performance", Financial Analysts Journal, Vol51, No.1 (1995), 133-138. https://doi.org/10.2469/faj.v51.n1.1869
  3. Chen, T. and C. Guestrin, "XGBoost: A Scalable Tree Boosting System", 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining(2016), 785-794.
  4. Chopra, V. K. and W. T. Ziemba, "The effect of errors in means, variances, and covariances on optimal portfolio choice", Journal of Portfolio Management, Vol.19, No.2(1993), 6-11. https://doi.org/10.3905/jpm.1993.409440
  5. Demiguel, V., L. Garlappi and R. Uppal, "Optimal versus naive diversification: How inefficient is the 1/n portfolio strategy?", Review of Financial Studies, Vol.22, No.5(2009), 1915-1953. https://doi.org/10.1093/rfs/hhm075
  6. Hah, D. W., Y. M., Kim and J. J., Ahn, "A study on KOSPI200 direction forecasting using XGBoost model", Journal of the Korean Data And Information Science Society, Vol.30, No.3(2019), 655-669. https://doi.org/10.7465/jkdi.2019.30.3.655
  7. Kim, S. W., "Robo-Advisor Algorithm with Intelligent View Model", Journal of Intelligence and Information Systems, Vol.25, No.2(2019), 39-55. https://doi.org/10.13088/JIIS.2019.25.2.039
  8. Lee, C. S. and K. B., Lee, "A Sensitivity Analysis of the effects of errors in parameter Estimation on portfolio efficiency", The Korean Journal of Financial Engineering, Vol.1, No.0(2002), 1-13.
  9. Lee, S. H., "Covariance Estimation and the Effect on the Performance of the Optimal Portfolio", Journal of the Korean Operations Research and Management Science Society, Vol.39, No.4(2014), 137-152. https://doi.org/10.7737/JKORMS.2014.39.4.137
  10. Markowitz, H. M., "Portfolio selection", Journal of Finance, Vol.7, No.1(1952), p.77-91. https://doi.org/10.1111/j.1540-6261.1952.tb01525.x
  11. Qian, E, "Risk parity portfolios: Efficient portfolios through true diversification, Panagora Asset Management, September(2005).
  12. Roh, T. H., "Integration Model of Econometric Time Series for Volatility Forecasting", Korean Management Consulting Review, Vol.13, No.1(2013), 313-340.
  13. Ru, J. P. and H. J. Shin, "An Option Hedge Strategy Using Machine Learning and Dynamic Delta Hedging", Journal of The Korea Academia-Industrial cooperation Society, Vol.12, No.2(2011), 712-717. https://doi.org/10.5762/KAIS.2011.12.2.712
  14. Sa, J. H., S. H., Hee and G. Y. Gim, "A study on Utilization of Robo-Advisor in Korea", Proceedings of Fall Conference on Korea Society of IT Sercvices(2016), 234-237.