Paper: arXiv 2409.00348
Authors: Peilun He, Gareth W. Peters, Nino Kordzakhia, Pavel V. Shevchenko
Abstract
The Nelson-Siegel model is widely used in fixed income markets to produce yield curve dynamics. The multiple time-dependent parameter model conveniently addresses the level, slope, and curvature dynamics of the yield curves. In this study, we present a novel state-space functional regression model that incorporates a dynamic Nelson-Siegel model and functional regression formulations applied to multi-economy setting. This framework offers distinct advantages in explaining the relative spreads in yields between a reference economy and a response economy. To address the inherent challenges of model calibration, a kernel principal component analysis is employed to transform the representation of functional regression into a finite-dimensional, tractable estimation problem. A comprehensive empirical analysis is conducted to assess the efficacy of the functional regression approach, including an in-sample performance comparison with the dynamic Nelson-Siegel model. We conducted the stress testing analysis of yield curves term-structure within a dual economy framework. The bond ladder portfolio was examined through a case study focused on spread modelling using historical data for US Treasury and UK bonds.
Complexity vs Empirical Score
- Math Complexity: 8.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced mathematical techniques including state-space models, functional regression, and kernel PCA, requiring dense theory and derivations. It also demonstrates strong empirical application with comprehensive historical data analysis, performance comparisons, stress testing, and a practical bond ladder case study, alongside accessible code and data availability.
Research Flowchart
flowchart TD
A["Research Goal:<br>Model Yield Curve Spreads &<br>Stress Test Multi-Economy Bonds"] --> B{"Data Inputs"};
B --> C["US & UK Treasury Data"];
B --> D["Nelson-Siegel<br>Parameters"];
C --> E["State-Space Functional Regression<br>with Kernel PCA"];
D --> E;
E --> F{"Model Assessment"};
F --> G["In-Sample Performance<br>vs. Dynamic Nelson-Siegel"];
F --> H["Stress Testing<br>Dual Economy Framework"];
G --> I["Key Outcomes"];
H --> I;
I --> J["Effective Spread Modeling<br>via Functional Regression"];
I --> K["Robust Stress Testing<br>on Bond Ladder Portfolios"];
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a novel dynamic Nelson‑Siegel functional regression (DNS‑FR) model that extends the DNS model by incorporating relative spreads between a reference and a response country.
Source sentence
we introduce a novel dynamic Nelson-Siegel functional regression (DNS-FR) model, which extends the DNS model by incorporating the relative spread between a reference country and a response country.
Assumes 6
- Missing data in reference country yields are filled by linear interpolation for simplicity. data
Source sentence
For the former, given the small amount of missing data in our datasets, we use linear interpolation to fill in the missing values for simplicity.
- A binary variable S_{ti} tracks missing response country yields. data
Source sentence
For the latter, we define a binary variable 𝑆𝑡𝑖 to track the missing data
- All bonds have the same variance and covariance decays with maturity difference in the simplified covariance structure. model
Source sentence
In this case, we assume that all bonds have the same variance, and the covariance of two bonds decays as the difference in maturities increases.
- Effective Federal Funds Rate (EFFR) is used as a proxy for the risk‑free interest rate. market
Source sentence
We used the effective federal funds rate (EFFR) as a proxy for the risk‑free interest rate.
Show 2 more
- The RBF kernel hyperparameter γ is selected via grid search over [0.001, 1] with step 0.001. statistical
Source sentence
The hyperparameter 𝛾 of the RBF kernel is estimated through a grid search. We choose 𝛾 from the range 0.001 to 1 with a step size of 0.001.
- The Kalman Filter estimates hidden factors by maximising the marginal likelihood. model
Source sentence
The Kalman Filter method is then employed to estimate unknown parameters and hidden state variables by maximising the marginal likelihood function.
Data
- US Treasury yields macro unknown
Source sentence
To estimate the yields of response countries, we first extract factors from US Treasury yields using kPCA
- UK bond yields macro unknown
Source sentence
The bond ladder portfolio was examined through a case study focused on spread modelling using historical data for US Treasury and UK bonds.
- Effective Federal Funds Rate (EFFR) macro public
Source sentence
The EFFR data was sourced from the website of the Federal Reserve Bank of New York.
- GBP/USD exchange rate macro public
Source sentence
Data was obtained from https://www.tradingview.com/.
Costs
Not applicable
Finds 3
- The DNS‑FR model significantly reduces in‑sample RMSE compared to the DNS model across all countries, especially for long‑term bonds (20‑30 years). predictive-accuracy
Source sentence
The DNS‑FR model significantly reduces the mean RMSE compared to the DNS model across all countries/regions.
