top of page

FINDING NEW AND BETTER CUSTOMERS THROUGH PROPENSITY MODELLING

Propensity modelling is an effective tool for financial services brands, particularly credit providers, to acquire new customers because it allows them to target their marketing efforts towards individuals who are most likely to be interested in their offerings and who have a higher likelihood of being approved for credit.

The benefits are proven to be threefold:

 

Propensity modelling increases conversion rates for customer acquisition campaigns. A study by McKinsey found that companies that use predictive analytics to target their marketing efforts have conversion rates that are 2.5 times higher than companies that don’t use such tools.

 

It improves customer engagement through better personalisation of marketing messages. Accenture found that propensity modelling increased customer engagement by up to 50%.

 

It reduces marketing costs. By targeting marketing efforts towards individuals who are most likely to be interested in their credit card offerings, credit card providers can reduce their marketing costs and improve return on investment. A study by IBM found that companies that use predictive analytics to target their marketing efforts have marketing costs that are 15-20% lower than companies that don’t use such tools.

 

Propensity modelling involves using statistical techniques to analyse large amounts of data and identify patterns and correlations that can help predict the likelihood of a certain event occurring, such as a customer applying for, and being approved for, a credit card.

 

By leveraging propensity modelling, credit card providers can identify potential customers based on a variety of factors, such as their credit history, income, spending habits and demographic information. This enables them to tailor their marketing efforts to these individuals and increase the likelihood of converting them into customers. Moreover, propensity modelling helps credit card providers to manage risk and reduce the likelihood of default. By identifying individuals who are more likely to default on their credit card payments, credit card providers can either deny them the credit card or set stricter terms and conditions to minimise their risk exposure.

For one of our credit card clients in Australia, this is exactly the approach we took to help them to work more collaboratively with its sister airline brand, to identify new customers from its frequent flier database.

 

By carrying out an initial customer profiling exercise, it was possible to define the profile of both customer bases at a high level, which meant we could provide an understanding of the profile of existing airline frequent fliers and match these with lookalikes in the card base. We created customer segmentation to identify groups of customers with similar characteristics. These were then used within our propensity model and deployed to identify the probability of a person with particular attributes to apply and be approved fora new credit card.

 

The model was designed with agility at its core to ensure that over time it becomes more effective, as the results and learnings from each campaign are fed back into it. As a result, it continues to work at identifying the top 20-50% of potential card applicants for the credit card brand. The continual improvement of the model resulted in the number of applications rising over time, with an increased successful application rate, as the model helps to reduce the number of rejections and application cancellations, resulting in more customers, a better customer experience and saved marketing budget.

Discover how Beyond can empower your business with unparalleled insights through our comprehensive analytics solutions. Contact us today to begin your journey towards enhanced business insight and informed decision-making.   Enjoy more of our Featured Insights including Driving Efficiency in Sanction Screening.

bottom of page