RussiaFinance and insurance2025 – ongoingMTS Bank
Predictive service scenarios and machine learning in scoring and risk
MTS Bank reported 700 million rubles of 2025 savings from predictive service scenarios and risk models
Problem
The bank wanted to lower the cost of customer service operations, collections and fraud control.
Approach
MTS Bank, a subsidiary of MTS, used 250 predictive scenarios in service and machine learning models for risk analysis, credit scoring and customer value. About 200 employees used an AI coding assistant. A personalization model and AI agents for routine tasks were pilot or planned.
Results
Takeaway
The bank did not say how it measured the savings. The 2.5 billion ruble three-year effect and the move from 40% to 60% automation are forecasts.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Customer serviceFinance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
InvestFuture, citing RIA Novosti, reports MTS Bank's AI figures. The bank said it saved 500 million rubles in service and 200 million rubles in collections and antifraud in 2025. It forecast more than 2.5 billion rubles over three years.
Full details are in the original sources.
