TY  - JOUR
AU  - Chen, Yinlei
AU  - Xu, Jingyuan
PY  - 2026
DA  - 2026/01/12
TI  - Deep Learning for U.S. Bond Yield Forecasting: An Enhanced LSTM–LagLasso Framework
JO  - ICCK Transactions on Emerging Topics in Artificial Intelligence
T2  - ICCK Transactions on Emerging Topics in Artificial Intelligence
JF  - ICCK Transactions on Emerging Topics in Artificial Intelligence
VL  - 3
IS  - 2
SP  - 61
EP  - 75
DO  - 10.62762/TETAI.2025.197745
UR  - https://www.icck.org/article/abs/TETAI.2025.197745
KW  - curve consistency projection
KW  - asymmetric economic calibration (AEC)
KW  - weakly-coupled second-maturity
KW  - yield curve forecasting
KW  - decision-aligned post-processing
KW  - basis-point economic loss
KW  - capacity-fair baselines
AB  - This paper advances a decision-aligned post-processing layer for government bond yield forecasts, turning competent sequence predictions into curve-consistent and economically calibrated outputs with minimal engineering burden. Starting from capacity-fair baselines in the LSTM, GRU and compact transformer families, used only to generate initial point forecasts for five, ten and thirty year maturities at short horizons, we add two model-agnostic stages. A curve consistency projection enforces monotone ordering across maturities and, when warranted, mild convexity while preserving local signal. An asymmetric economic calibration then learns a monotone mapping that down-weights the costlier side of error in basis points and in price space via duration and convexity. Rather than a perfectly linear workflow, we report practical adjustments such as solver choices for the projection and calibration folds for stability. Evaluation considers violation rates, smoothness and decision-weighted loss, and probes weakly coupled transfer from ten year forecasts to five and thirty year using rolling linear links without retraining. Results indicate lower violation rates and reduced economic loss to some extent across horizons, though gains can depend on regimes and may partly reflect calibration rather than new information. Alternative explanations including liquidity frictions or structural breaks remain plausible, and further research is needed on denser tenor grids, portfolio utilities and additional markets.
SN  - 3068-6652
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Chen2026Deep,
  author = {Yinlei Chen and Jingyuan Xu},
  title = {Deep Learning for U.S. Bond Yield Forecasting: An Enhanced LSTM–LagLasso Framework},
  journal = {ICCK Transactions on Emerging Topics in Artificial Intelligence},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {61-75},
  doi = {10.62762/TETAI.2025.197745},
  url = {https://www.icck.org/article/abs/TETAI.2025.197745},
  abstract = {This paper advances a decision-aligned post-processing layer for government bond yield forecasts, turning competent sequence predictions into curve-consistent and economically calibrated outputs with minimal engineering burden. Starting from capacity-fair baselines in the LSTM, GRU and compact transformer families, used only to generate initial point forecasts for five, ten and thirty year maturities at short horizons, we add two model-agnostic stages. A curve consistency projection enforces monotone ordering across maturities and, when warranted, mild convexity while preserving local signal. An asymmetric economic calibration then learns a monotone mapping that down-weights the costlier side of error in basis points and in price space via duration and convexity. Rather than a perfectly linear workflow, we report practical adjustments such as solver choices for the projection and calibration folds for stability. Evaluation considers violation rates, smoothness and decision-weighted loss, and probes weakly coupled transfer from ten year forecasts to five and thirty year using rolling linear links without retraining. Results indicate lower violation rates and reduced economic loss to some extent across horizons, though gains can depend on regimes and may partly reflect calibration rather than new information. Alternative explanations including liquidity frictions or structural breaks remain plausible, and further research is needed on denser tenor grids, portfolio utilities and additional markets.},
  keywords = {curve consistency projection, asymmetric economic calibration (AEC), weakly-coupled second-maturity, yield curve forecasting, decision-aligned post-processing, basis-point economic loss, capacity-fair baselines},
  issn = {3068-6652},
  publisher = {Institute of Central Computation and Knowledge}
}