Emerging Tech

Guessing shopper behavior online

Seattle-based Cleverset is bringing out a next-generation recommendation engine to figure out shopper behavior.

Seattle-based Cleverset is bringing out a next-generation recommendation engine to figure out shopper behavior.

An excerpt from Technology review:

Many systems just match products to people by looking at the products that others have bought. For instance, if you are looking at a blender, and people who bought the blender also bought a toaster oven, then the system would suggest a toaster oven to you. The problem here, says D'Ambrosio, is that all this analysis of purchases happens offline, and the system has no awareness of what a consumer is trying to accomplish at that specific point in time.

Cleverset's founder Bruce D'Ambrosio believes that a statistical relational model does the best job at taking in all factors into consideration, no matter how small, to drive the recommendations to the customer.

The relational model factors in the relation among several datasets pertaining to the customer while statistics are deployed to ascertain the importance of the relationships.

What's your experience with recommendations at several retailers? Has it worked for you?

2 comments
w2ktechman
w2ktechman

Personally, I do not mind these much. They are just recommendations and suggestions from what others have purchased. Once in a while, I find them at least entertaining, sometimes (but rarely) useful, and other times just plain not interested. But all in all, some sites are better than others with this (at least for me), I think that Amazon.coms setup is more useful on recommendations than other retail stores like Target. but then again it may be due to circumstances that I think so. When on Amazon, I am more likely browsing for things of interest, and have some time to browse. When on another site, it is usually to look up a few specific items for a price compare to see where to buy from.

pr.arun
pr.arun

How has been your experience with recommendations at several retailers. Has it worked for you?

Editor's Picks