Techcombank: Ushering Personalized Banking for Millions of Customers

Overview

Techcombank, Vietnam's largest private financial institution with 315 branches serving over 15.3 million customers, adopted the Databricks Data + AI Platform to unify data from disparate on-premises databases and a legacy data warehouse. Central to the initiative is 'Customer Brain,' a customer-360 tool centralizing customer data for targeted marketing, and the Lead Allocation Curated Engine (LACE), which uses AI insights to prioritize and assign sales leads. Techcombank built machine learning models for fraud detection and credit risk management, using an enterprise feature store with over 7,500 features and more than 100 ML risk models to manage a credit lifecycle handling a twentyfold increase in retail credit applications. MLOps on Databricks with MLflow cut model implementation from months to weeks. The bank is developing an internal RAG-based chatbot, Smartie, built on Databricks AI Search, and piloting AI/BI Genie for natural-language data queries. The platform has over 1,000 active users bank-wide.

The challenge

Techcombank's data landscape consisted of numerous on-premises databases and a legacy data warehouse, creating a steep learning curve and hindering collaboration among teams; the massive volume of transaction data added complexity and slowed decision-making; governance was challenging as users generated their own datasets in various areas, complicating access and security management; and data teams often had to manually manipulate data in Excel to resolve discrepancies.

The solution

Techcombank onboarded the Databricks Data + AI Platform to unify intelligence from various systems. Central to the initiative is 'Customer Brain,' a customer-360 tool centralizing customer data for targeted marketing and personalized offerings that also acts as an omnichannel orchestrator, and the Lead Allocation Curated Engine (LACE), which aggregates customer profiles and behaviors to equip relationship managers with enriched data and AI-scored, prioritized leads. The bank also built machine learning models for fraud detection and credit risk management using an enterprise feature store with over 7,500 features and more than 100 ML risk models, implemented the Geosense tool for merchant network expansion, applied graph analytics via GraphFrame technology, and is developing an internal RAG-based chatbot called Smartie built on Databricks AI Search while piloting AI/BI Genie for natural-language data queries.

Reported business value

The platform has more than 1,000 active users bank-wide. Techcombank has managed a twentyfold increase in credit applications from retail clients and a threefold increase from corporate clients. MLOps on Databricks with MLflow has fast-tracked model implementation from what previously took months down to weeks.