Recommender systems and The Long Tail

The introduction of TheLong Tail by Chris Anderson is available online! Anderson describes how recommender systems help you ‘navigate’ the long tail. He then lists (context-related, time-related) problems of music recommender systems:

1) They tend to run out of suggestions pretty quickly as you dig deeper into a niche, where there may
be few other people whose taste and preferences can be measured. Plus, many kinds of recommendations tend
to be better for one genre than for another—rock recommendations aren’t useful for classical and vice versa. In the old hit-driven model, one size fit all. In this new model, where niches and sub-niches are abundant, there’s a need for specialization.

2) Even where a service can provide good suggestions and encourage you to explore a genre new to you, the advice often
stays the same over time. Come back a month later, after you’ve heard all the recommendations, and they’re probably pretty much as they were. … You’ll need another kind of filter to take you to your next stop on your exploration.

Points worthy of further research ;-)

5 Responses to “Recommender systems and The Long Tail”

  1. mike says:

    With regard to the second point, it might be interesting to find out who bought the books I liked a month before I did, then find out what they bought this month.

  2. That´s right. I guess it may be well worth doing so by considering recently released items only.

  3. neal says:

    Or, rather than only recently released items, maybe the recommendation system should take into account what recommendations it has already given you? (and, whether you acted on those recommendations or not?)

  4. Considering whether one acted upon the recommendations she received is a good idea. But would that address point 2?

  5. [...] previous posts we were discussing the long-tailed characteristic of music, books, and other physical items. It now [...]