TimeSHAP on regression sequence model about timeshap HOT 2 CLOSED

Hello @danhoonlee

From what you describe, TimeSHAP can work in your use case. If you want explanations for each of the checkups, you can use TimeSHAP to explain each checkup individually given their respective previous events.

Regarding the error message, changing the baseline sequence is not a classification specific case although it is more direct in that domain. You can try different baseline sequences that suit your domain to obtain different results.

Regarding the option "skipping the pruning algorithm", I have double checked the code and it will not solve this error message (my previous answer in the commit is outdated). The value 0.1 is hard coded and it is more tailored for classification problems. If this problem persists, feel free to tell me and I can change this value to be user-defined in order to get around cases like this.

Note that currently, 0.1 is the minimum allowed difference between the explained sequence and the baseline, which represents the budget that TimeSHAP will have to distribute among the explained axis (event/feature/cell). If this value is too small, the explanations will be very small also.

If you have any further questions, don't hesitate to contact us.

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.