{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T11:28:32Z","timestamp":1784546912012,"version":"3.55.0"},"reference-count":57,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72004173"],"award-info":[{"award-number":["72004173"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2021IVB030"],"award-info":[{"award-number":["2021IVB030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Fundamental Research Funds for the Central Universities of China","award":["72004173"],"award-info":[{"award-number":["72004173"]}]},{"name":"the Fundamental Research Funds for the Central Universities of China","award":["2021IVB030"],"award-info":[{"award-number":["2021IVB030"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>With the development of quantitative finance, machine learning methods used in the financial fields have been given significant attention among researchers, investors, and traders. However, in the field of stock index spot\u2013futures arbitrage, relevant work is still rare. Furthermore, existing work is mostly retrospective, rather than anticipatory of arbitrage opportunities. To close the gap, this study uses machine learning approaches based on historical high-frequency data to forecast spot\u2013futures arbitrage opportunities for the China Security Index (CSI) 300. Firstly, the possibility of spot\u2013futures arbitrage opportunities is identified through econometric models. Then, Exchange-Traded-Fund (ETF)-based portfolios are built to fit the movements of CSI 300 with the least tracking errors. A strategy consisting of non-arbitrage intervals and unwinding timing indicators is derived and proven profitable in a back-test. In forecasting, four machine learning methods are adopted to predict the indicator we acquired, namely Least Absolute Shrinkage and Selection Operator (LASSO), Extreme Gradient Boosting (XGBoost), Back Propagation Neural Network (BPNN), and Long Short-Term Memory neural network (LSTM). The performance of each algorithm is compared from two perspectives. One is an error perspective based on the Root-Mean-Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and goodness of fit (R2). Another is a return perspective based on the trade yield and the number of arbitrage opportunities captured. Finally, a performance heterogeneity analysis is conducted based on the separation of bull and bear markets. The results show that LSTM outperforms all other algorithms over the entire time period, with an RMSE of 0.00813, MAPE of 0.70 percent, R2 of 92.09 percent, and an arbitrage return of 58.18 percent. Meanwhile, in certain market conditions, namely both the bull market and bear market separately with a shorter period, LASSO can outperform.<\/jats:p>","DOI":"10.3390\/e24101462","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T20:55:11Z","timestamp":1665694511000},"page":"1462","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Stock Index Spot\u2013Futures Arbitrage Prediction Using Machine Learning Models"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2864-8928","authenticated-orcid":false,"given":"Yankai","family":"Sheng","sequence":"first","affiliation":[{"name":"School of Economics, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Economics, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1111\/j.1540-6261.1983.tb02496.x","article-title":"Taxes and the Pricing of Stock Index Futures","volume":"38","author":"Cornell","year":"1983","journal-title":"J. Financ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1002\/fut.3990110304","article-title":"The intraday ex post and ex ante profitability of index arbitrage","volume":"11","author":"Klemkosky","year":"1991","journal-title":"J. Futures Mark."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1016\/j.jbankfin.2004.05.001","article-title":"Price discovery and volatility spillovers in index futures markets: Some evidence from Mexico","volume":"28","author":"Zhong","year":"2004","journal-title":"J. Bank Financ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1111\/j.1468-036X.2011.00638.x","article-title":"Direct and Indirect Effects of Index ETFs on Spot-Futures Pricing and Liquidity: Evidence from the CAC 40 Index","volume":"20","author":"Deville","year":"2014","journal-title":"Eur. Financ. Manag."},{"key":"ref_5","first-page":"154","article-title":"How Do Restrictive Trading Regulations Affect the Relationship between Stock Index Futures and the Spot Market?","volume":"2","author":"Xu","year":"2019","journal-title":"J. Financ. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TEVC.2008.928176","article-title":"Evolving Least Squares Support Vector Machines for Stock Market Trend Mining","volume":"13","author":"Yu","year":"2009","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, C.K., and Kim, D. (2020). Monitoring Volatility Change for Time Series Based on Support Vector Regression. Entropy, 22.","DOI":"10.3390\/e22111312"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shi, Y., Zheng, Y., Guo, K., Jin, Z., and Huang, Z. (2020). The Evolution Characteristics of Systemic Risk in China\u2019s Stock Market Based on a Dynamic Complex Network. Entropy, 22.","DOI":"10.3390\/e22060614"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.ejor.2017.11.054","article-title":"Deep learning with long short-term memory networks for financial market predictions","volume":"270","author":"Fischer","year":"2018","journal-title":"Eur. J. Oper. Res."