{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:25:05Z","timestamp":1783009505751,"version":"3.54.5"},"reference-count":53,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T00:00:00Z","timestamp":1550016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JRFM"],"abstract":"<jats:p>Machine learning research has gained momentum\u2014also in finance. Consequently, initial machine-learning-based statistical arbitrage strategies have emerged in the U.S. equities markets in the academic literature, see e.g., Takeuchi and Lee (2013); Moritz and Zimmermann (2014); Krauss et al. (2017). With our paper, we pose the question how such a statistical arbitrage approach would fare in the cryptocurrency space on minute-binned data. Specifically, we train a random forest on lagged returns of 40 cryptocurrency coins, with the objective to predict whether a coin outperforms the cross-sectional median of all 40 coins over the subsequent 120 min. We buy the coins with the top-3 predictions and short-sell the coins with the flop-3 predictions, only to reverse the positions after 120 min. During the out-of-sample period of our backtest, ranging from 18 June 2018 to 17 September 2018, and after more than 100,000 trades, we find statistically and economically significant returns of 7.1 bps per day, after transaction costs of 15 bps per half-turn. While this finding poses a challenge to the semi-strong from of market efficiency, we critically discuss it in light of limits to arbitrage, focusing on total volume constraints of the presented intraday-strategy.<\/jats:p>","DOI":"10.3390\/jrfm12010031","type":"journal-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T03:21:46Z","timestamp":1550114506000},"page":"31","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Statistical Arbitrage in Cryptocurrency Markets"],"prefix":"10.3390","volume":"12","author":[{"given":"Thomas G\u00fcnter","family":"Fischer","sequence":"first","affiliation":[{"name":"Department of Statistics and Econometrics, University of Erlangen-N\u00fcrnberg, 90403 N\u00fcrnberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Krauss","sequence":"additional","affiliation":[{"name":"Department of Statistics and Econometrics, University of Erlangen-N\u00fcrnberg, 90403 N\u00fcrnberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Deinert","sequence":"additional","affiliation":[{"name":"Department of Statistics and Econometrics, University of Erlangen-N\u00fcrnberg, 90403 N\u00fcrnberg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,2,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.econmod.2017.03.019","article-title":"Can volume predict Bitcoin returns and volatility? A quantiles-based approach","volume":"64","author":"Balcilar","year":"2017","journal-title":"Economic Modelling"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.econlet.2018.10.008","article-title":"Asymmetric volatility in cryptocurrencies","volume":"173","author":"Baur","year":"2018","journal-title":"Economics Letters"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.ribaf.2019.01.001","article-title":"Investigating volatility transmission and hedging properties between Bitcoin and Ethereum","volume":"48","author":"Beneki","year":"2019","journal-title":"Research in International Business and Finance"},{"key":"ref_4","first-page":"565","article-title":"A statistically precise and relatively simple method of estimating the bio-assay with quantal response, based on the logistic function","volume":"48","author":"Berkson","year":"1953","journal-title":"Journal of the American Statistical Association"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1080\/1351847X.2014.953698","article-title":"Pairs trading in the UK equity market: Risk and return","volume":"22","author":"Bowen","year":"2016","journal-title":"The European Journal of Finance"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Machine Learning"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"ref_8","unstructured":"coinmarketcap.com (2018, July 27). Overview of available cryptocurrencies. Available online: coinmarketcap.com."},{"key":"ref_9","unstructured":"Colianni, Stuart, Rosales, Stephanie, and Signorotti, Michael (2015). Algorithmic Trading of Cryptocurrency Based on Twitter Sentiment Analysis, Working Paper."},{"key":"ref_10","unstructured":"cryptocompare.com (2018, September 06). Overview of CryptoCompare API. Available online: cryptocompare.com."