You are here:  Home  >  Uncategorized  >  Current Article

Yandex Boosts Precision Ad Targeting; Machine-Learning Method MatrixNet Is Behind The Scenes

By   /  September 17, 2013  /  No Comments

Search engine Yandex said today that it’s boosting its precision-advertising audience targeting, and that the potential is there to increase clickthrough rates from banner ads by hundreds of percents.

To get there, the search engine vendor has enhanced its behavior analytics technology Crypta, which is based on its machine learning method MatrixNet and whose earliest history is in learning to tell gender and age groups from one another to show relevant ads. Now, all kinds of demographics are covered, and Crypta can find various patterns in a website visitor’s behavior and pair them with other visitors’ similar behavior to show targeted banner ads. Crypta, according to the company, continually keeps its knowledge updated by processing and updating information about virtually every Yandex user on a daily basis.

“Combined with the information about users’ actions on a website, provided by our website analytics tool Yandex.Metrica, the new targeting allows advertisers to show their ads to a very narrow audience – those who have already made a purchase on their website, for instance. Or, conversely, those who put an item in the basket, but didn’t pay for it,” Yandex writes in its blog about the new capability. The look-alike targeting, as Yandex calls it, increased clickthrough rates on banner ads from clothing company Quelle by 300 percent in field tests.

Yandex says the feature is useable by any website owner with at least 15,000 visitors per week. That’s the minimal sample size for the technology to find patterns.

This is the first major feature announcement to come out of Yandex since the death of its co-founder and Chief Technology Officer, Ilya Segalovich. Segalovich in July. Late in August, the company announced the winners of its  open championship in competitive programming, Yandex.Algorithm, that involved more than 3,000 competitors from 84 countries trying to solve algorithmic problems in timed events..

About the author

Jennifer Zaino is a New York-based freelance writer specializing in business and technology journalism. She has been an executive editor at leading technology publications, including InformationWeek, where she spearheaded an award-winning news section, and Network Computing, where she helped develop online content strategies including review exclusives and analyst reports. Her freelance credentials include being a regular contributor of original content to The Semantic Web Blog; acting as a contributing writer to RFID Journal; and serving as executive editor at the Smart Architect Smart Enterprise Exchange group. Her work also has appeared in publications and on web sites including EdTech (K-12 and Higher Ed), Ingram Micro Channel Advisor, The CMO Site, and Federal Computer Week.

You might also like...

Nov 13 DataEd Webinar: Data Architecture vs Data Modeling

Read More →