Problems adopting TimeSHAP in an attribution model about timeshap HOT 2 CLOSED

Hello Antonio,

1. Although we did not specifically test TimeSHAP applied to regression, TimeSHAP is implemented on top of KernelSHAP which works for regression. I do not see a reason on why TimeSHAP would not be applicable to regression where the range of scores are not between 0 and 1. In case you test this, we would appreciate the feedback, and in case you have an example we would be happy to add it to our examples.
2. In our examples we use a fixed sequence length only due to all sequences of the dataset being the same length. TimeSHAP explains one sequence at a time, and the sequence length is not a factor for TimeSHAP.
3. According to the game theory of the Shapley Values, the calculated explanations are a fair distribution of the model score across the considered features (and events/cells in TimeSHAP). In the application of KernelSHAP and consequently of TimeSHAP, the difference between the instance score and the baseline score is distributed fairly across the considered axis, and therefore, their explanations can be interpreted quantitatively. An intuitive example follows: Given a feature A with value 20, with a "background" (uninformative) value of 10; If the Shapley value of A is 0.2, that means that the predicted score will be 0.2 higher if A=20 than if A=10; or f(A=20) = f(A=10) + 0.2.

Let me know if you have any further questions

from timeshap.

Closed this issue due to inactivity. If you have any further questions feel free to re-open the issue or create a new one

from timeshap.