- 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.
"recommendations" entries
Four short links: 14 May 2014
Problem Solving, Fashion Mining, Surprising Recommendations, and Migrating Engines
The more you engage, the better the advice
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.
The search for serendipitous recommendations
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.
Publishing News: Goodreads chases the recommendation Holy Grail
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.
Strata Week: Cracking a book's genetic code
Decoding book DNA, parsing Wikipedia with WikiHadoop, and the rise of the "Data Civilization"
BookLamp and the Book Genome Project look to book DNA for smarter recommendations, sorting through Wikipedia's vast data dump gets easier thanks to WikiHadoop, and a timeline from WolframAlpha charts major milestones in data knowledge.
How online bookstores should get social
A social layer on book sites would help readers, retailers and publishers.
What if you could take the social aspects of brick-and-mortar bookstores and blend them with the convenience of online sales? Joe Wikert explains how an online social layer would benefit everyone involved in the publishing chain.
Three Paradoxes of the Internet Age – Part Two
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.”
Three Paradoxes of the Internet Age – Part One
In the circles that I travel the Internet is often breathlessly embraced as the herald of all things good; the bringer of increased choice, personal empowerment, social harmony… and the list goes on. And yet, as with any powerful technology, the truth of its consequences eludes such a singular and happy narrative. More access to information doesn’t bring people together, often it isolates us.