Papers
Topics
Authors
Recent
Search
2000 character limit reached

Detecting Toxic Flow

Published 10 Dec 2023 in q-fin.TR and cs.LG | (2312.05827v1)

Abstract: This paper develops a framework to predict toxic trades that a broker receives from her clients. Toxic trades are predicted with a novel online Bayesian method which we call the projection-based unification of last-layer and subspace estimation (PULSE). PULSE is a fast and statistically-efficient online procedure to train a Bayesian neural network sequentially. We employ a proprietary dataset of foreign exchange transactions to test our methodology. PULSE outperforms standard machine learning and statistical methods when predicting if a trade will be toxic; the benchmark methods are logistic regression, random forests, and a recursively-updated maximum-likelihood estimator. We devise a strategy for the broker who uses toxicity predictions to internalise or to externalise each trade received from her clients. Our methodology can be implemented in real-time because it takes less than one millisecond to update parameters and make a prediction. Compared with the benchmarks, PULSE attains the highest PnL and the largest avoided loss for the horizons we consider.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. Dealership market: Market-making with inventory. Journal of financial economics, 8(1):31–53.
  2. Deep attentive survival analysis in limit order books: Estimating fill probabilities with convolutional-transformers. arXiv preprint arXiv:2306.05479.
  3. Bagehot, W. (1971). The only game in town. Financial Analysts Journal, 27(2):12–14.
  4. Internalisation by electronic FX spot dealers. Quantitative Finance, 19(1):35–56.
  5. Bandits for algorithmic trading with signals. Available at SSRN 4484004.
  6. Brokers and informed traders: dealing with toxic flow and extracting trading signals. Available at SSRN.
  7. Optimal execution with stochastic delay. Finance and Stochastics, 27(1):1–47.
  8. Information effects on the bid-ask spread. The Journal of Finance, 38(5):1457–1469.
  9. Efficient online bayesian inference for neural bandits. In International Conference on Artificial Intelligence and Statistics, pages 6002–6021. PMLR.
  10. Liquidity, information, and infrequently traded stocks. The Journal of Finance, 51(4):1405–1436.
  11. Fawcett, T. (2006). An introduction to roc analysis. Pattern Recognition Letters, 27(8):861–874. ROC Analysis in Pattern Recognition.
  12. Bid, ask and transaction prices in a specialist market with heterogeneously informed traders. Journal of financial economics, 14(1):71–100.
  13. On the impossibility of informationally efficient markets. The American Economic Review, 70(3):393–408.
  14. The Elements of Statistical Learning. Springer Series in Statistics. Springer New York Inc., New York, NY, USA.
  15. Adam: A method for stochastic optimization. In Bengio, Y. and LeCun, Y., editors, 3rd International Conference on Learning Representations, ICLR 2015.
  16. Kyle, A. S. (1985). Continuous auctions and insider trading. Econometrica: Journal of the Econometric Society, pages 1315–1335.
  17. Kyle, A. S. (1989). Informed speculation with imperfect competition. The Review of Economic Studies, 56(3):317–355.
  18. The recursive variational Gaussian approximation (R-VGA). Statistics and Computing, 32(1):10.
  19. How many degrees of freedom do we need to train deep networks: a loss landscape perspective.
  20. Stein’s lemma for the reparameterization trick with exponential family mixtures.
  21. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45(1-3):503–528.
  22. Murphy, K. P. (2022). Probabilistic Machine Learning: An Introduction. MIT Press.
  23. Murphy, K. P. (2023). Probabilistic Machine Learning: Advanced Topics. MIT Press.
  24. Ollivier, Y. (2017). Online natural gradient as a Kalman filter.
  25. Oomen, R. (2017). Execution in an aggregator. Quantitative Finance, 17(3):383–404.
Citations (5)

Summary

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.