Matthew W.

Location:

London

Member since:

February 4, 2012

What are your areas of interest?

Not currently working on them (am doing an MSc at the moment) but have dabbled with recommender systems in the past, in particular worked on a ratings-based music recommender. Some areas in which I'm interested in following progress: - Interactive / user-guided recommendation systems allowing for sensitivity to mood - Hybrids of social and data-driven approaches to recommendations - The role of serendipity and avoiding overly conservative "try some more of the same" recommendations while still applying some intelligence to the task. Suggest something which challenges me or pushes my boundaries a bit, but which you still have some basis for recommending. - The problem of bland "averaged-out" recommendations in multi-modal preference spaces. Instead identify my preference clusters and help me explore them separately For Bayesians, my analogy is: I don't want a MAP estimate of "music I'll like", I want a good sample from the posterior, which is multi-modal :)

Introduction

Mathematician by training, software engineer by trade, now doing an MSc in Computational Statistics and Machine Learning. Interested in commercial applications, engineering challenges and research. Ideal job: chief scientist at data-driven startup


Our Sponsors

  • idio

    Meeting space, publicity & technology services

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy