Predictability Without Monetization: A Point-in-Time Audit of Order-Flow Signals on the Moscow Exchange
Description
Version 2 — revision after two independent reviews. The headline result has changed: the order-flow composite is not worth more than a free 12-month momentum rank, and the short-borrow fee, now measured at the broker (median 25.0% a year across 72 names, range 20.0–125.0%), leaves the book below the policy rate at every realistic rate. Additions: the registered momentum test E1 (contrast +0.019% per day, interval containing zero), a power ladder for the confirmation rule (14.8% power at 60 dates; 561 dates for 80%), a risk profile (maximum drawdown −18.2%, 99% Cornish–Fisher loss −4.3%), a capacity bound, a measurement of pipeline latency, and a registered protocol for a second real-time window from 19 October 2026.
Objective: This working paper audits whether commercially available order-flow data predicts the cross-section of Russian equity returns and whether such prediction can be monetized, applying strict AI/ML research and reproducibility standards.
Methodology & Data: The study analyzes the 100 most liquid Moscow Exchange (MOEX) stocks using five-minute order-book, order, and trade statistics from AlgoPack. The research protocol enforces rigorous AI SDLC practices: hypotheses and thresholds are fixed prior to outcome evaluation, the universe is built point-in-time, overlapping labels are purged, and results are benchmarked against permutation placebos and mechanism-free controls.
Key Findings:
- Effects estimated on regenerated rows are about twice their real-time size (e.g., IC 0.117–0.133 on the regenerated fitting sample vs. 0.096 in real time).
- Value beyond 12-month momentum (IC 0.107, t = 3.95) is not established: the composite-minus-momentum contrast is +0.019%/day with an interval containing zero.
- Evidence for monetization is inconclusive: with borrow fees now measured at the broker (median 25%, range 20–125%), the book earns 0.038%/day at the median fee with a 95% interval that includes zero, and turns negative at the upper quartile; gross returns concentrate in the short leg, and borrow availability by date remains unmeasured.
- Of 42 tested research directions, 33 failed their pre-specified criteria, four passed without beating the policy rate, and five remain leads awaiting frozen forward tests.
Reproducibility Statement: The primary contribution of this work is the point-in-time audit framework and the documentation of provenance hazards, rather than a deployable trading strategy. To ensure full reproducibility, all code, execution plans, run logs, and model hashes are publicly available in the associated repository.
Keywords: Quantitative Finance, Algorithmic Trading, Order Flow, MOEX, Reproducible Research
Files
main.pdf
Additional details
Dates
- Issued
-
2026-10v1
- Updated
-
2026-11v2
Software
- Repository URL
- https://github.com/alterfo/moex-trader
- Programming language
- Go , Python
- Development Status
- Active
References
- Erdinc Akyildirim, Ahmet Sensoy, Guzhan Gulay, Shaen Corbet, and Hajar Novin Salari. Big data analytics, order imbalance and the predictability of stock returns. Journal of Multinational Financial Management, 62:100717, 2021. doi: 10.1016/j.mulfin.2021.100717
- Diego Amaya, Peter Christoffersen, Kris Jacobs, and Aurelio Vasquez. Does realized skewness predict the cross-section of equity returns? Journal of Financial Economics, 118(1):135–167, 2015. doi: 10.1016/j.jfineco.2015.02.009
- Yakov Amihud. Illiquidity and stock returns: Cross-section and time-series effects. Journal of Financial Markets, 5(1):31–56, 2002. doi: 10.1016/S1386-4181(01)00024-6
- Donald W. K. Andrews. Heteroskedasticity and autocorrelation consistent covariance matrix estimation. Econometrica, 59(3):817–858, 1991. doi: 10.2307/2938229
