Feature construction (also known as constructive induction or attribute discovery) enriches data by adding derived features. These can enrich a data analysis pipeline by capturing relevant relationships within the data that downstream processes are otherwise unable to model or exploit. They may also support explainable AI by making relationships explicit that would otherwise be implicit and difficult to comprehend.
Our pioneering research demonstrated that feature construction can empower machine learning systems to construct more accurate models across a wide range of learning tasks.
Publications
[bibtex file=feature-construction.bib template=publist-norel format=my-format sort=year order=desc process_titles=0]