Detecting Toxic Flow
This work addresses a domain-specific problem for brokers in finance by providing an incremental improvement in toxic trade detection to optimize trade internalization or externalization strategies.
The paper tackles the problem of predicting toxic trades in foreign exchange transactions using a novel online Bayesian method called PULSE, which outperforms benchmarks like logistic regression and random forests by achieving the highest profit and loss (PnL) and largest avoided loss in real-time predictions.
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.