Lotame

In his blog post over at GigaOm entitled “One Size Doesn’t Fit All When It Comes To Online Recommendations,” Darren Vengroff writes about 4 different product recommendations approaches, all deeply rooted in the smart use of data. This is very similar to some of the processes that can be employed when it comes to making decisions about which advertisement to show, and whom to show it to, with the aid of a data driven ad targeting platform:

• Segmentation, which divides users into groups based on characteristics like age, gender, and geographic location;
• Collaboration, which starts with an individual and attempts to locate others like them;
• Personalization, which relies on a user’s prior actions to determine what they are likely to do next; and
• Similarity, which starts with products, rather than users, and models relationships between them to drive recommendations.

In our business at Lotame, we have found that ad campaigns don’t have to be reliant on a single approach, and at times it may be best to combine different approaches simultaneously. Additionally, we have found that other approaches to use data that revolve around some of the unique social data that Lotame collects.

Darren is chief scientist at richrelevance. Previously, Darren was CTO and co-founder of Pelago, principal engineer at Amazon.com, and a vice president at Goldman Sachs. The entire article, with deeper definitions of each of the four approaches, can be found here.

Related articles by Zemanta

• One Size Doesn’t Fit All When It Comes To Online Recommendations (gigaom.com)

Tags: Darren Vengroff, Data, GigaOm, Marketing, recommendation, richrelevence, Targeting

This entry was posted on Wednesday, May 27th, 2009 at 7:04 am and is filed under Data. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.