- Stress tests show that middle and long‑end UK bond maturities are most affected, and temporary shocks have persistent effects even after the shock ends. performance
Source sentence
The study reveals that middle and long‑end maturities of UK bonds are mostly affected, regardless of whether the shock is applied to the short‑end, middle, or long‑end maturities of the US Treasury yield curve. Interestingly, for temporary shocks, their effects persist in the long run even after the shocks end.
- In the bond ladder case study, predicted portfolio values for 6‑month, 1‑year, and 30‑year bonds are similar, but the 30‑year bond carries higher risk with a wider confidence interval and a potential loss in the worst case. performance
Source sentence
The predicted portfolio values for the three bonds are similar, but the bond with a longer maturity carries higher risk, reflected in a wider confidence interval. The 5% VaR suggests that investing in the 6‑month and 1‑year bonds is unlikely to result in a loss over one year, whereas investing in the 30‑year bond may l
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 13 related papers). Coverage is partial, so this is neither replication nor refutation.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (50)
- Forecasting the term structures of Treasury and corporate yields using dynamic Nelson-Siegel models (2011)
- Forecasting the term structure of government bond yields (2006)
- Global yield curve dynamics and interactions: a dynamic Nelson–Siegel approach (2008)
- Parsimonious modeling of yield curves (1987)
- Analyzing the term structure of interest rates using the dynamic Nelson–Siegel model with time-varying parameters (2010)
- Multi yield curve stress-testing framework incorporating temporal and cross tenor structural dependencies (2017)
- Nonlinear component analysis as a kernel eigenvalue problem (1998)
- Kernel PCA and de-noising in feature spaces (1998)
and 42 more
- Kernel PCA for feature extraction and de-noising in nonlinear regression (2001)
- Kernel PCA for novelty detection (2007)
- Conditions for the positivity of determinants (1996)
- The macroeconomy and the yield curve: a dynamic latent factor approach (2006)
- Estimating and interpreting forward interest rates: Sweden 1992-1994 (1994)
- An equilibrium characterization of the term structure (1977)
- A Theory of the Term Structure of Interest Rates (1985)
- A yield-factor model of interest rates (1996)
- Pricing interest-rate-derivative securities (1990)
- Bond pricing and the term structure of interest rates: A new methodology for contingent claims valuation (1992)
- Nonparametric estimation of functional dynamic factor model (2022)
- Functional dynamic factor models with application to yield curve forecasting (2012)
- Do US factors impact the Brazilian yield curve? Evidence from a dynamic factor model (2019)
- Forecasting functional time series (2009)
- A probability-based stress test of Federal Reserve assets and income (2015)
- Kernel methods for pattern analysis (2004)
- Interest rate models: an introduction (2004)
- Descriptive Bond-Yield and Forward-Rate Models for the British Government Securities’ Market (1998)
- Stability of models for the term structure of interest rates with application to german market data (2001)
- The F.T.-Actuaries fixed interest indices (1978)
- Multivariate functional-coefficient regression models for nonlinear vector time series data (2014)
- The dynamics of economic functions: modeling and forecasting the yield curve (2008)
- Everything you always wanted to know about multiple interest rate curve bootstrapping but were afraid to ask (2013)
- The yield curve and predicting recessions (2006)
- The predictive power of the yield curve across countries and time (2015)
- An arbitrage-free generalized Nelson-Siegel term structure model (2009)
- An Analysis of the Ultra Long-Term Yields (2011)
- Empirical analysis and forecasting of multiple yield curves (2020)
- Optimal bond portfolios with fixed time to maturity (2013)
- Financial big data solutions for state space panel regression in interest rate dynamics (2018)
- Valuation of life insurance products under stochastic interest rates (2008)
- Market value of life insurance contracts under stochastic interest rates and default risk (2005)
- Optimal investment, consumption and life insurance purchase with learning about return predictability (2023)
- Optimal consumption, portfolio, and life insurance policies under interest rate and inflation risks (2017)
- Robust optimal investment strategy for an AAM of DC pension plans with stochastic interest rate and stochastic volatility (2018)
- Valuation of general GMWB annuities in a low interest rate environment (2023)
- Analyzing the interest rate risk of equity-indexed annuities via scenario matrices (2024)
- Introduction to Fixed Income Markets and Bonds (to appear)
- Yield curve modeling and forecasting: the dynamic Nelson-Siegel approach (2013)
- NMOF: Numerical methods and optimization in finance (2016) — link
- YieldCurve: Modelling and estimation of the yield curve (2010) — link
- A note on the Nelson–Siegel family (1999)
0 of 50 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.