A deep learning approach for pricing convertible bonds with path-dependent reset and call provisions

2026-05-12

AI Summary

This study addresses the pricing challenge of convertible bonds featuring path-dependent downward reset provisions and issuer call options by proposing a novel integration of path-dependent partial differential equations (PPDEs) with deep learning. The method employs a discrete-time dynamic programming framework implemented via neural networks to efficiently approximate conditional expectations, thereby handling complex path dependencies. It demonstrates robust performance across multiple underlying asset dynamics—including geometric Brownian motion, CEV, and Heston models—and accurately captures both prices and sensitivities in an empirical application to China CITIC Bank’s convertible bond. The analysis yields three key economic insights: contractual terms predominantly drive valuation; the call provision substantially depresses bond value; and, counterintuitively, the downward reset mechanism can lead to lower prices rather than enhancing investor protection.

Abstract

This paper develops a deep learning-based framework for pricing convertible bonds with path-dependent contractual features, namely downward conversion price reset and issuer call clauses under rolling-window trigger rules, which are widespread in the convertible bond market. We formulate the valuation problem as a path-dependent partial differential equation (PPDE), which explicitly captures the dependence of the convertible bond value on the historical path of the underlying asset and the dynamic evolution of the conversion price. We derive consistent PPDE formulations for three canonical underlying dynamics: geometric Brownian motion (GBM), constant elasticity of variance (CEV) and Heston stochastic volatility. We then construct a discrete-time dynamic programming scheme in which conditional expectations are approximated by neural networks, which remains tractable in such high-dimensional path-dependent setting. Empirical tests on China CITIC Bank Convertible Bond show that our framework produces stable and accurate prices and sensitivity patterns across all model specifications. Three key economic insights emerge: 1. Contractual features dominate underlying dynamics in determining convertible bond values. 2. The call provision decreases convertible bonds prices by truncating upside gains. 3. Counterintuitively, despite improving conversion terms, the downward reset provision further decreases the price of convertible bonds by lowering the effective call threshold and making early redemption more likely. The proposed PPDE-deep learning approach provides an efficient, flexible tool for pricing convertible bonds with complex path-dependent structures.

Problem

• convertible bonds
• path-dependent provisions
• downward reset
• call provision
• pricing

Innovation

• path-dependent PDE
• deep learning
• convertible bond pricing
• downward reset provision
• issuer call clause