Paper: arXiv 2511.17892

Authors: Xiang Gao, Cody Hyndman

Abstract

We develop an arbitrage-free deep learning framework for yield curve and bond price forecasting based on the Heath-Jarrow-Morton (HJM) term-structure model and a dynamic Nelson-Siegel parameterization of forward rates. Our approach embeds a no-arbitrage drift restriction into a neural state-space architecture by combining Kalman, extended Kalman, and particle filters with recurrent neural networks (LSTM/CLSTM), and introduces an explicit arbitrage error regularization (AER) term during training. The model is applied to U.S. Treasury and corporate bond data, and its performance is evaluated for both yield-space and price-space predictions at 1-day and 5-day horizons. Empirically, arbitrage regularization leads to its strongest improvements at short maturities, particularly in 5-day-ahead forecasts, increasing market-consistency as measured by bid-ask hit rates and reducing dollar-denominated prediction errors.

Complexity vs Empirical Score

  • Math Complexity: 9.2/10
  • Empirical Rigor: 7.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced mathematics, including the Heath-Jarrow-Morton framework, stochastic differential equations, Kalman/particle filters, and neural network integration with explicit arbitrage constraints, warranting a high complexity score. It also demonstrates strong empirical rigor with backtesting on U.S. Treasury and corporate bond data, measuring performance across horizons and maturities, and reporting metrics like bid-ask hit rates and dollar-denominated errors.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Arbitrage-Free Bond &<br>Yield Curve Forecasting"] --> B["Data & Inputs:<br>US Treasury & Corporate Bonds"]
  B --> C["Methodology:<br>Neural State-Space Model<br>with HJM Constraints"]
  C --> D["Computational Process:<br>LSTM/CLSTM + Kalman/Particle Filters"]
  D --> E["Training:<br>Arbitrage Error<br>Regularization AER"]
  E --> F["Key Findings:<br>Increased Accuracy<br>Bid-Ask Alignment<br>Short Maturity Improvement"]

Cited References (46)

  1. Deep Learning for Bond Yield Forecasting: The LSTM‐LagLasso (2025) — link
  2. Real-world models for multiple term structures: a unifying HJM semimartingale framework — → 2411.01983
  3. Yield curve extrapolation with machine learning (2024) — link
  4. Forecasting the yield curve: the role of additional and time‐varying decay parameters, conditional heteroscedasticity, and macro‐economic factors (2024) — link
  5. Machine Learning and the Yield Curve: Tree-Based Macroeconomic Regime Switching (2024) — link
  6. VolGAN: A Generative Model for Arbitrage-Free Implied Volatility Surfaces (2024) — link
  7. A Smooth Shadow-Rate Dynamic Nelson-Siegel Model for Yields at the Zero Lower Bound (2024) — link
  8. Multiple yield curve modeling and forecasting using deep learning (2024) — link
and 38 more
  1. The geometry of multi-curve interest rate models — → 2401.11619
  2. Transformers Can Solve Non-Linear and Non-Markovian Filtering Problems in Continuous Time For Conditionally Gaussian Signals (2023) — link
  3. Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter (2023) — link
  4. Term structure modeling with overnight rates beyond stochastic continuity (2023) — link
  5. A stochastic control perspective on term structure models with roll-over risk (2023) — link
  6. Particle Filter with LMMSE Importance Sampling (2022) — link
  7. Learning Forecast-Efficient Yield Curve Factor Decompositions with Neural Networks (2022) — link
  8. KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics (2021) — link
  9. Arbitrage-Free Neural-SDE Market Models (2021) — link
  10. Model-Based Deep Learning (2020) — link
  11. Deep Arbitrage-Free Learning in a Generalized HJM Framework via Arbitrage-Regularization (2017) — link
  12. Machine Learning for Better Models for Predicting Bond Prices (2017) — link
  13. Parameter Estimation For Multivariate Generalized Gaussian Distributions (2013) — link
  14. Price Dispersion in OTC Markets: A New Measure of Liquidity (2011) — link
  15. A stochastic processes toolkit for risk management: Geometric Brownian motion, jumps, GARCH and variance gamma models (2007) — link
  16. Global Yield Curve Dynamics and Interactions : A Dynamic (2007) — link
  17. Credit risk modeling with affine processes (2007) — link
  18. On the Existence of Finite‐Dimensional Realizations for Nonlinear Forward Rate Models (2001) — link
  19. Long Short-Term Memory (1997) — link
  20. Testing Term Structure Estimation Methods (1996)
  21. Estimating and Interpreting Forward Interest Rates: Sweden 1992-1994 (1994) — link
  22. Common Factors Affecting Bond Returns (1991) — link
  23. Autoencoder-Based Risk-Neutral Model for Interest Rates (2024) — link
  24. Yield Curve Forecasting using Deep Learning Nelson-Siegel Model (2023) — link
  25. Nonlinear Kalman filtering in affine term structure models (2014)
  26. LIQUIDITY AND CREDIT RISK PREMIA IN GOVERNMENT BOND YIELDS (2012)
  27. The affine arbitrage-free class of Nelson–Siegel term structure models (2011)
  28. NBER WORKING PAPER SERIES THE MACROECONOMY AND THE YIELD CURVE: A DYNAMIC LATENT FACTOR APPROACH (2004)
  29. The Rodney L . White Center for Financial Research Forecasting the Term Structure of Government Bond Yields (2003)
  30. Filtering in finance (2003)
  31. Monte Carlo strategies in scientific computing (2001)
  32. A No-Arbitrage Vector Autoregression of Term Structure Dynamics with Macroeconomic and Latent Variables (1999)
  33. Monte Carlo filter and smoother for non-Gaussian nonlinear state space models (1996)
  34. Bond pricing and the term structure of interest rates: A new methodology for contingent claims valuation (1992)
  35. Parsimonious modeling of yield curves (1987) — link
  36. Deep learning of data-driven Heath–Jarrow–Morton models
  37. Stochastic control, numerical methods, and machine learning in finance and insurance
  38. Machine learning for interest rates: Using auto-encoders for the risk-neutral modeling of yield curves

2 of 46 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.