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"B\u00f6rjesson, L., and Singull, M. (2020). Forecasting Financial Time Series through Causal and Dilated Convolutional Neural Networks. Entropy, 22.","DOI":"10.3390\/e22101094"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, X., Su, J., Tang, B., and Wu, S. (2020). A Labeling Method for Financial Time Series Prediction Based on Trends. Entropy, 22.","DOI":"10.3390\/e22101162"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"159519","DOI":"10.1109\/ACCESS.2019.2950858","article-title":"PRAM: A Novel Approach for Predicting Riskless State of Commodity Future Arbitrages with Machine Learning Techniques","volume":"7","author":"He","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"113799","DOI":"10.1016\/j.eswa.2020.113799","article-title":"Option pricing using Machine Learning","volume":"163","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1007\/s10489-020-01839-5","article-title":"A multi-layer and multi-ensemble stock trader using deep learning and deep reinforcement learning","volume":"51","author":"Carta","year":"2021","journal-title":"Appl. Intell"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1111\/j.1540-6261.1987.tb04368.x","article-title":"The Temporal Price Relationship between S&P 500 Futures and the S&P 500 Index","volume":"42","author":"Kawaller","year":"1987","journal-title":"J. Financ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1093\/rfs\/5.1.123","article-title":"A Further Analysis of the Lead\u2013Lag Relationship Between the Cash Market and Stock Index Futures Market","volume":"5","author":"Chan","year":"1992","journal-title":"Rev. Financ. Stud."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1002\/fut.3990150405","article-title":"Return and volatility dynamics in the FT-SE 100 stock index and stock index futures markets","volume":"15","author":"Abhyankar","year":"1995","journal-title":"J. Futures Mark."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1002\/(SICI)1096-9934(199909)19:6<619::AID-FUT1>3.0.CO;2-M","article-title":"Price discovery in the German equity index derivatives markets","volume":"19","author":"Booth","year":"1999","journal-title":"J. Futures Mark."},{"key":"ref_19","first-page":"97","article-title":"Research on the price discovery function of stock index futures under different trends","volume":"9","author":"Zhang","year":"2013","journal-title":"Economist"},{"key":"ref_20","first-page":"144","article-title":"A Study of Price Discovery of HS300 Index Futures in China","volume":"28","author":"Huang","year":"2019","journal-title":"Oper. Res. Manag. Sci."},{"key":"ref_21","first-page":"16","article-title":"The design of index funds and alternative methods of replication","volume":"82","author":"Andrews","year":"1986","journal-title":"Invest. Anal."},{"key":"ref_22","first-page":"871","article-title":"Index Funds\u2014Construction and Performance Measurement","volume":"40","author":"Meade","year":"1989","journal-title":"J. Oper. Res. Soc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"50","DOI":"10.3905\/jpm.2005.470578","article-title":"Indexing and statistical arbitrage: Tracking error or cointegration","volume":"31","author":"Carol","year":"2005","journal-title":"J. Portf. Manag."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"33","DOI":"10.3905\/jpm.2002.319830","article-title":"Optimal Benchmark Tracking with Small Portfolios","volume":"28","author":"Jansen","year":"2002","journal-title":"J. Portf. Manag."},{"key":"ref_25","first-page":"908","article-title":"Stock index futures arbitrage based on the ETF portfolio","volume":"42","author":"Zhang","year":"2012","journal-title":"J. Univ. Sci. Technol. China"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1002\/fut.3990030103","article-title":"The relationship between spot and futures prices in stock index futures markets: Some preliminary evidence","volume":"3","author":"Modest","year":"1983","journal-title":"J. Futures Mark."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"287","DOI":"10.2307\/2331208","article-title":"General Equilibrium Stock Index Futures Prices: Theory and Empirical Evidence","volume":"26","author":"Hemler","year":"1991","journal-title":"J. Financ. Quant. Anal."},{"key":"ref_28","first-page":"60","article-title":"Research on current arbitrage of CSI 300 stock index futures","volume":"S1","author":"Li","year":"2014","journal-title":"Res. Financ. Econ. Issues"},{"key":"ref_29","first-page":"125","article-title":"Empirical research of pricing model and arbitrage on Hushen 300 stock index futures","volume":"32","author":"Liu","year":"2018","journal-title":"Commun. Appl. Math. Comput."},{"key":"ref_30","first-page":"134","article-title":"Three Major Stock Index Futures\u2019 Price Law Seen from the Perspective of Spot-futures Arbitrage","volume":"36","author":"Xie","year":"2020","journal-title":"Stat. Decis."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1002\/fut.20145","article-title":"Price relations among hog, corn, and soybean meal futures","volume":"25","author":"Liu","year":"2005","journal-title":"J. Futures Mark."},{"key":"ref_32","first-page":"54","article-title":"A Research on Forecasting of Shanghai Zinc Futures Price Based on Artificial Neural Network","volume":"38","author":"Lin","year":"2017","journal-title":"Theory Pract. Financ. Econ."},{"key":"ref_33","first-page":"297","article-title":"Research on the Application of Machine Learning in Stock Index Futures Forecast\u2014Comparison and analysis based on BP neural network, SVM and XGBoost","volume":"48","author":"Huang","year":"2018","journal-title":"Math. Pract. Theory"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Sepp","year":"1997","journal-title":"Neural Comput."},{"key":"ref_35","first-page":"125","article-title":"An arbitrage strategy model for ferrous metal futures based on LSTM neural network","volume":"48","author":"Long","year":"2018","journal-title":"J. Univ. Sci. Technol. China"},{"key":"ref_36","first-page":"84","article-title":"Intertemporal Arbitrage of Commodity Futures based on Spread Forecast","volume":"7","author":"Zhou","year":"2019","journal-title":"Financ. Theory Pract."