Lunch & Learn “Model comparison based on the strength of dependence between responses and their predictions”
We are pleased to announce that our second Lunch & Learn of the year will take place on October 26, 2021 from 12:30 to 13:30.
It will be given in French using materials in English. It's completely free and open to everyone!
Modern data science tools are effective to produce predictions that strongly correlate with responses. Model comparison can therefore be based on the strength of dependence between responses and their predictions. Positive expectation dependence turns out to be attractive in that respect.
The present L&L proposes an effective testing procedure for this dependence concept and applies it to compare two models. Empirical illustrations using insurance loss data demonstrate the relevance of the approach for model selection in supervised learning.
Detralytics Learning Team