You are here:  Home  >  Data Education  >  Current Article

Yandex Takes Its Machine Learning Smarts Into New Role as Business Services Provider

By   /  December 10, 2014  /  No Comments

yandex-logo (1)by Jennifer Zaino

Yandex is going beyond web search and into the enterprise. This week it announced a new venture, the Yandex Data Factory, which will apply its machine-learning products and algorithms – which power more than 70 percent of its own products and applications – to business’ Big Data issues.

Using a client’s pre-existing data, the press release notes, Yandex creates an algorithmic model, which it then applies to the client’s new data to predict what will happen next in various scenarios. “This is exactly what is happening every second on Yandex’s services when we personalize search suggestions, recommend music, recognize speech or images, or target ads,” the release notes.

The model cases for Yandex Data Factory include: churn prediction by running segmentation and micro-segmentation algorithms on the data to find patterns in customer behavior that indicate they’re heading for the exit or that possible fraud activity is underway; personalizing cross-sell and up-sell recommendations based on user profiles built upon the searches they made, links or ads they clicked, videos they watched, and other activities; using its speech-to-text technology to analyze call center or other support call speech streams and detect anomalies in interactions to drive employee interaction quality and improve skills.

It also uses history-based prediction technology and its own computer vision and image recognition technologies to enables businesses to analyze large volumes of images and videos to spot anomalies, find recurring objects or events, and other things that will help them assess conditions and assure productivity.

Yandex says that it is enabling all this in part through the creation of production-scale adaptations of well-known machine learning algorithms and methods (support vector machines, principle component analysis, Naïve Bayes, and Deep Neural Networks). But its key capabilities, it says, “stem from unique proprietary technologies, such as MatrixNet, Friendly Machine Learning (FML), Yandex Map-Reduce (YAMR), Real-Time Map-Reduce (RTMR) and [its big data storage and processing platform] Yandex Tables (YT).”

The company says it has in the last year run a number of pilot projects, with Yandex Data Factory helping a leading European bank increase sales by offering its products to customers whose behavior was similar to those who have already bought these products. “By applying MatrixNet to behavior data on a few million of the bank’s clients, we created a model that could predict net present value of communication of a product to a specific client via a specific channel. This model was then applied to the bank’s new data to generate personalised product recommendations for each client paired with communication channel and ranked by potential net profit value,” Yandex says.

It also enabled a road and traffic management agency to become 30 times more accurate in predicting accidents thanks to its machine-learning technologies and expertise in geolocation. “Using MatrixNet, we first trained predictive formulas on our own [user-generated content] information about almost 40,000 road accidents and 5 billion speed tracks minded over two and a half years, complemented by the information provided by the agency: traffic information, information about road conditions, weather information. These formulas were then applied to larger data sets and a predictive system for road traffic accidents was developed and deployed in the agency’s situation rooms,” according to Yandex.

Yandex also says that a mobile service provider used the Yandex Data Factory to target anonymous SIM card owners more precisely. Close to a couple of dozen other projects are also continuing worldwide.


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...

Case Study: Cox Automotive Solves Data Drift and ETL Challenges

Read More →