Paper: arXiv 2601.18686

Authors: Stefano Corti, Roberto Daluiso, Andrea Pallavicini

Abstract

In recent decades, companies have frequently adopted share repurchase programs to return capital to shareholders or for other strategic purposes, instructing investment banks to rapidly buy back shares on their behalf. When the executing institution is allowed to hedge its exposure, it encounters several challenges due to the intrinsic features of the product. Moreover, contractual clauses or market regulations on trading activity may make it infeasible to rely on Greeks. In this work, we address the hedging of these products by developing a machine-learning framework that determines the optimal execution of the buyback while explicitly accounting for the bank’s actual trading capabilities. This unified treatment of execution and hedging yields substantial performance improvements, resulting in an optimized policy that provides a feasible and realistic hedging approach. The pricing of these programs can be framed in terms of the discount that banks offer to the client on the price at which the shares are delivered. Since, in our framework, risk measures serve as objective functions, we exploit the concept of indifference pricing to compute this discount, thereby capturing the actual execution performance.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper provides a strong theoretical and mathematical framework by unifying deep hedging and optimal execution for Accelerated Share Repurchases (ASR). While the numerical experiments in the excerpt rely on standard Black-Scholes simulations, the formulation of probabilistic optimal stopping relaxed for neural network back-propagation is highly innovative and practical.

Research Flowchart

  flowchart TD
    A[Research Goal: Optimal execution & deep hedging for share repurchase programs] --> B[Inputs: Contract clauses, market regulations & bank trading constraints]
    B --> C[Methodology: Machine Learning Framework for Deep Hedging]
    C --> D[Computational Process: Joint optimization of buyback execution & risk-based hedging]
    D --> E[Pricing Mechanism: Calculate client discounts via Indifference Pricing]
    E --> F[Outcomes: Realistic, feasible hedging policy with substantial performance improvements]

Cited References (32)

  1. Changing Motives for Share Repurchases (2003) — link
  2. Accelerated share repurchases (2011)
  3. Dividend Policy, Growth, and the Valuation of Shares (1961)
  4. Payout policy (2003)
  5. Payout Policy (2014) — link
  6. Accelerated share repurchase and other buyback programs: what neural networks can bring (2020) — link
  7. Deep hedging (2019) — link
  8. Empirical deep hedging (2023) — link
and 24 more
  1. No‑Transaction Band Network: A Neural Network Architecture for Efficient Deep Hedging (2021) — link
  2. Pricing and Managing Complex Share Buy-Back Contracts: An Alternative to Optimal Control (2024) — link
  3. Stochastic Finance: An Introduction in Discrete Time (2016) — link
  4. Accelerated Share Repurchase: pricing and execution strategy (2015) — link
  5. Optimal Execution of Accelerated Share Repurchase Contracts with Fixed Notional (2017) — link
  6. Convex Measures of Risk and Trading Constraints (2002) — link
  7. An old-new concept of convex risk measures: the optimized certainty equivalent (2007) — link
  8. Hedging American Put Options with Deep Reinforcement Learning (2024) — link
  9. Deep Hedging Bermudan Swaptions (2024) — link
  10. Fast Deep Hedging with Second-Order Optimization (2024) — link
  11. Efficient Learning of Nested Deep Hedging using Multiple Options — → 2305.12264
  12. Ambiguity-Averse Deep Hedging with Feature Clustering (2025) — link
  13. Distributional Adversarial Attacks and Training in Deep Hedging (2025) — link
  14. Relationship between deep hedging and delta hedging: Leveraging a statistical arbitrage strategy (2024) — link
  15. Deep Hedging with Options Using the Implied Volatility Surface (2025) — link
  16. Deep Gamma Hedging (2024) — link
  17. Gamma and Vega Hedging using Deep Distributional Reinforcement Learning (2023) — link
  18. Deep Hedging: Learning to Simulate Equity Option Markets (2019) — link
  19. A Data-driven Market Simulator for Small Data Environments (2020) — link
  20. Multi-Asset Spot and Option Market Simulation (2021) — link
  21. Deep Generators on Commodity Markets; application to Deep Hedging (2022) — link
  22. Deep Hedging: Learning to Remove the Drift under Trading Frictions with Minimal Equivalent Near-Martingale Measures (2022) — link
  23. Deep Hedging: Learning Risk-Neutral Implied Volatility Dynamics (2021) — link
  24. Optimal Accelerated Share Repurchases (2017) — link

1 of 32 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.