Multi-Task Dynamic Pricing in Credit Market with Contextual Information

2024-10-18

arXiv.org

AI Summary

To address the challenges of sparse trading, scarce pricing data, and low transparency in over-the-counter (OTC) credit markets—particularly for bonds—this paper proposes a Two-Stage Multi-Task (TSMT) dynamic pricing framework. TSMT is the first method to jointly leverage unregularized global estimation and regularized individual fine-tuning under heterogeneity constraints, synergistically exploiting structural similarities across securities and feedback from probe orders to learn competitive quotes. Theoretically, TSMT achieves an optimal regret bound of $ ilde{O}(delta_{max}sqrt{T M d} + M d)$, substantially outperforming both fully independent and fully joint baseline approaches. Empirically, on $M$ securities, TSMT attains higher pricing accuracy and faster convergence, demonstrating scalability and robustness. This work establishes a novel, practical paradigm for dynamic pricing in opaque OTC credit markets.

Technology Category

• Search and Optimization: Learning to Search
• Multiagent Systems: Mechanism Design
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Advertising auctions, pricing, markets, and exchanges
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We study the dynamic pricing problem faced by a broker seeking to learn prices for a large number of credit market securities, such as corporate bonds, government bonds, loans, and other credit-related securities. A major challenge in pricing these securities stems from their infrequent trading and the lack of transparency in over-the-counter (OTC) markets, which leads to insufficient data for individual pricing. Nevertheless, many securities share structural similarities that can be exploited. Moreover, brokers often place small"probing"orders to infer competitors' pricing behavior. Leveraging these insights, we propose a multi-task dynamic pricing framework that leverages the shared structure across securities to enhance pricing accuracy. In the OTC market, a broker wins a quote by offering a more competitive price than rivals. The broker's goal is to learn winning prices while minimizing expected regret against a clairvoyant benchmark. We model each security using a $d$-dimensional feature vector and assume a linear contextual model for the competitor's pricing of the yield, with parameters unknown a priori. We propose the Two-Stage Multi-Task (TSMT) algorithm: first, an unregularized MLE over pooled data to obtain a coarse parameter estimate; second, a regularized MLE on individual securities to refine the parameters. We show that the TSMT achieves a regret bounded by $ ilde{O} ( delta_{max} sqrt{T M d} + M d ) $, outperforming both fully individual and fully pooled baselines, where $M$ is the number of securities and $delta_{max}$ quantifies their heterogeneity.

Problem

• Dynamic pricing for infrequently traded credit market securities
• Learning winning prices in OTC markets with contextual data
• Multi-task framework to improve pricing accuracy across securities

Innovation

• Multi-task dynamic pricing framework for credit securities
• Two-Stage Multi-Task algorithm with MLE refinement
• Contextual linear model for competitor yield pricing