Predicting the Behavior of Dealers in Over-The-Counter Corporate Bond Markets

TL;DR

This paper develops machine learning models, including a novel PPRZ Transformer, to predict OTC dealer trading behavior in US corporate bonds, highlighting the importance of activity level and dealer clustering.

Contribution

It introduces the PPRZ Transformer model for dealer behavior prediction and demonstrates its effectiveness over existing models, considering dealer activity and clustering.

Findings

Individual dealer history yields best predictions for active dealers.

Collective models outperform for less active dealers.

Clustering dealers enhances prediction accuracy.

Abstract

Trading in Over-The-Counter (OTC) markets is facilitated by broker-dealers, in comparison to public exchanges, e.g., the New York Stock Exchange (NYSE). Dealers play an important role in stabilizing prices and providing liquidity in OTC markets. We apply machine learning methods to model and predict the trading behavior of OTC dealers for US corporate bonds. We create sequences of daily historical transaction reports for each dealer over a vocabulary of US corporate bonds. Using this history of dealer activity, we predict the future trading decisions of the dealer. We consider a range of neural network-based prediction models. We propose an extension, the Pointwise-Product ReZero (PPRZ) Transformer model, and demonstrate the improved performance of our model. We show that individual history provides the best predictive model for the most active dealers. For less active dealers, a collective model provides improved performance. Further, clustering dealers based on their similarity can improve performance. Finally, prediction accuracy varies based on the activity level of both the bond and the dealer.