ThailandFinance and insurance2024 – ongoingTMBThanachart Bank
Delphi personalization engine for customer offers
TTB's Delphi engine raised highly targeted offers tenfold and doubled digital sales growth
Problem
TTB's on-premises systems limited personalized services to 500,000 customers. Batch processing left a two-day data lag and could not handle streaming data.
Approach
TTB moved its in-house Delphi Personalization Engine and more than 1,000 tables to a lakehouse on Azure Databricks. Delphi handles product recommendations, propensity scoring, fraud detection and customer engagement across channels. Real-time processing let the bank act on customer events as they happened.
Results
Takeaway
TTB rebuilt the data layer under an engine it already ran. The engine then reached the wider customer base it had been unable to serve.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Marketing and sales
- Innovation type
- Process innovation
- Adoption
- Built in-house
- Evidence
- Vendor case study
Sources
Source summaries
Databricks describes how TMBThanachart Bank moved its Delphi personalization engine to a lakehouse on Azure Databricks. It reports a tenfold rise in highly targeted offers, digital sales growing twice as fast, and 5.5 million customers reached with personalized products. The page also gives data-platform figures, which are not used here.
Full details are in the original sources.
