Credit Factor Investing with Machine Learning techniques
Friday 08 July 2022
The most common models to assess asset returns are a linear combination of risk factors. We have employed tree-based machine learning algorithms to capture nonlinearities and detect interaction effects among risk factors in the EUR and USD credit space. We have built a nonlinear credit pricing model and compared it to our baseline linear credit pricing model using error metrics on training and testing sets and during different periods. In-sample error metrics revealed the benefit of treebased regressions.
Working Paper - July 2022
Time to refocus on bonds - Rethinking portfolios after the great repricing
Inflation has risen to levels not seen in 40 years, leading to a repricing of financial markets this year, which has been particularly severe in the fixed income space.
Italy election: no major surprise from the polls, maybe positive for markets
Investment Talks - September 2022
ECB raises its rates and commits to do more in the next meetings