Design a recommender system: they read your resume

Goodreads is a Social Web site about books. They need a recommender system. Thus, they issued a challenge: design their recommendation engine, and they will read your resume. I suppose this is the poor man’s version of the Netflix challenge.

There is nothing wrong with the challenge, but I wish the current Goodreads engineers would publish their own recommender system. How hard can it be to do item-based analysis?

Update: Students at Stanford built and tested a recommender system for Goodreads.

Published by

Daniel Lemire

A computer science professor at the University of Quebec (TELUQ).

3 thoughts on “Design a recommender system: they read your resume”

  1. I read that more as an interview question – and I believe such a question would be effective.

    ITA has some crazy good puzzles; Google’s also used them.

    It isn’t a terribly difficult challenge; anyone that’s picked up Programming Collective Intelligence should be able to give a decent answer. Finding those few people that do read books, however, is actually quite difficult.

    Reply

  3. This sounds like a very clever commercial proposal. They get the solution free and could amalgamate the best of several ideas submitted. Quite an education for those who loose out.

    Reply

Leave a Reply

Your email address will not be published.

To create code blocks or other preformatted text, indent by four spaces:

    This will be displayed in a monospaced font. The first four 
    spaces will be stripped off, but all other whitespace
    will be preserved.
    
    Markdown is turned off in code blocks:
     [This is not a link](http://example.com)

To create not a block, but an inline code span, use backticks: 

Here is some inline `code`.

For more help see http://daringfireball.net/projects/markdown/syntax

Or, you can subscribe without commenting.

You may subscribe to this blog by email.