Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of KOSPI200 Index option volatility using Artificial Intelligence

이기종 머신러닝기법을 활용한 KOSPI200 옵션변동성 예측

  • Shin, Sohee (Department of Applied Artificial Intelligence, Sungkyunkwan University) ;
  • Oh, Hayoung (College of Computing and Informatics, Sungkyunkwan University) ;
  • Kim, Jang Hyun (College of Interaction Science, Sungkyunkwan University)
  • Received : 2022.06.13
  • Accepted : 2022.09.20
  • Published : 2022.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Volatility is one of the variables that the Black-Scholes model requires for option pricing. It is an unknown variable at the present time, however, since the option price can be observed in the market, implied volatility can be derived from the price of an option at any given point in time and can represent the market's expectation of future volatility. Although volatility in the Black-Scholes model is constant, when calculating implied volatility, it is common to observe a volatility smile which shows that the implied volatility is different depending on the strike prices. We implement supervised learning to target implied volatility by adding V-KOSPI to ease volatility smile. We examine the estimation performance of KOSPI200 index options' implied volatility using various Machine Learning algorithms such as Linear Regression, Tree, Support Vector Machine, KNN and Deep Neural Network. The training accuracy was the highest(99.9%) in Decision Tree model and test accuracy was the highest(96.9%) in Random Forest model.

블랙숄즈모형에서 옵션가격을 결정하는 변수 중 기초자산의 변동성은 현재 시점에서는 알 수 없고, 미래시점에 실현된 변동성을 사후에야 알 수 있다. 하지만 옵션이 거래되는 시장에서 관찰되는 가격이 있기 때문에 가격에 내재된 변동성을 역으로 산출한 내재변동성은 현재 시점에 구할 수 있다. 내재변동성을 구하기 위해서는 옵션가격과, 블랙숄즈 모형의 변동성을 제외한 옵션가격결정변수인 기초자산가격, 무위험이자율, 배당률, 행사가격, 잔존기간이 필요하다. 블랙숄즈모형의 변동성은 고정된 상수이나, 내재변동성 산출시 행사가격에 따라 변동성이 다르게 산출되는 변동성스마일현상을 보이기도 한다. 따라서 내재변동성 산출시 옵션 단일 종목이 아닌 시장전반의 변동성을 감안하는 것이 필요하다고 판단하여 본 연구에서는 V-KOSPI지수도 설명변수로 추가하였다. 머신러닝기법 중 지도학습방법을 사용하였으며, Linear Regression 계열, Tree 계열, SVR과 KNN 알고리즘 및 딥뉴럴네트워크로 학습 및 예측하였다. Training성능은 Decision Tree모형이 99.9%로 가장 높았고 Test성능은 Random Forest 알고리즘이 96.9%로 가장 높았다.

Keywords

Acknowledgement

We would like to express my gratitude to Young Sam Yoo at Korea Exchange for giving the idea of this research and this work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. NRF-2022R1F1A1074696 ).

References

  1. J. Choi and J. T. Lee, "An estimation of implied volatility for KOSPI200 option," Journal of the Korean Data and Information Science Society, vol. 25, no. 3, pp. 513-522, May 2014. https://doi.org/10.7465/JKDI.2014.25.3.513
  2. H. Park, N. Kim, and J. Lee, "Parametric models and non-parametric machine learning models for predicting option prices: Empirical comparison study over KOSPI200 Index Options," Expert Systems with Applications, vol. 41, no. 11, pp. 5227-5237, Sep. 2014. https://doi.org/10.1016/j.eswa.2014.01.032
  3. S. Lee and K. Park, "The Correlation between KOSPI200 Futures' Price Disparity Ratio and Implied Volatility of KOSPI200 Options," Financial Planning Review, vol. 9, no. 2, pp. 61-86, May 2016.
  4. S. W. Park and D. Pak, "Forecasting KOSPI200 Volatility using Option Demand Index," Review of Financial Information Studies, vol. 8, no. 1, pp. 1-22, Feb. 2019. https://doi.org/10.35214/RFIS.8.1.201902.001
  5. D. Jung and J. Park, "A Comparative Test for the Information Contents between Futures Market and Option Market : Using VPIN," Journal of Industrial Economics and Business, vol. 32, no. 2, pp. 877-894, Apr. 2019. https://doi.org/10.22558/jieb.2019.04.32.2.877
  6. Y. S. Choi and H. J. Lee, "Forecasting KOSPI200 Volatility by Volatility Measurements," Communications for Statistical Applications and Methods, vol. 17, no. 2, pp. 293-308, Mar. 2010. https://doi.org/10.5351/CKSS.2010.17.2.293
  7. M. S. Kim and Y. Lei, "The Comparative Study of Volatility Smile by Using SSE 50ETF Index Option and KOSPI200 Index Option," Journal of Industrial Economics and Business, vol. 33, no. 2, pp. 319-333, Apr. 2020. https://doi.org/10.22558/jieb.2020.4.33.2.319
  8. K. H. Ko, "Neural Network Approach to Understanding KOSPI200 Option Implied Volatility Movement," M. S. thesis, KAIST, 2020.
  9. S. H. Jeon, "A Study on the Effect of the Information from the Implied Volatility Surface of the KOSPI200 Index Options on the Predictability of the Rime Series Model," M. S. thesis, KAIST, 2021.
  10. K. Y. Ohk and S. G. Lee, "Deterministic Model of Volatility Surface in the KOSPI200 Options Market," Journal of the Korean Data Analysis Society, vol. 14, no. 3, pp. 1633-1643, Jun. 2012.
  11. S. S. Kwon and J. H. Lee, "The Function of Intraday Implied Volatility in the KOSPI200 Options," Korean Journal of Financial Studies, vol. 37, no. 5, pp. 913-948, Oct. 2008.
  12. J. W. Lee and T. H. Kwon, "The Information Content and Volatility Transfer Effect of Implied Volatility on KOSPI200 Return," The Korean Journal of Financial Engineering, vol. 5, no. 1, pp. 41-59, Mar. 2006.
  13. J. B. Chay and H. S. Ryu, "Intraday Stock Market Volatility around Expiration Days in Korea," Korean Corporation Management Review, vol. 12, no. 1, pp. 213-224, Jun. 2005.
  14. Y. Cho and D. Kim, "The Market Efficiency of the KOSPI200 Index Options and Mini Options," Journal of Industrial Economics and Business, vol. 34, no. 2, pp. 319-340, Apr. 2021. https://doi.org/10.22558/jieb.2021.4.34.2.319