Friday, July 20, 2012

EMI's Million Interview Dataset

This weekend marks the first in a series of community events, conferences and competitions taking place as part of a collaborative project between EMI and the non-profit organization Data Science London.

EMI has embarked on a MASSIVE market research initiative called the EMI Million Interview Dataset, aiming to log interviews with one-million music fans across 25 countries and detail their music-related interests, awareness and tendencies. In an effort to "radically transform analysis and insight in the music industry, improving the understanding of how artists and their fans connect to the benefit of music lovers everywhere" (source), EMI has opted to make sub-sets of this data available to the public.

The Music Data Science Hackathon is a 24-hour event challenging data science programmers and music geeks "to design an algorithm that combines users’ (a) demographics, (b) artist and track ratings, (c) answers to questions about their preferences for music, and (d) words that they use to describe EMI artists in order to predict how much they like tracks they have just heard." The competition will take place through the web platform Kaggle.

Elsewhere digital media strategist Mark Mulligan (former Vice President and Research Director at Jupiter Research and then Forrester Research) has done his own analysis of global streaming music adoption using parts of the EMI Million Interview Dataset, allowing him to present some very interesting statistics.

Read a summary of Mark Mulligan's analysis on his blog:

We've also posted his full report for online viewing:

No comments:

Post a Comment