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.frl.2015.10.008","article-title":"Bitcoin, gold and the dollar\u2014A GARCH volatility analysis","volume":"16","author":"Dyhrberg","year":"2016","journal-title":"Finance Research Letters"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1016\/j.eswa.2005.06.024","article-title":"The use of data mining and neural networks for forecasting stock market returns","volume":"29","author":"Enke","year":"2005","journal-title":"Expert Systems with Applications"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"383","DOI":"10.2307\/2325486","article-title":"Efficient capital markets: A review of theory and empirical work","volume":"25","author":"Fama","year":"1970","journal-title":"The Journal of Finance"},{"key":"ref_14","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":"European Journal of Operational Research"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"150288","DOI":"10.1098\/rsos.150288","article-title":"Social signals and algorithmic trading of Bitcoin","volume":"2","author":"Garcia","year":"2015","journal-title":"Royal Society Open Science"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1093\/rfs\/hhj020","article-title":"Pairs trading: Performance of a relative-value arbitrage rule","volume":"19","author":"Gatev","year":"2006","journal-title":"Review of Financial Studies"},{"key":"ref_17","unstructured":"Gilbert, Clayton J. Hutto Eric (, January June). Vader: A parsimonious rule-based model for sentiment analysis of social media text. Paper presented at Eights International Conference on Weblogs and Social Media, Ann Arbor, MI, USA."},{"key":"ref_18","unstructured":"Gregoriou, Greg N. (2012). Handbook of Short Selling, Academic Press."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s12293-018-0252-y","article-title":"Finding attractive technical patterns in cryptocurrency markets","volume":"10","author":"Ha","year":"2018","journal-title":"Memetic Computing"},{"key":"ref_20","unstructured":"Hastie, Trevor, Tibshirani, Robert, and Friedman, Jerome (2008). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer. [2nd ed.]."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1109\/ICDAR.1995.598994","article-title":"Random decision forests","volume":"vol. 1","author":"Ho","year":"1995","journal-title":"Paper presented at the third International Conference on Document Analysis and Recognition"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1109\/34.709601","article-title":"The random subspace method for constructing decision forests","volume":"20","author":"Ho","year":"1998","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1016\/j.ejor.2008.03.025","article-title":"Pairs selection and outranking: An application to the S&P 100 index","volume":"196","author":"Huck","year":"2009","journal-title":"European Journal of Operational Research"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1016\/j.ejor.2010.06.043","article-title":"Pairs trading and outranking: The multi-step-ahead forecasting case","volume":"207","author":"Huck","year":"2010","journal-title":"European Journal of Operational Research"},{"key":"ref_25","unstructured":"IEEE, and The Open Group (2018, September 06). The open group base specifications. Available online: http:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/basedefs\/V1_chap04.html#tag_04_16."},{"key":"ref_26","unstructured":"Intercontinental Exchange (2018, December 30). Behind the Scenes\u2014An insider\u2019s guide to the NYSE closing auction. Available online: https:\/\/www.nyse.com\/article\/nyse-closing-auction-insiders-guide."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1111\/j.1540-6261.1990.tb05110.x","article-title":"Evidence of predictable behavior of security returns","volume":"45","author":"Jegadeesh","year":"1990","journal-title":"The Journal of Finance"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jiang, Zhengyao, and Liang, Jinjun (arXiv, 2017). Cryptocurrency portfolio management with deep reinforcement learning, arXiv.","DOI":"10.1109\/IntelliSys.2017.8324237"},{"key":"ref_29","unstructured":"Jones, Eric, Oliphant, Travis, and Peterson, Pearu (2018, December 30). SciPy: open source scientific tools for Python. Available online: http:\/\/www.scipy.org\/."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kim, Y. Bin, Kim, Jun G., Kim, Wook, Im, Jae H., Kim, Tae H., Kang, Shin J., and Kim, Chang H. (2016). Predicting fluctuations in cryptocurrency transactions based on user comments and replies. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0161197"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kleinbaum, David G., and Klein, Mitchel (2010). Logistic Regression: A Self-Learning Text, Springer.","DOI":"10.1007\/978-1-4419-1742-3"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.econlet.2018.10.004","article-title":"Return and volatility spillovers among cryptocurrencies","volume":"173","author":"Koutmos","year":"2018","journal-title":"Economics Letters"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1111\/joes.12153","article-title":"Statistical arbitrage pairs trading strategies: Review and outlook","volume":"31","author":"Krauss","year":"2017","journal-title":"Journal of Economic