Bond return predictability: Macro factors and machine learning methods

Research output: Journal PublicationArticlepeer-review


We investigate the impact of macroeconomic variables on bond risk premia prediction via machine learning techniques. Based on Chinese treasury bonds from March 2006 to December 2022, we show that adding macroeconomic factors improves bond return forecasts and generates higher economic benets to investors. This is achieved when the nonlinear relationship between macroeconomic variables and bond returns is modeled via machine learning methods. Furthermore, the importance of macroeconomic determinants changes along the yield curve. Our study sheds new light on the information contained in macroeconomic variables for treasury bond valuation and highlights the importance of utilizing appropriate machine learning methods.
Original languageEnglish
Number of pages32
JournalEuropean Financial Management
Publication statusPublished - 12 Mar 2024


  • Chinese bond market
  • machine learning
  • unspanned macroeconomic information
  • yieldterm structure


Dive into the research topics of 'Bond return predictability: Macro factors and machine learning methods'. Together they form a unique fingerprint.

Cite this