SKLearn DT regressor - good enough score?

Question

SKLearn DT regressor - good enough score?

lte__

2020年7月12日 21:07

What constitutes as a "good enough" score for a Decision Tree Regressor? The .score() function gives us a general score about our model. This can be 1 if the model predicts all data with a 100% accuracy, and can be arbitrarily worse. If I understand correctly, a score of 0 means the prediction is quasi constant. But starting with what value can we say that the prediction is "usable" (i know this is ambiguous, but still). Is a score of 0.4-0.5 good enough to use the predictions in practice as opposed to not using any machine learning techniques?

Topic score decision-trees regression scikit-learn

Category Data Science

Brian Spiering · Accepted Answer · 2020年6月12日 19:48

1

Brian Spiering answered at 2020年6月12日 19:48

The quality of the score depends on the context of the project.

One approach is a model comparison approach. Define a baseline model. Then see if Decision Tree Regressor is better than the baseline.

SKLearn DT regressor - good enough score?

About