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.physa.2016.02.052","article-title":"Has microblogging changed stock market behavior? Evidence from China","volume":"452","author":"Jin","year":"2016","journal-title":"Physica A"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.eneco.2018.11.015","article-title":"Do high-frequency stock market data help forecast crude oil prices? Evidence from the MIDAS models","volume":"78","author":"Zhang","year":"2019","journal-title":"Energy Econ."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/0165-1889(88)90041-3","article-title":"Statistical analysis of cointegration vectors","volume":"12","author":"Johansen","year":"1988","journal-title":"J. Econ. Dyn. Control"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"424","DOI":"10.2307\/1912791","article-title":"Investigating Causal Relations by Econometric Models and Cross-spectral Methods","volume":"37","author":"Granger","year":"1969","journal-title":"Econometrica"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jfineco.2011.12.010","article-title":"Econometric measures of connectedness and systemic risk in the finance and insurance sectors","volume":"104","author":"Billio","year":"2012","journal-title":"J. Financ. Econ."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"101532","DOI":"10.1016\/j.intfin.2022.101532","article-title":"Does implied volatility (or fear index) affect Islamic stock returns and conventional stock returns differently? Wavelet-based granger-causality, asymmetric quantile regression and NARDL approaches","volume":"77","author":"Karim","year":"2022","journal-title":"J. Int. Financ. Mark. Inst. Money"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"33","DOI":"10.2307\/1913643","article-title":"Regression Quantiles","volume":"46","author":"Koenker","year":"1978","journal-title":"Econometrica"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1080\/14697680903124632","article-title":"Statistical arbitrage in the US equities market","volume":"10","author":"Avellaneda","year":"2010","journal-title":"Quant. Financ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2471","DOI":"10.1111\/jofi.12727","article-title":"Do ETFs Increase Volatility?","volume":"73","author":"Franzoni","year":"2018","journal-title":"J. Financ."},{"key":"ref_46","unstructured":"Cao, G. (2009). Selectivity of Stock Index Futures Arbitrage Strategies of Chinese Institutional Investors. [Master\u2019s Thesis, Fudan University]."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1111\/j.1467-9868.2011.00771.x","article-title":"Regression shrinkage and selection via the lasso: A retrospective","volume":"73","author":"Tibshirani","year":"2011","journal-title":"J. R. Stat. Soc. Ser. B-Stat. Methodol."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.elerap.2018.08.002","article-title":"Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning","volume":"31","author":"Ma","year":"2018","journal-title":"Electron. Commer. Res. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"105405","DOI":"10.1016\/j.aap.2019.105405","article-title":"Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis","volume":"136","author":"Parsa","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/j.renene.2016.03.103","article-title":"Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method","volume":"94","author":"Wang","year":"2016","journal-title":"Renew. Energy"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"113260","DOI":"10.1016\/j.cam.2020.113260","article-title":"Application of innovative risk early warning mode under big data technology in Internet credit financial risk assessment","volume":"386","author":"Du","year":"2021","journal-title":"J. Comput. Appl. Math."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.trc.2015.03.014","article-title":"Long short-term memory neural network for traffic speed prediction using remote microwave sensor data","volume":"54","author":"Ma","year":"2015","journal-title":"Transp. Res. Pt. C-Emerg. Technol."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"3639","DOI":"10.1109\/TGRS.2016.2636241","article-title":"Deep Recurrent Neural Networks for Hyperspectral Image Classification","volume":"55","author":"Mou","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1111\/1475-679X.12292","article-title":"Detecting Accounting Fraud in Publicly Traded U.S. Firms Using a Machine Learning Approach","volume":"58","author":"Bao","year":"2020","journal-title":"J. Account. Res."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1186\/s40854-021-00243-3","article-title":"An efficient stock market prediction model using hybrid feature reduction method based on variational autoencoders and recursive feature elimination","volume":"7","author":"Gunduz","year":"2021","journal-title":"Financ. Innov."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"117600","DOI":"10.1016\/j.eswa.2022.117600","article-title":"Prediction of SSE Shanghai Enterprises index based on bidirectional LSTM model of air pollutants","volume":"204","author":"Liu","year":"2022","journal-title":"Expert Syst. Appl."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/10\/1462\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:53:31Z","timestamp":1760144011000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/10\/1462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,13]]},"references-count":57,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["e24101462"],"URL":"https:\/\/doi.org\/10.3390\/e24101462","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,13]]}}}