Using unsupervised learning to extract factors underlying Treasury yields

Researchers Zura Kakushadze from Quantigic Solutions and Willie Yu from the Centre for Computational Biology at Duke-NUS Medical School give explicit algorithms and source code for extracting factors underlying Treasury yields using unsupervised machine learning techniques, such as nonnegative matrix factorization (NMF) and statistically deterministic clustering.

NMF is a popular ML algorithm (used in computer vision, bioinformatics/computational biology, document classification, etc.), but is often misconstrued and misused. The researchers discuss how to properly apply NMF to Treasury yields. They analyze the factors based on NMF and clustering and their interpretation, and discuss their implications for forecasting Treasury yields in the context of out-of-sample ML stability issues.

Read the paper

Related Posts

Previous Post
Broadridge survey: dismal success rates for innovation projects as digitization pressure increasing
Next Post
Get the weekly SFM update – our May 15 newsletter is online

Fill out this field
Fill out this field
Please enter a valid email address.


Reset password

Create an account