IBS Journal: The iconic monthly FinTech magazine

February 2020 issue out now! Subscribe now

Launching India FinTech Report 2020

Market sizing and forecast of Digital Lending, Payments, WealthTech & RegTech. Subscribe now

Leading Back Office Systems for Banks

In-depth Supplier Profiles and User Lists. Subscribe now

In-depth Banking Tech and FinTech Research

Over 300 research reports that's updated quarterly. Subscribe now

Sberbank creates a machine learning algorithm for sales campaigns

Anatoly Popov, Deputy Chairman of the Executive Board of Sberbank

Sberbank, the Russian banking and financial services company, has created a new model of machine learning- Auto ML, an algorithm that can create other models, according to Anatoly Popov, the Deputy Chairman of the Executive Board at Sberbank.

The algorithm created can reportedly, create other models which solve application tasks quicker than a human. This was proved in the first pilot held in January 2019, wherein,  Auto ML algorithms were used to create several baseline models (first versions) of Next BestAction class (targeting of sales campaigns). Auto ML optimizes the creation of a baseline model, whose quality is comparable and works 10-15 times faster than the manually developed ones. For example, as the bank stated- The algorithm produced forecasts that match the work of data scientists in terms of quality. At the same time, it managed to solve the task in 55 minutes against one to two days of human work.

This newly developed algorithm will be used for the sales campaigns for Sberbank’s corporate and investment business.

Anatoly Popov commented: “Introducing AI is one of the possibilities to increase the efficiency of all business processes at the bank. However, the creation of tens and thousands of models to cover all aspects of activity is an almost impossible task if data scientists and developers attempt to create and introduce models manually. That’s why we are introducing Auto ML, one of the most advanced approaches in the world to working with machine learning models. The algorithm system that quickly and independently creates application solutions on the basis of machine learning models.”

Recently, in a bid to boost digital banking, Russian lender Sberbank introduced consumer loans that cover processes from application to disbursal for individuals via mobile app, eliminating the need to visit a physical branch.

PJSC Sberbank is a state-owned Russian banking and financial services company headquartered in Moscow. The company was known as “Sberbank of Russia” until 2015. Sberbank has operations in several European and post-Soviet countries.

Related Posts