- Andrei Ankudinov, Rustam Ibragimov, and Oleg Lebedev. Sanctions and the Russian stock market. Research in International Business and Finance, 40:150–162, 2017. doi: 10.1016/j.ribaf. 2017.01.005
- David H. Bailey and Marcos López de Prado. The Sharpe ratio efficient frontier. Journal of Risk, 15(2):3–44, 2012. doi: 10.21314/JOR.2012.255
- David H. Bailey and Marcos López de Prado. The deflated Sharpe ratio: Correcting for selection bias, backtest overfitting, and non-normality. Journal of Portfolio Management, 40(5):94–107, 2014. doi: 10.3905/jpm.2014.40.5.094
- David H. Bailey, Jonathan M. Borwein, Marcos López de Prado, and Qiji Jim Zhu. Pseudo- mathematics and financial charlatanism: The effects of backtest overfitting on out-of-sample performance. Notices of the American Mathematical Society, 61(5):458–471, 2014. doi: 10.1090/ noti1105
- David H. Bailey, Jonathan M. Borwein, Marcos López de Prado, and Qiji Jim Zhu. The probability of backtest overfitting. Journal of Computational Finance, 20(4):39–69, 2017. doi: 10.21314/JCF. 2016.322
- Yoav Benjamini and Yosef Hochberg. Controlling the false discovery rate: A practical and power- ful approach to multiple testing. Journal of the Royal Statistical Society: Series B (Methodological), 57(1):289–300, 1995. doi: 10.1111/j.2517-6161.1995.tb02031.x
- Yoav Benjamini and Daniel Yekutieli. The control of the false discovery rate in multiple testing under dependency. Annals of Statistics, 29(4):1165–1188, 2001. doi: 10.1214/aos/1013699998
- Vincent Bogousslavsky and Pierre Collin-Dufresne. Liquidity, volume, and order imbalance volatility. Journal of Finance, 78(4):2189–2232, 2023. doi: 10.1111/jofi.13248
- Jean-Philippe Bouchaud, Julius Bonart, Jonathan Donier, and Martin Gould. Trades, Quotes and Prices: Financial Markets Under the Microscope. Cambridge University Press, Cambridge, 2018. doi: 10.1017/9781316659335
- Jacob Boudoukh, Ronen Israel, and Matthew Richardson. Long-horizon predictability: A cautionary tale. Financial Analysts Journal, 75(1):17–30, 2019. doi: 10.1080/0015198X.2018. 1547056
- Tarun Chordia and Avanidhar Subrahmanyam. Order imbalance and individual stock returns: Theory and evidence. Journal of Financial Economics, 72(3):485–518, 2004. doi: 10.1016/S0304- 405X(03)00175-2
- Tarun Chordia, Richard Roll, and Avanidhar Subrahmanyam. Order imbalance, liquidity, and market returns. Journal of Financial Economics, 65(1):111–130, 2002. doi: 10.1016/S0304- 405X(02)00136-8
- Tarun Chordia, Amit Goyal, and Alessio Saretto. Anomalies and false rejections. Review of Financial Studies, 33(5):2134–2179, 2020. doi: 10.1093/rfs/hhaa018
- Rama Cont, Arseniy Kukanov, and Sasha Stoikov. The price impact of order book events. Journal of Financial Econometrics, 12(1):47–88, 2014. doi: 10.1093/jjfinec/nbt003
- Rama Cont, Mihai Cucuringu, and Chao Zhang. Cross-impact of order flow imbalance in equity markets. Quantitative Finance, 23(10):1373–1393, 2023. doi: 10.1080/14697688.2023.2236159
- Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou. A decoder-only foundation model for time-series forecasting. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pages 10148–10167, 2024
- Pavel Dovbnya. Announcements of sanctions and the Russian equity market: An event study approach. Russian Journal of Money and Finance, 79(1):74–92, 2020. doi: 10.31477/rjmf.202001. 74
- David Easley, Marcos M. López de Prado, and Maureen O'Hara. Flow toxicity and liquidity in a high-frequency world. Review of Financial Studies, 25(5):1457–1493, 2012. doi: 10.1093/rfs/ hhs053
- Eugene F. Fama and James D. MacBeth. Risk, return, and equilibrium: Empirical tests. Journal of Political Economy, 81(3):607–636, 1973. doi: 10.1086/260061
