MatrixNet is a machine learning algorithm developed by Yandex and widely used in all the company’s products. The algorithm is based on gradient enhancement and has been introduced since 2009.


Digital platforms: Windows, Android, IOS, Linux, MacOS

Versions: Cloud/On-Premise 


An important feature of this method is that it is robust to overtraining. This allows very many ranking factors to be taken into account – without increasing the number of assessors’ scores or fearing that the machine will find non-existent patterns.

CERN uses the algorithm to analyse and search the colossal output data generated by the Large Hadron Collider.