# Causal interventions in bond multi-dealer-to-client platforms

## TL;DR

This paper introduces a new framework using probabilistic models and causal inference to optimize trading strategies in bond trading platforms.

## Contribution

A novel framework combining probabilistic graphical models and causal inference for analyzing and optimizing multi-dealer-to-client bond trading.

## Key findings

- Generative models can match the predictive accuracy of discriminative models like LightGBM in bond trading.
- Generative models enforce business requirements such as spread monotonicity.
- The framework helps dealers compute optimal prices and identify interested clients.

## Abstract

The digitalization of financial markets has shifted trading from voice to electronic channels, with Multi-Dealer-to-Client (MD2C) platforms now enabling clients to request quotes (RfQs) for financial instruments like bonds from multiple dealers simultaneously. In this competitive landscape, dealers cannot see each other’s prices, making a rigorous analysis of the negotiation process crucial to ensure their profitability. This article introduces a novel general framework for analyzing the RfQ process using probabilistic graphical models and causal inference. Within this framework, we explore different inferential questions that are relevant for dealers participating in MD2C platforms, such as the computation of optimal prices, estimating potential revenues and the identification of clients that might be interested in trading the dealer’s axes. We then move into analyzing two different approaches for model specification: a generative model built on the work of (Fermanian, Guéant, & Pu, 2017); and discriminative models utilizing machine learning techniques. Our results show that generative models can match the predictive accuracy of leading discriminative algorithms such as LightGBM (ROC-AUC: 0.742 vs. 0.743) while simultaneously enforcing critical business requirements, notably spread monotonicity.