Robust Yield Curve Estimation for Mortgage Bonds Using Neural Networks

Paper: arXiv 2510.21347

Authors: Sina Molavipour, Alireza M. Javid, Cassie Ye, Björn Löfdahl, Mikhail Nechaev

Abstract

Robust yield curve estimation is crucial in fixed-income markets for accurate instrument pricing, effective risk management, and informed trading strategies. Traditional approaches, including the bootstrapping method and parametric Nelson-Siegel models, often struggle with overfitting or instability issues, especially when underlying bonds are sparse, bond prices are volatile, or contain hard-to-remove noise. In this paper, we propose a neural networkbased framework for robust yield curve estimation tailored to small mortgage bond markets. Our model estimates the yield curve independently for each day and introduces a new loss function to enforce smoothness and stability, addressing challenges associated with limited and noisy data. Empirical results on Swedish mortgage bonds demonstrate that our approach delivers more robust and stable yield curve estimates compared to existing methods such as Nelson-Siegel-Svensson (NSS) and Kernel-Ridge (KR). Furthermore, the framework allows for the integration of domain-specific constraints, such as alignment with risk-free benchmarks, enabling practitioners to balance the trade-off between smoothness and accuracy according to their needs.

Complexity vs Empirical Score

• Math Complexity: 5.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper provides a practical machine learning application for yield curve construction in illiquid markets, supported by clear mathematical formulations of standard benchmarks like NSS and Kernel-Ridge. The empirical validation on Swedish mortgage bonds demonstrates solid utility, though open code availability is missing.

Research Flowchart

  flowchart TD
    A[Goal: Robust Yield Curve Estimation for Small, Noisy Mortgage Markets] --> B[Data Inputs: Swedish Mortgage Bond Prices & Risk-Free Benchmarks]
    B --> C[Neural Network Framework: Independent Daily Curve Estimation]
    C --> D[Computational Core: Custom Loss Function enforcing Smoothness, Stability & Constraints]
    D --> E[Outcomes: Outperforms NSS & KR Models with Optimal Smoothness-Accuracy Trade-off]

Cited References (12)

1. Parsimonious Modeling of Yield Curves (1987)
2. Estimating and interpreting forward interest rates: Sweden 1992-1994 (1994)
3. Yield curve modelling and a conceptual framework for estimating yield curves: evidence from the European Central Bank’s yield curves (2018)
4. Yield curve modelling at the bank of canada (1999)
5. Stripping the Discount Curve — a Robust Machine Learning Approach (2022)
6. Measuring the Term Structure of Interest Rates (1971)
7. The tax-adjusted yield curve (1975)
8. Learning forecast-efficient yield curve factor decompositions with neural networks (2022)

0 of 12 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.