Brand Analytics: Fault Detector

The main articles are:

• Neural networks (neural networks)
• Big Data
• Digital Dashboard

2022: Failure Detector Service Launch

The company, Brand Analytics a resident, Skolkovo Foundation prepared and launched Russian the Failure Detector service. This was reported by the press service of the Skolkovo Foundation on June 14, 2022. This service already at the start shows a picture of performance for more than 100 well-known services. In the observed pool mobile applications banks and delivery services,,, etc online stores transport infrastructure.

The quality of life in the country is largely determined by the efficiency of the most popular services and services. The news that one of the large banks had problems with the mobile application is federal news regarding the majority of citizens. Therefore, the ability to see in one place a picture of the availability and failures of mass services will allow companies to reduce their downtime and improve the quality of life. Until recently, this problem was solved by the foreign service DownDetector (DD). However, in the spring of 2022, he stopped working in Russia.

The main feature of this service is its focus on the Russian market, that is, the specifics are taken into account and the specific resources of our country are monitored. The solution will be in demand both by users and partners who can use data and analytics in their work, commented on Oksana Ulyankova, Head of Promising Projects in the Field of Information Security of the Skolkovo Foundation Information Technology Cluster.

For 2022, there was a situation when companies more often learn about the malfunctions of their services from users than from internal services. People share emotions on social networks due to problems with the service, counting on the support and advice of friends. However, in order to find such information and understand what is happening, it is necessary to analyze a very large data stream and use real-time neural networks for this. The "failure detector" can do this and warns companies about their problems, noted Natalya Sokolova, CEO Brand Analytics.

As noted in Brand Analytics, the failure detector is not an analogue of DownDetector (DD). DD could only analyze Twitter. The failure detector analyzes all sources of social media and, first of all, the largest - Russian social networks VKontakte and Odnoklassniki, as well as Telegram. Moreover, many of the well-known services are partners of Brand Analytics and use the analytics system of the same name in their work. Fault detection technology has been running for several years inside the Brand Analytics system and has proven to be effective in practice. Now it has formed the basis of a public service. Further development of the Detector will necessarily take into account the reverse communication from both partners and directly from users of social networks.

To identify problems in the work of various services, the Detector neural network analyzes over 40 million Russian-language user messages every day in various sources of social media and finds information about failures. The detector represents a set of dashboards, each of which belongs to a separate service. The dashboard of each service shows its status (available, there is a probability of failure, failure), the dynamics of failures "through the eyes of users," identified problems, foci of failures on the thermal map of the world and a message feed that helps to understand the situation.

Improving the quality and availability of services used by millions of people is the result targeted by the Failure Detector. The submitted version of the service is the first, but not the final one. Brand Analytics plans to further develop the Detector.