- Data Jujitsu — new O’Reilly Radar report by the wonderful DJ Patil about the exploration and problem solving part of data science. Me gusta.
- Style Finder: Fine-Grained Clothing Style Recognition and Retrieval (PDF) — eBay labs machine learning, featuring the wonderful phrase “Women’s Fashion: Coat dataset”.
- Amazon’s Drug Dealer Shopping List — reinforcing recommendations surface unexpected patterns …
- Migrating Virtual Machines from Amazon EC2 to Google Compute Engine — if you want the big players fighting for your business, you should ensure you have portability.
Patrick Brown on the Goodreads recommendation engine and fine-tuning discoverability.
The Goodreads recommendation engine has been in development for six years. In this podcast, Patrick Brown, community manager at Goodreads, talks about that development process and how the algorithm works.
Mark Johnson on what sets Zite apart and how CNN ownership will affect the company.
Zite CEO Mark Johnson recently sat down with us to talk about his company, how his recommendation engine works and how CNN is welcoming Zite into its family.
A new kind of book recommendation appears at Goodreads and HTML5 had a very big week in the media world.
Goodreads put its Discovereads purchase to good use. Also, Hearst and The Boston Globe are doubling down on HTML5.
This gem from Whimsley makes the point – with extensive statistical modeling supporting the argument – that our algorithm-obsessed, long tail merchants are actually depleting the overall choice pool despite the fact that as individuals we may be experiencing a sense of more choice through recommendations engines. “Online merchants such as Amazon, iTunes and Netflix may stock more items than your local book, CD, or video store, but they are no friend to “niche culture”. Internet sharing mechanisms such as YouTube and Google PageRank, which distil the clicks of millions of people into recommendations, may also be promoting an online monoculture.”