Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Robo-Advisor Algorithm with Intelligent View Model

지능형 전망모형을 결합한 로보어드바이저 알고리즘

  • 김선웅 (국민대학교 비즈니스IT전문대학원)
  • Received : 2019.04.29
  • Accepted : 2019.05.28
  • Published : 2019.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

최근 은행과 증권회사를 중심으로 다양한 로보어드바이저 금융상품들이 출시되고 있다. 로보어드바이저는 사람 대신 컴퓨터가 포트폴리오 자산배분에 대한 투자 결정을 실행하기 때문에 다양한 자산배분 알고리즘이 활용되고 있다. 본 연구에서는 대표적 로보어드바이저 알고리즘인 블랙리터만모형의 강점을 살리면서 객관적 투자자 전망을 도출할 수 있는 지능형 전망모형을 제안하고 이를 내재균형수익률과 결합하여 최종 포트폴리오를 도출하는 로보어드바이저 자산배분 알고리즘을 새로이 제안하며, 실제 주가자료를 이용한 실증분석 결과를 통해 전문가의 주관적 전망을 대신할 수 있는 지능형 전망모형의 실무적 적용 가능성을 보여주고자 한다. 그동안 주가 예측에서 우수한 성과를 보여주었던 기계학습 방법 중 SVM 모형을 이용하여 각 자산별 기대수익률에 대한 예측과 예측 확률을 도출하고 이를 각각 기대수익률에 대한 투자자 전망과 전망에 대한 신뢰도 수준의 입력변수로 활용하는 지능형 전망모형을 제안하였다. 시장포트폴리오로부터 도출된 내재균형수익률과 지능형 전망모형의 기대수익률, 확률을 결합하여 최종적인 블랙리터만모형의 최적포트폴리오를 도출하였다. 주가자료는 2008년부터 2018년까지의 132개월 동안의 8개의 KOSPI 200 섹터지수 월별 자료를 분석하였다. 블랙리터만모형으로 도출된 최적포트폴리오의 결과가 기존의 평균분산모형이나 리스크패리티모형 등과 비교하여 우수한 성과를 보여주었다. 구체적으로 2008년부터 2015년까지의 In-Sample 자료에서 최적화된 블랙리터만모형을 2016년부터 2018년까지의 Out-Of-Sample 기간에 적용한 실증분석 결과에서 다른 알고리즘보다 수익과 위험 모두에서 좋은 성과를 기록하였다. 총수익률은 6.4%로 최고 수준이며, 위험지표인 MDD는 20.8%로 최저수준을 기록하였다. 수익과 위험을 동시에 고려하여 투자 성과를 측정하는 샤프비율 역시 0.17로 가장 좋은 결과를 보여주었다. 증권계의 애널리스트 전문가들이 발표하는 투자자 전망자료의 신뢰성이 낮은 상태에서, 본 연구에서 제안된 지능형 전망모형은 현재 빠른 속도로 확장되고 있는 로보어드바이저 관련 금융상품을 개발하고 운용하는 실무적 관점에서 본 연구는 의의가 있다고 판단된다.

Keywords

JJSHBB_2019_v25n2_39_f0001.png 이미지

Robo-Advisor System

JJSHBB_2019_v25n2_39_f0002.png 이미지

Implied Equilibrium Return vs Average Return

JJSHBB_2019_v25n2_39_f0003.png 이미지

Portfolio Weights Comparison(2016)

JJSHBB_2019_v25n2_39_f0004.png 이미지

Equity Curves on MVO and BLO

Statistics on Sector Index Returns

JJSHBB_2019_v25n2_39_t0001.png 이미지

Portfolio Weights on Robo-Advisor Algorithms(%)

JJSHBB_2019_v25n2_39_t0002.png 이미지

Performance Report on Robo-Advisor Algorithms(2016~2018)

JJSHBB_2019_v25n2_39_t0003.png 이미지

References

  1. Beketov, M., K. Lehmann and M. Wittke, "Robo Advisors: quantitative methods inside the robot", Journal of Asset Management, Vol.19 (2018), 363-370. https://doi.org/10.1057/s41260-018-0092-9
  2. Best, M. and R. Grauer, "On the sensitivity of mean-variance-efficient portfolios to changes in asset means- Some analytical and computational results", The Review of Financial Studies, Vol.4(1991), 315-342. https://doi.org/10.1093/rfs/4.2.315
  3. Black, F. and R. Litterman, "Asset allocation: Combing investor views with market equilibrium", Journal of Fixed Income, Vol.1 (1991), 7-18. https://doi.org/10.3905/jfi.1991.408013
  4. Duqi, A., L. Franci and G. Torluccio, "The Black-Litterman model: The definition of views based on volatility forecasts", Applied Financial Economics, Vol.24(2014), 1285-1296. https://doi.org/10.1080/09603107.2014.925056
  5. He, P., A. Grant and J. Fabre, "Economic value of analyst recommendations in Australia: An application of the Black-Litterman asset allocation model", Accounting and Finance, Vol.53(2013), 441-470. https://doi.org/10.1111/j.1467-629X.2012.00509.x
  6. Idzorek, T., "A step-by-step guide to the Black-Litterman model", Ibbotson Associates, Working Paper, 2005.
  7. Kim, K.-j. and H. Ahn, "Optimization of Support Vector Machines for financial forecasting", Journal of Intelligence and Information Systems, Vol.17(2011), 223-236.
  8. Kim, S.W and H. Ahn, "Development of an intelligent trading system using Support Vector Machines and genetic algorithms", Journal of Intelligence and Information Systems, Vol.16(2010), 71-92.
  9. Kim, S.W. and H.S. Choi, "Estimation of GARCH models and performance analysis of volatility trading system using Support Vector Regression", Journal of Intelligence and Information Systems, Vol.23(2017), 107-122. https://doi.org/10.13088/jiis.2017.23.2.107
  10. Kooli, M. and M. Selam, "Revisiting the Black-Litterman model: The case of hedge funds", Journal of Derivatives & Hedge Funds, Vol.16(2010), 70-81. https://doi.org/10.1057/jdhf.2010.1
  11. Markowitz, H., "Portfolio selection", The Journal of Finance, Vol.7(1952), 77-91. https://doi.org/10.1111/j.1540-6261.1952.tb01525.x
  12. Park, J. J., "The performance comparison between the Black-Litterman mean-variance and Copula-Option-Pooling model", Korean Journal of Financial Studies, Vol.45(2016), 343-378.
  13. Pyo, S. and J. Lee, "Exploiting the low-risk anomaly using machine learning to enhance the Black-Litterman framework: Evidence from South Korea", Pacific-Basin Finance Journal, Vol.51(2018), 1-12. https://doi.org/10.1016/j.pacfin.2018.06.002
  14. Reddy, P., "Black-Litterman portfolios with machine learning derived views", available at www.reaserchgate.net, 2018, 1-28.
  15. Satchell, S. and A. Scowcroft, "A demystification of the Black-Litterman model: Managing quantitative and traditional construction", Journal of Asset Management, Vol.1(2000), 138-150. https://doi.org/10.1057/palgrave.jam.2240011
  16. Song, J., Y. Lee and G. Park, "Sector investment strategy with the Black-Litterman model", Korean Management Science Review, Vol.29 (2012), 57-71. https://doi.org/10.7737/KMSR.2012.29.1.057
  17. Walters, J., "The Black-Litterman model in detail", Jay Walters, CFA, 2014.

Cited by

  1. XGBoost를 활용한 리스크패리티 자산배분 모형에 관한 연구 vol.26, pp.1, 2020, https://doi.org/10.13088/jiis.2020.26.1.135