Surveys"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1016\/j.ejor.2016.10.031","article-title":"Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500","volume":"259","author":"Krauss","year":"2017","journal-title":"European Journal of Operational Research"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2307\/2937816","article-title":"Fads, martingales, and market efficiency","volume":"105","author":"Lehmann","year":"1990","journal-title":"The Quarterly Journal of Economics"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/S0169-2070(99)00048-5","article-title":"Forecasting stock indices: A comparison of classification and level estimation models","volume":"16","author":"Leung","year":"2000","journal-title":"International Journal of Forecasting"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1080\/14697688.2016.1231928","article-title":"Model-based pairs trading in the Bitcoin markets","volume":"17","author":"Lintilhac","year":"2017","journal-title":"Quantitative Finance"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1080\/14697688.2016.1184304","article-title":"Intraday pairs trading strategies on high frequency data: The case of oil companies","volume":"17","author":"Liu","year":"2017","journal-title":"Quantitative Finance"},{"key":"ref_39","unstructured":"Madan, Isaac, Saluja, Shaurya, and Zhao, Aojia (2015). Automated Bitcoin Trading via Machine Learning Algorithms, Working Paper."},{"key":"ref_40","first-page":"51","article-title":"Data structures for statistical computing in python","volume":"vol. 445","author":"McKinney","year":"2010","journal-title":"Paper presented at the 9th Python in Science Conference"},{"key":"ref_41","unstructured":"McNally, Sean, Roche, Jason, and Caton, Simon (, January March). Predicting the price of Bitcoin using machine learning. Paper presented at the 26th International Conference on Parallel, Distributed and Network-Based Processing, Cambridge, UK."},{"key":"ref_42","unstructured":"Moritz, Benjamin, and Zimmermann, Tom (2014). Deep Conditional Portfolio Sorts: The Relation between Past and Future Stock Returns, Working Paper."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1750003","DOI":"10.1142\/S2010495217500038","article-title":"A statistical risk assessment of Bitcoin and its extreme tail behavior","volume":"12","author":"Osterrieder","year":"2017","journal-title":"Annals of Financial Economics"},{"key":"ref_44","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref_45","unstructured":"Python Software Foundation (2018, December 15). Python 3.5.2 Documentation. Available online: https:\/\/docs.python.org\/3.5\/."},{"key":"ref_46","unstructured":"Quantopian Inc. (2018, December 15). Empyrical: Common Financial Risk Metrics. Available online: https:\/\/github.com\/quantopian\/empyrical."},{"key":"ref_47","unstructured":"Raschka, Sebastian (2015). Python Machine Learning, Packt Publishing."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Schnaubelt, Matthias, Rende, Jonas, and Krauss, Christopher (2019). Testing Stylized Facts of Bitcoin Limit Order Books. Journal of Risk and Financial Management, 12.","DOI":"10.3390\/jrfm12010025"},{"key":"ref_49","unstructured":"Shah, Devavrat, and Zhang, Kang (, January October). Bayesian regression and Bitcoin. Paper presented at the 52nd Conference on Communication, Control, and Computing, Monticello, IL, USA."},{"key":"ref_50","unstructured":"Takeuchi, Lawrence, and Lee, Yu-Ying (2013). Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks, Working Paper."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1972","DOI":"10.1016\/j.jedc.2013.05.010","article-title":"Dynamic pairs trading using the stochastic control approach","volume":"37","author":"Tourin","year":"2013","journal-title":"Journal of Economic Dynamics and Control"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MCSE.2011.37","article-title":"The NumPy array: A structure for efficient numerical computation","volume":"13","author":"Colbert","year":"2011","journal-title":"Computing in Science & Engineering"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.3758\/s13428-012-0314-x","article-title":"Norms of valence, arousal, and dominance for 13,915 English lemmas","volume":"45","author":"Warriner","year":"2013","journal-title":"Behavior Research Methods"}],"container-title":["Journal of Risk and Financial Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1911-8074\/12\/1\/31\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:31:46Z","timestamp":1760185906000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1911-8074\/12\/1\/31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,13]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,3]]}},"alternative-id":["jrfm12010031"],"URL":"https:\/\/doi.org\/10.3390\/jrfm12010031","relation":{},"ISSN":["1911-8074"],"issn-type":[{"value":"1911-8074","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,13]]}}}