Hi
user
Admin Login:
Username:
Password:
Name:
Beyond the Black Box: Interpreting ML Models with SHAP
--client
pyohio
--show
pyohio_2025
--room orchid_west 15551 --force
Next: 10 From Data to Insights in Minutes: Accelerating Predictive Modelling (in Python) with AutoML
show more...
Marks
Author(s):
Avik Basu
Location
Ballroom A
Date
jul Sat 26
Days Raw Files
Start
14:06
First Raw Start
13:39
Duration
00:30:00
Offset
0:27:12
End
14:36
Last Raw End
15:09
Chapters
00:00
0:02:48
Total cuts_time
30 min.
https://www.pyohio.org/2025/program/talks/beyond-the-black-box
raw-playlist
raw-mp4-playlist
encoded-files-playlist
host
mp4
svg
png
assets
release.pdf
Beyond_the_Black_Box_Interpreting_ML_Models_with_SHAP.json
logs
Admin:
episode
episode list
cut list
raw files day
marks day
marks day
image_files
State:
---------
borked
edit
encode
push to queue
post
richard
review 1
email
review 2
make public
tweet
to-miror
conf
done
Locked:
clear this to unlock
Locked by:
user/process that locked.
Start:
initially scheduled time from master, adjusted to match reality
Duration:
length in hh:mm:ss
Name:
Video Title (shows in video search results)
Emails:
email(s) of the presenter(s)
Released:
has someone authorised pubication
Unknown
Yes
No
Normalise:
Channelcopy:
m=mono, 01=copy left to right, 10=right to left, 00=ignore.
Thumbnail:
filename.png
Description:
markdown
ML models behave as a black box in most scenarios. Model predicts or provides a certain output but it is very difficult to generate any actionable insights directly. This is mostly because we generally have no idea which features are contributing the most to the model behavior internally. SHAP provides a certain way to explain model predictions, and can act as an important tool in a data scientist’s toolbox. In this talk, we will begin by explaining to the audience the need for explainable ML models and why it is important to understand beyond what the model outputs. We will then briefly go over the mathematical intuition behind Shapley values and its origins from game theory. After that we will walk through a couple of case studies of tree based and neural network based models. We will be focusing on interpretation of SHAP through various plots using the shap library in Python. Finally, we will discuss the best practices for interpreting SHAP visualizations, handling large datasets, and common pitfalls to avoid.
Comment:
production notes
2025-07-26/13_39_45.ts
Apply:
13:39:45 - 14:06:57 ( 00:27:12 )
S:
13:39:45 -
E:
14:09:45
D:
00:30:00
(
End:
1632.0)
show more...
vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/orchid_west/2025-07-26/13_39_45.ts :start-time=00.0 --audio-desync=0
Raw File
Cut List
13:39:45
seconds: 0.0
Wall: 13:39:45
Duration
00:30:00
14:09:45
seconds: 1632.0
Wall: 14:06:57
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
2025-07-26/13_39_45.ts
Apply:
14:06:57 - 14:09:45 ( 00:02:48 )
S:
13:39:45 -
E:
14:09:45
D:
00:30:00
(
Start:
1632.0)
show more...
vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/orchid_west/2025-07-26/13_39_45.ts :start-time=01632.0 --audio-desync=0
Raw File
Cut List
13:39:45
seconds: 1632.0
Wall: 14:06:57
Duration
00:30:00
14:09:45
seconds: 0.0
Wall: 13:39:45
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
2025-07-26/14_09_45.ts
Apply:
14:09:45 - 14:37:49 ( 00:28:04 )
S:
14:09:45 -
E:
14:39:44
D:
00:29:59
(
End:
1684.0)
show more...
vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/orchid_west/2025-07-26/14_09_45.ts :start-time=00.0 --audio-desync=0
Raw File
Cut List
14:09:45
seconds: 0.0
Wall: 14:09:45
Duration
00:29:59
14:39:44
seconds: 1684.0
Wall: 14:37:49
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
2025-07-26/14_09_45.ts
Apply:
14:37:49 - 14:39:44 ( 00:01:55 )
S:
14:09:45 -
E:
14:39:44
D:
00:29:59
(
Start:
1684.0)
show more...
vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/orchid_west/2025-07-26/14_09_45.ts :start-time=01684.0 --audio-desync=0
Raw File
Cut List
14:09:45
seconds: 1684.0
Wall: 14:37:49
Duration
00:29:59
14:39:44
seconds: 0.0
Wall: 14:09:45
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
2025-07-26/14_39_45.ts
Apply:
14:39:45 - 14:50:59 ( 00:11:14 )
S:
14:39:45 -
E:
15:09:44
D:
00:29:59
(
End:
674.0)
show more...
vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/orchid_west/2025-07-26/14_39_45.ts :start-time=00.0 --audio-desync=0
Raw File
Cut List
14:39:45
seconds: 0.0
Wall: 14:39:45
Duration
00:29:59
15:09:44
seconds: 674.0
Wall: 14:50:59
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
2025-07-26/14_39_45.ts
Apply:
14:50:59 - 15:09:44 ( 00:18:45 )
S:
14:39:45 -
E:
15:09:44
D:
00:29:59
(
Start:
674.0)
show more...
vlc ~/Videos/veyepar/pyohio/pyohio_2025/dv/orchid_west/2025-07-26/14_39_45.ts :start-time=0674.0 --audio-desync=0
Raw File
Cut List
14:39:45
seconds: 674.0
Wall: 14:50:59
Duration
00:29:59
15:09:44
seconds: 0.0
Wall: 14:39:45
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
Rf filename:
root is .../show/dv/location/, example: 2013-03-13/13:13:30.dv
Sequence:
get this:
check and save to add this
2025-07-26/13_39_45.ts
2025-07-26/14_09_45.ts
2025-07-26/14_39_45.ts
Veyepar
Video Eyeball Processor and Review