Propensity-to-buy scoring of clients for consumer loans offers
Identifies customers with high-propensity scores
Added business value for 70% of client base
Effective for customers with no loan history
Project Brief
Creating a prediction propensity model aimed at identifying clients likely to take out consumer loan products and optimising campaign targeting.
Profinit’s propensity-to-buy model delivered added business value for almost 70% of our client base, including challenging segments like new and inactive customers.
Peter Baláži
Head of Credit Risk, Equa bank, a.s.
Project background
Equa bank – a fast-growing Czech challenger bank and long-term Profinit partner – asked our team to create a propensity-to-buy scoring model (hereafter “propensity model”) that would help identify clients likely to apply for future consumer loan products. The project involved compiling data from the 2-year transactional history of 400,000 Equa clients as well as analysing the socio-demographic and product information available for this specific group.
Business needs
The solution needed to meet the following business targets:
- Improve the conversion rate of consumer-loan product offerings
- Generate accurate prediction scores for Equa’s entire client base
- Evaluate added business value for different client segments
Challenge
To create a sufficiently accurate propensity model, we needed to execute a number of highly complex computations based on a huge volume of unstructured data. The task would involve processing tens of millions of transactional records and hundreds of millions of links across the client network.
To that end, we knew that employing relational databases or conventional statistical methods like regression and segmentation just wouldn’t do. The challenge required a sophisticated technical solution.
Solution: The propensity model
Our unique propensity-to-buy solution was based on modelling client behaviour and social similarity networks. With these insights, we were able to identify client microsegments using advanced machine-learning methods developed in close consultation with our research partners at Charles University in Prague.
To handle the huge volume and complexity of input data, we built a big data computational pipeline using specifically designed data structures on Apache Spark and the Hadoop platform. The set of clients evaluated by the Profinit team was independently verified by data analysts at Equa bank. They confirmed the high precision of our prediction model (87% AUC). Not only that, they found that our propensity-to-buy scoring was effective across almost 70% of the client population including new customers, inactive clients and those with no previous loan history.
Tech stack
- Profinit propensity-to-buy lending solution
- Hadoop
- Apache Spark
- Python
Project Summary
We rolled out an advanced propensity-to-buy model to enhance consumer loan uptake for our client Equa bank, delivering the following results:
- Propensity scores computed for all bank clients
- High-accuracy propensity model for future loan applications
- Added business value for almost 70% of the client base as confirmed by Equa bank analysts
- Applicable even for new and inactive clients without previous loan history
Would your company benefit from accessing propensity-to-buy prediction model?
Profinit improves the way organisations use and access data in-house. Let us show you how.
Related success stories and use cases
Raiffeisenbank Competitor loans consolidation
Profinit helped Raiffeisenbank CZ detect twice as many loans with competitors – and approach more clients to consolidate their loans – while remaining “the most customer-friendly bank”.
Learn More
Erste Group Bank Computing anti-fraud predictors
How Profinit helped the Česká spořitelna (Erste Group) dramatically speed up fraud detection, to process 1.5 billion transactions per day.
Learn More
Erste Group Bank Central log monitoring for security
How Profinit helped the Erste Group Bank AG meet new cyber security regulations, and enabled rapid access to fresh data.
Learn More