To help combat unregulated financial activity, the service finds web pages related to microfinance and consumer loans, and, using Yandex’s MatrixNet algorithm, evaluates the legality of financial organisations.

By using keyword analysis across a search index owned by parent company, Yandex, the Yandex Data Factory has identified seven million web pages related to finance topics. In order to help build the specialised search model, Bank of Russia experts sorted through and categorised 8,000 web pages.

Once the model was trained and put to work, a total of 2,500 suspicious organisations were exposed. The algorithm is successful in assigning a web page to its correct category in 71% of cases, while it correctly identifies if an organisation is licenced in 98% of cases. As a result, it is unlikely that potentially fraudulent organisations will be overlooked by officials.

Once identified, reports are automatically generated and sent to the Bank of Russia with details of the organisations pulled from the search – from licensed providers to those with terminated licenses, along with organisations which never owned a licence and those whose licencing status could not be identified.

With this information, employees from the Bank of Russia are then able to act and feedback on the classification for each website identified, helping the algorithm to learn and improve.

Alexander Khaytin, COO for Yandex Data Factory, presented the custom search model at a Bank of Russia advisory board session stating: "When it comes to consumer loans, illegal activity is rife and many people fall victims to scams. By using machine learning to locate these illegal organisations and reporting them to the Bank of Russia, we can go a long way towards preventing fraudulent activity."

Jane Zavalishina, CEO Yandex Data Factory: "Yandex Data Factory applies Yandex technologies to solve tasks for companies from different sectors – finance, healthcare, commerce etc. Cooperation with the Bank of Russia is another instance of Yandex technologies helping organisations across different industries."

Yandex Data Factory are the Machine Learning and data analytics experts that use data science to improve business’ operations, revenues and profitability. By building upon the real-time personalisation and predictive analytics technologies of its parent company Yandex, one of the largest internet businesses in Europe and Russia’s leading search engine, Yandex Data Factory helps clients improve their business through the exploitation of their own data.

Yandex Data Factory’s proven data science and technology continually analyses, tests, refines and reapplies thousands of hypotheses to the customers’ datasets to determine the best next course of action.

It offers tailored, scalable, SaaS-driven Machine Learning services to a wide variety of data-reliant verticals, such as retail, financial services, travel and telecoms, who wish to use their data for purposes such as improving personalisation, segmentation, churn prevention or fraud detection.

Yandex Data Factory has previously used its custom search capabilities to build an antibiotics research database for AstraZeneca, a global biopharmaceutical company. The project aimed to locate all scientific research papers relevant to a specific topic and collate into one database, ranking each paper in order of relevance.

Yandex Data Factory was founded in 2014 by Yandex and is headquartered in Amsterdam, operating throughout Europe.