Scott Lundberg, Microsoft Research - Explainable Machine Learning with Shapley Values -

This session was recorded in NYC on October 22nd, 2019.
Slides from the session can be viewed here: www.slideshare...
Explainable Machine Learning with Shapley Values
Shapley values are popular approach for explaining predictions made by complex machine learning models. In this talk I will discuss what problems Shapley values solve, an intuitive presentation of what they mean, and examples of how they can be used through the ‘shap’ python package.
Bio: I am a senior researcher at Microsoft Research. Before joining Microsoft, I did my Ph.D. studies at the Paul G. Allen School of Computer Science & Engineering of the University of Washington working with Su-In Lee. My work focuses on explainable artificial intelligence and its application to problems in medicine and healthcare. This has led to the development of broadly applicable methods and tools for interpreting complex machine learning models that are now used in banking, logistics, sports, manufacturing, cloud services, economics, and many other areas.

[@julianocamargo6674]

Great presentation, thanks!

[@abdelbaki8625]

i dont understand how calculate shap value

[@Malbao14]

I have a question that I'm facing today. When seeing with shap that you model does not behave like you want it to (like in 14:30 in the video), how can we force this change on the model?

[@naveen3046]

Hi sir, I like to share my opinion. This problem is related to our model. So It can be solved by focusing on the data set that we have, collecting more data relevant to that feature, we need to teach our model how to analyze that feature, Changing the model may help. My opinion is that this like problems are relevant to our data set, and model. I too experienced this problem, then I collected data which mainly focus on those features and then designed my model again. It helped little bit to solve. Thank you