Machine Learning for Yield Curve Feature Extraction: Application to\n Illiquid Corporate Bonds

2018/11/22 by Greg Kirczenow, Masoud Hashemi, Kirczenow, Greg +5
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #FOS: Computer and information sciences #FOS: Economics and business #Financial Markets and Investment Strategies #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Finance (q-fin.ST) #Stock Market Forecasting Methods

paper · pdf · doi:10.48550/arxiv.1812.01102

openalex publication_date 2018/11/22 · openalex created_date 2022/08/01 · openalex updated_date 2026/07/28

Abstract

This paper studies an application of machine learning in extracting features\nfrom the historical market implied corporate bond yields. We consider an\nexample of a hypothetical illiquid fixed income market. After choosing a\nsurrogate liquid market, we apply the Denoising Autoencoder (DAE) algorithm to\nlearn the features of the missing yield parameters from the historical data of\nthe instruments traded in the chosen liquid market. The DAE algorithm is then\nchallenged by two "point-in-time" inpainting algorithms taken from the image\nprocessing and computer vision domain. It is observed that, when tested on\nunobserved rate surfaces, the DAE algorithm exhibits superior performance\nthanks to the features it has learned from the historical shapes of yield\ncurves.\n

Related

• Machine Learning for Yield Curve Feature Extraction: Application to Illiquid Corporate Bonds (Preliminary Draft)
• Machine learning for multiple yield curve markets: fast calibration in the Gaussian affine framework
• Why Existing Machine Learning Methods Fails At Extracting the Information of Future Returns Out of Historical Sctock Prices : the Curve-Shape-Feature and Non-Curve-Shape-Feature Modes
• A Statistical Machine Learning Approach to Yield Curve Forecasting
• Machine Learning and the Yield Curve: Tree-Based Macroeconomic Regime Switching