- Jerome Friedman, Trevor Hastie, and Robert Tibshirani. Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software, 33(1):1–22, 2010. doi: 10.18637/jss.v033.i01
- Nicolae Gârleanu and Lasse Heje Pedersen. Dynamic trading with predictable returns and transaction costs. Journal of Finance, 68(6):2309–2340, 2013. doi: 10.1111/jofi.12080
- Stefano Giglio, Yuan Liao, and Dacheng Xiu. Thousands of alpha tests. Review of Financial Studies, 34(7):3456–3496, 2021. doi: 10.1093/rfs/hhaa111
- Richard C. Grinold and Ronald N. Kahn. Active Portfolio Management. McGraw-Hill, New York, 2nd edition, 2000a
- Richard C. Grinold and Ronald N. Kahn. The efficiency gains of long–short investing. Financial Analysts Journal, 56(6):40–53, 2000b. doi: 10.2469/faj.v56.n6.2402
- Shihao Gu, Bryan Kelly, and Dacheng Xiu. Empirical asset pricing via machine learning. Review of Financial Studies, 33(5):2223–2273, 2020. doi: 10.1093/rfs/hhaa009
- Peter Reinhard Hansen. A test for superior predictive ability. Journal of Business & Economic Statistics, 23(4):365–380, 2005. doi: 10.1198/073500105000000063
- Campbell R. Harvey and Yan Liu. False (and missed) discoveries in financial economics. Journal of Finance, 75(5):2503–2553, 2020. doi: 10.1111/jofi.12951
- Campbell R. Harvey, Yan Liu, and Heqing Zhu. . . . and the cross-section of expected returns. Review of Financial Studies, 29(1):5–68, 2016. doi: 10.1093/rfs/hhv059
- Erik Hjalmarsson. New methods for inference in long-horizon regressions. Journal of Financial and Quantitative Analysis, 46(3):815–839, 2011. doi: 10.1017/S0022109011000135
- Arthur E. Hoerl and Robert W. Kennard. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1):55–67, 1970. doi: 10.1080/00401706.1970.10488634
- Kewei Hou, Chen Xue, and Lu Zhang. Replicating anomalies. Review of Financial Studies, 33(5): 2019–2133, 2020. doi: 10.1093/rfs/hhy131
- Bruce I. Jacobs, Kenneth N. Levy, and David Starer. On the optimality of long–short strategies. Financial Analysts Journal, 54(2):40–51, 1998. doi: 10.2469/faj.v54.n2.2164
- Narasimhan Jegadeesh. Evidence of predictable behavior of security returns. Journal of Finance, 45(3):881–898, 1990. doi: 10.1111/j.1540-6261.1990.tb05110.x
- Shachar Kaufman, Saharon Rosset, Claudia Perlich, and Ori Stitelman. Leakage in data mining: Formulation, detection, and avoidance. ACM Transactions on Knowledge Discovery from Data, 6 (4):15:1–15:21, 2012. doi: 10.1145/2382577.2382579
- Matloob Khushi. QFRS: Quantitative finance reporting standards for forecasting, evaluation and trading claims. Artificial Intelligence Review, 2026. doi: 10.1007/s10462-026-11664-w. In press
- Petter N. Kolm, Jeremy Turiel, and Nicholas Westray. Deep order flow imbalance: Extracting alpha at multiple horizons from the limit order book. Mathematical Finance, 33(4):1044–1081, 2023. doi: 10.1111/mafi.12413
- Hans R. Künsch. The jackknife and the bootstrap for general stationary observations. Annals of Statistics, 17(3):1217–1241, 1989. doi: 10.1214/aos/1176347265
- Albert S. Kyle. Continuous auctions and insider trading. Econometrica, 53(6):1315–1335, 1985. doi: 10.2307/1913210
- Daniël Lakens. Equivalence tests: A practical primer for t tests, correlations, and meta-analyses. Social Psychological and Personality Science, 8(4):355–362, 2017. doi: 10.1177/1948550617697177
- Daniël Lakens, Anne M. Scheel, and Peder M. Isager. Equivalence testing for psychological research: A tutorial. Advances in Methods and Practices in Psychological Science, 1(2):259–269, 2018. doi: 10.1177/2515245918770963
- Nathan Lassance, Victor DeMiguel, and Frédéric Vrins. Optimal portfolio diversification via independent component analysis. Operations Research, 70(1):55–72, 2022. doi: 10.1287/opre. 2021.2140
