University of Cambridge > Talks.cam > Data Intensive Science Seminar Series > Unlocking the Power of Transfer Learning: Meeting the Challenge of Mobile App Predictions in Data-Scarce Environments

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Unlocking the Power of Transfer Learning: Meeting the Challenge of Mobile App Predictions in Data-Scarce Environments

Download to your calendar using vCal

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

We’ll explore the world of predictive modelling at Bending Spoons. In our suite of apps, each with distinct traits, accurate predictions on user renewals drive rapid app improvement and translate into increased profits. However, for some apps we don’t have sufficient data to make reliable predictions. Transfer learning is a technique that can allow predictive models to learn generic features of all apps, and fine-tune those models on the unique behaviour of each app. I’ll delve into the problems and potential solutions that empower us to acquire and rapidly scale new apps to their full potential.

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

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

FW11, William Gates Building. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon Seminar Room 8, Clinical School, Addenbrooke's hospital test

Other talks

The spread of environmental cost-benefit analysis in UK government, c.1966-1995: representing the public in the Anthropocene Director's Welcome Online Causal Inference Seminar Discussion II continued Group Work The elephant in the room: Machine Learning directly into physical models
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity