Model Interpretability (or Why have you sent me another marketing offer?)

Add to your list(s) Download to your calendar using vCal

• Ben Houghton -- Head of Data Science for Barclays Payments
• Thursday 24 October 2019, 13:00-14:30
• Kavli Large Meeting Room, Kavli Building.

If you have a question about this talk, please contact James Fergusson.

As more complex models are being adopted within the financial sector, and “deep learning” is becoming the norm, Machine Learning practitioners have to pay closer and closer attention to the inner workings of their models, particularly in a heavily regulated environment such as Financial Services. In this talk, Ben Houghton (Head of Data Science, Barclays Payments) will discuss the importance of model interpretability, the techniques which can be used to help explain models and provide some real world examples of where model interpretability has played an important part.

This talk is part of the Data Intensive Science Seminar Series series.

This talk is included in these lists:

• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Combined External Astrophysics Talks DAMTP
• Cosmology, Astrophysics and General Relativity
• Institute of Astronomy Extra Talks
• Institute of Astronomy Talk Lists
• Interested Talks
• Kavli Large Meeting Room, Kavli Building
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.