Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Sky - Recommender Systems

Sky - Recommender Systems

Sky Research and Development (R&D). Keywords: content analysis, social recommendations, collaborative filtering

Federico Cargnelutti

July 12, 2009
Tweet

More Decks by Federico Cargnelutti

Other Decks in Technology

Transcript

  1. Recommender Systems
    Federico Cargnelutti / BSkyB R&D

    View full-size slide

  2. The goal of a recommender system is to predict the
    degree to which a user will like or dislike a set of items
    such as movies or TV shows

    View full-size slide

  3. Recommender Systems
    Most recommender systems use a combination of different
    approaches, but broadly speaking there are three different methods
    that can be used:
    Content analysis
    and extraction of common patterns
    Social recommendations
    based on personal choices from other people
    Collaborative filtering
    of different users behaviour, preferences, and ratings

    View full-size slide

  4. Content-based
    Content-based recommenders use features such as the genre, cast
    and age of the show as attributes for a learning system. However,
    such features are only weakly predictive of whether viewers will like
    the show.
    In the TV world, the only content-analysis technologies available to
    date rely on the metadata associated with the programmes.
    The recommendations are only as good as the metadata.

    View full-size slide

  5. Social Recommendations
    Social-networking technologies allow for a new level of
    sophistication whereby users can easily receive recommendations
    based on the shows that other people within their social network
    have ranked highly.
    Social recommendations provide a more personal level of
    recommendations.
    The advantage of social recommendations is that because they have
    a high degree of personal relevance they are typically well received,
    with the disadvantage being that the suggested shows tend to
    cluster around a few well known or cult-interest programmes.

    View full-size slide

  6. Collaborative filtering
    Collaborative filter methods are based on collecting and analysing a
    large amount of information on users’ behaviour, activity or
    preferences and predicting what users will like based on their
    similarity to other users.
    Passive filtering
    Provides recommendations based on activity without explicitly
    asking the users’ permission (e.g. Amazon).
    Active filtering
    Uses the information provided by the user as the basis for
    recommendations (e.g. Netflix).

    View full-size slide

  7. Collaborative filtering
    Collaborative filtering systems can be categorized along the
    following major dimensions:
    User-user or item-item systems
    In user-user systems, correlations (or similarities or distances) are
    computed between users. In item-item systems metrics are computed
    between items (e.g. shows or movies).
    Form of the learned model
    Most collaborative filtering systems to date have used k-nearest
    neighbour models in user-user space. However there has been work
    using other model forms such as Bayesian networks, decision trees,
    cluster models and factor analysis.

    View full-size slide

  8. Collaborative filtering
    Similarity or distance function
    Memory-based systems and some others need to define a distance
    metric between pairs of items or users. The most popular and one of
    the most effective measures used to date has been the simple and
    obvious Pearson product moment correlation coefficient (PMCC).
    Combination function
    Having defined a similarity metric between pairs of users or items, the
    system needs to make recommendations for the active user for an
    unrated item. Memory-based systems typically use the k-nearest
    neighbour formula.

    View full-size slide

  9. Collaborative filtering
    User tasks for which collaborative filtering is useful
    1. Help me find new items I might like.
    2. Advise me on a particular item.
    3. Help me find a user I might like.
    4. Help our group find something new that we might like.
    5. Help me find a mixture of "new" and "old" items.
    6. Help me with tasks that are specific to this domain.

    View full-size slide

  10. Collaborative filtering
    Google’s PageRank mechanism is possible in the web because
    pages are linked to each other, but for TV we need to find another
    approach to relevance that will allow us to prioritise the most
    appropriate programming ahead of less relevant items.

    View full-size slide

  11. What makes a good recommendation system?

    View full-size slide

  12. The best algorithms take into account each of these factors:
    1. Programme Information
    2. Scheduling
    3. Channel
    4. Popularity
    5. Viewer behaviour
    6. Number of repeats and episodes

    View full-size slide

  13. What else makes a good recommendation system?
    • Transparency: Explain how the system works.
    • Scrutability: Allow users to tell the system it is wrong.
    • Trust: Increase users confidence in the system.
    • Persuasiveness: Convince users to try or buy.
    • Effectiveness: Help users make good decisions.
    • Satisfaction: Make the use of the system fun.

    View full-size slide

  14. Challenges
    The difficulty in implementing recommendations is that different
    users have different tastes and opinions about which television
    programmes they prefer.

    View full-size slide

  15. Challenges
    Quality
    A substantial portion of the shows that are recommended to the user
    should be shows that they would like to watch, or at least might find
    interesting.
    Transparency
    It should be clear to the user why they have been recommended
    certain shows so that if they have been recommended a show they
    don’t like they can at least understand why.

    View full-size slide

  16. Challenges
    User feedback
    People are fanatical about television programmes and if they are being
    recommended a show that they don’t like they should have an
    immediate way to say that they don’t like it and subsequently never
    have it recommended again.
    Driving take-up
    The recommendations needs to drive the take up of the shows that
    they are recommending. This can only be measured by monitoring the
    shows that are recommended and seeing how user behaviours change.

    View full-size slide

  17. TiVo Recommendation Engine
    • Every show in the TiVo universe has a unique identifying series
    ID assigned by Tribune Media Services (TMS).
    • Shows come in two types: movies and series which are recurring
    programs such as 'Friends'.
    • A series consists of a set of episodes. All episodes of a series
    have the same series ID.
    • Prediction is made at the series level so TiVo does not currently
    try to predict whether you will like one episode more than
    another.

    View full-size slide

  18. TiVo Recommendation Engine
    The flow of data starts with a user rating a show.
    There are two types of rating:
    1. Explicit feedback: The viewer can use the thumbs-up and
    thumbs-down buttons on the TiVo remote control to indicate if she
    likes the show.
    2. Implicit feedback: Since various previous collaborative filtering
    systems have noted that users are very unlikely to volunteer explicit
    feedback, in order to get sufficient data the only user action that
    results in an implicit rating happens when the user choose to record
    a previously unrated show.

    View full-size slide

  19. TiVo Recommendation Engine
    The following sequence details the events leading to TiVo making a
    show suggestion for the viewer:
    1. Viewer feedback
    2. Transmit profile
    3. Anonymization
    4. Server-side computation
    5. Correlation download
    6. Client-side computation
    7. Suggestions list
    8. Inferred recordings

    View full-size slide

  20. Thank you. Questions?

    View full-size slide