Arbitrage-Free Bond and Yield Curve Forecasting with Neural Filters under HJM Constraints
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914167293739008 |
|---|---|
| author | Gao, Xiang Hyndman, Cody |
| author_facet | Gao, Xiang Hyndman, Cody |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_17892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Arbitrage-Free Bond and Yield Curve Forecasting with Neural Filters under HJM Constraints Gao, Xiang Hyndman, Cody Mathematical Finance Machine Learning Computational Finance 91G30 (Primary) 65C30, 60H30 (Secondary) 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. |
| title | Arbitrage-Free Bond and Yield Curve Forecasting with Neural Filters under HJM Constraints |
| topic | Mathematical Finance Machine Learning Computational Finance 91G30 (Primary) 65C30, 60H30 (Secondary) |
| url | https://arxiv.org/abs/2511.17892 |