- Andrew W. Lo. The statistics of Sharpe ratios. Financial Analysts Journal, 58(4):36–52, 2002. doi: 10.2469/faj.v58.n4.2453
- Marcos López de Prado. Advances in Financial Machine Learning. Wiley, Hoboken, NJ, 2018
- N. M. Makeeva, P. A. Navolotskaia, R. R. Iskyandyarov, and A. A. Navolotskii. News sentiment index and its predictive power for the Russian stock market. Voprosy Ekonomiki, (6):135–154, 2026. doi: 10.32609/0042-8736-2026-6-135-154
- R. David McLean and Jeffrey Pontiff. Does academic research destroy stock return predictability? Journal of Finance, 71(1):5–32, 2016. doi: 10.1111/jofi.12365
- A. Yu. Mikhaylov, N. B. A. Yousif, Yu. N. Sotskov, and L. I. Khomyakova. Construction of high-order dynamic portfolio models based on VAR-ICA-MGARCH. Finance: Theory and Practice, 30(4):19–37, 2026. doi: 10.26794/2587-5671-2026-30-4-19-37
- Moscow Exchange. Results of trading on the Moscow Exchange in 2025: Private investors (press release, in Russian). https://www.moex.com/n96827, 2026a. Released 14 January 2026; reports a 70.7% retail share of equity trading volume in 2025
- Moscow Exchange. AlgoPack: Super candles (TradeStats, OrderStats, OBStats, HI2) and the moexalgo library. https://moexalgo.github.io/, 2026b. Accessed October 2026
- Dmitriy Muravyev, Neil D. Pearson, and Joshua M. Pollet. Anomalies and their short-sale costs. Journal of Finance, 2025. doi: 10.1111/jofi.13501. Early view.
- Whitney K. Newey and Kenneth D. West. A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix. Econometrica, 55(3):703–708, 1987. doi: 10.2307/1913610
- Miquel Noguer i Alonso and Rodolfo Pereira Franklin. Pretrained time-series foundation models for financial return forecasting. arXiv preprint arXiv:2606.27100, 2026
- Brian A. Nosek, Charles R. Ebersole, Alexander C. DeHaven, and David T. Mellor. The preregis- tration revolution. Proceedings of the National Academy of Sciences, 115(11):2600–2606, 2018. doi: 10.1073/pnas.1708274114
- Robert Novy-Marx. Backtesting strategies based on multiple signals. NBER Working Paper 21329, National Bureau of Economic Research, 2015
- Robert Novy-Marx and Mihail Velikov. A taxonomy of anomalies and their trading costs. Review of Financial Studies, 29(1):104–147, 2016. doi: 10.1093/rfs/hhv063
- Dale R. Nyholt. A simple correction for multiple testing for single-nucleotide polymorphisms in linkage disequilibrium with each other. American Journal of Human Genetics, 74(4):765–769, 2004. doi: 10.1086/383251
- Michael Parkinson. The extreme value method for estimating the variance of the rate of return. Journal of Business, 53(1):61–65, 1980. doi: 10.1086/296071
- Eghbal Rahimikia, Hao Ni, and Weiguan Wang. Re(Visiting) time series foundation models in finance. arXiv preprint arXiv:2511.18578, 2025
- Joseph P. Romano and Michael Wolf. Stepwise multiple testing as formalized data snooping. Econometrica, 73(4):1237–1282, 2005. doi: 10.1111/j.1468-0262.2005.00615.x
- Tyler Shumway. The delisting bias in CRSP data. Journal of Finance, 52(1):327–340, 1997. doi: 10.1111/j.1540-6261.1997.tb03818.x
- Ryan Sullivan, Allan Timmermann, and Halbert White. Data-snooping, technical trading rule performance, and the bootstrap. Journal of Finance, 54(5):1647–1691, 1999. doi: 10.1111/0022- 1082.00163.
- Halbert White. A reality check for data snooping. Econometrica, 68(5):1097–1126, 2000. doi: 10.1111/1468-0262.00152.
- Fan Zhang, Zhen Li, Sijia Peng, and Yu Chen. When alpha disappears: A one-switch benchmark for decision-time leakage in financial backtests. arXiv preprint arXiv:2605.23959, 2026.
- Hui Zou and Trevor Hastie. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301–320, 2005. doi: 10.1111/j.1467-9868.2005.00503.x.
- Bank of Russia. Key rate decisions, 2025–2026