Static Artificial Neural Networks

Why netflix's recommendations are more interesting than amazon's

I have always found Netflix's recommendations to be more interesting than Amazon's.  When you buy a Bruce Willis movie on Amazon, they often recommend other Bruce Willis movies.  Netflix, on the other hand, is much more likely to suggest movies I wouldn't have thought of or even heard of.  Why is this?  

Generally recommendation systems can be tuned to simply please the user (emphasize overall popular items) or to wow users (emphasize less popular items).   I think the difference is due not to difference in expertise but difference in goals.  Amazon sells products and Netflix rents them (at least in the case of physical DVDs).  Amazon wants an algorithm that simply optimizes sales, and showing a popular item is more likely to lead to a sale.

Netflix has a different challenge.  They have an inventory of DVDs.  If everyone is renting the most popular movies, they have to stock tons of those movies, and the "long tail" movies sit idle in their warehouse.  They want an algorithm that gets people to go down the tail and watch movies that would otherwise go unwatched and therefore keeping more of their inventory in circulation.  Hence the algorithm is tuned to "going out on a limb, " making the recommendations more interesting.

Source: cdixon's posterous

You might also like:

Christopher Morse, Evolutionary Robotics, Fall 2011, University of Vermont, video 2.
Christopher Morse, Evolutionary Robotics, Fall 2011, University of Vermont, video 2.

Investment advice

2002-02-10 00:07:53 by dont

The residual effects of the Enron (ENE) debacle are slowly, but surely, beginning to PERMEATE the investment landscape. In many instances it is hard to know whether the secondary problems are critically severe, or just a case of paranoid investors overreacting to ghosts. In 1997, ENE was a rather ordinary gas distribution company trading at $20/share. In the 1998-2000 period, the stock rocketed to nearly $85/share, because of celebrious views about their on-line commodity trading capabilities, an 18,000-mile fiber-optic cable and ultimately, the perceived 'rewards' from the California electricity crisis. Management gradually succumbed to the temptation to artificially inflate earnings with artful 'financial engineering' techniques and, all the while, they piled up debt and preferred...

Sharemarket troubles bring economic outlook concerns  — ABC Online
LEIGH SALES, PRESENTER: A huge sell-off on the Australian share market today has wiped $23 billion from the value of local stocks as fears of a new global recession buffet world economies. The Australian spiral follows a similar slump on American …

Market wipes $8000 off household assets  — Perth Now
The energy and resources sector is leading losses on the share market today, with big mining stocks taking a hit. But Dr Oliver said this presented an opportunity for investors to pick up some cheap stocks. Mr Weston said shares in resources companies …

Profit forecast forces Qantas shares to all-time low  — ABC Online
GREG HOY: Blaming rising fuel prices and a deterioration in the global market driven by Europe's faultering economy, Qantas' announcement to the share market today suggested its international arm is expecting a fall in profit of some $450 million this …

Related posts:

  1. Tutorial on Artificial Neural Networks
  2. Fast Artificial Neural Networks
  3. STATISTICA Neural Networks
  4. Usage of Artificial Neural Networks