Banking Transformation: A Central Platform for Enterprise-Class Automated Analytics

23 May 2025

Client:

A prominent European banking institution providing comprehensive financial services across 40+ countries, specializing in retail banking, corporate financing, and innovative digital banking solutions.

Industry: Finance

Department: Data Mining, CRM Support & Marketing Automation

Problem:

Customer-centric analytics requires C360 data model (thousands of customer-centric parameters)
Propensity to buy (ML) models too slow
SAS and Oracle-based analytics platforms were not scalable

Solution:

Implementation of Azure platform in accordance with CAF and WAF
A modern data platform based on Databricks service, implementing proprietary solutions Ingestion Framework, Feature Store, and Model Factory.
Implementation of a complete MLOps framework – Mlflow
Full configuration of ISO 27001

Business impact:

Dynamically scale computing resources for Customer 360 calculations
Fast model creation and serving mechanism (deploy new models in hours rather than weeks)
Single source of reliable information about customer data

Enable ML teams to use highly scalable Databricks clusters cost-effectively

Read previous

Use All Spark Workers' CPUs to read from a REST API

2025-04-02 12:55:12

Spark driver and workers: Recently, we explored how to create our data sources in Spark by using syntax like: spark.read.format("myrestdatasource") to read from a REST API. Now, we’ll examine how to use all worker CPUs to read simultaneously from a REST API. Key idea Spark will read in parallel if we define multiple […]