This article examines contemporary algorithmic approaches to multiparametric immunization of interest rate risk in a fixed-income portfolio, explicitly accounting for non-parallel shifts in the yield curve. Using the Nelson–Siegel framework, the bond-price sensitivities to the three primary factors—level, slope, and curvature—are characterized, and the traditional Duration and Duration–Convexity immunization strategies are reviewed. It is demonstrated that attempting to hedge all three factors simultaneously with classical techniques often yields extreme portfolio weights, excessive leverage, and poor out-of-sample performance. To overcome these limitations, we implement L¹ (Lasso) and L² (Ridge) regularization—subject to a strict overall leverage cap—on U.S. Treasury data. An empirical replication of a “retirement bond” (a pension-payment stream) shows that leverage-constrained Lasso strategies reduce the median absolute deviation of the funding ratio while also lowering turnover. These results confirm the hypothesis that regularization improves both the robustness and economic efficiency of interest-rate hedging for institutional investors with long-dated liabilities. The insights presented will interest financial-engineering researchers specializing in stochastic yield-curve modeling and optimal portfolio-management methods. Portfolio managers, institutional risk officers, and quantitative teams at hedge funds seeking to integrate high-frequency and machine-learning algorithms into their volatility-reduction workflows and to ensure stable returns amid changing market rates will also find practical guidance here.

algorithmic hedging, interest rate risk, regularization, Lasso

Mantilla-Garcia D. et al. Improving interest rate risk hedging strategies through regularization //Financial Analysts Journal. – 2022. – Vol. 78 (4). – pp. 18-36.

Martellini L., Milhau V. Advances in Retirement Investing. – Cambridge University Press, 2020. – pp. 1-10.

Martellini L., Milhau V., Mulvey J. Securing Replacement Income with Goal-Based Retirement Investing Strategies //The Journal of Retirement. – 2020. – Vol. 7 (4). – pp. 8-26.

Khatri C. A. Integration of Artificial Intelligence in Pricing and Hedging Strategies for Currency and Credit Derivatives: A Comprehensive Analysis of Exposure and Market Dynamics //Library of Progress-Library Science, Information Technology & Computer. – 2024. – Vol. 44 (3). – pp.1-9.

Gubareva M., Keddad B. Emerging markets financial sector debt: A Markov‐switching study of interest rate sensitivity //International Journal of Finance & Economics. – 2022. – Vol. 27 (4). – pp. 3851-3863.

Cherrat H., Prigent J. L. On the hedging of interest rate margins on bank demand deposits //Computational Economics. – 2023. – Vol. 62 (3). – pp. 935-967.

Pagnottoni P., Spelta A. Hedging global currency risk: A dynamic machine learning approach //Physica A: Statistical Mechanics and its Applications. – 2024. – Vol. 649. – pp. 1-9.