Nedbank Finds Value in Endless, Fragmented Data Streams with SAS

Nedbank processes three billion transactions at any given time. Data enters the organisation through various channels such as Point of Sales machines, Internet banking, social media, the Nedbank contact centre and thousands of branches countrywide.

Just managing this high volume of data is challenging enough and transforming it into valuable, usable insights is a different ballgame.

We have all the information we need to create deeper relationships with clients.

Simon Marland
Business Intelligence Head, Nedbank

By using SAS Office Analytics and SAS Enterprise Miner, Nedbank has been able to identify what it calls “golden nuggets” of information that leads to targeted and relevant conversations with the customer.

Simon Marland, BI head at Nedbank, defines a “golden nugget” example as follows: “People getting a monthly deposit in their accounts typically aren’t golden nuggets, because that’s their salary. It has to be an abnormal deposit that catches our attention, because then we can offer the customer a relevant product, like a unit trust or stock brokering.”

These nuggets allow the bank to tell stories with its data. For example, the bank takes information from the point of sale machines and tracks its own client and competitor card swipes to break these down into research and operational data that provide insights into customer behaviour.

SAS Enterprise Miner allows the bank to build descriptive and predictive models that help uncover opportunities hidden in data. These models can predict which customers will purchase what products and when; which customers are leaving and what can be done to retain them, thus increasing response rates for marketing campaigns and improving anticipated resource demands.

For instance, the bank can paint a picture of the way in which a visitor to the Gateway Shopping Centre in Durban behaves. “It’s very busy there on a Tuesday night. Boyfriends like to take their girlfriends to the movies. Those couples will pop into Guess to buy a pair of jeans. So that type of insight – knowing that there’s good turnover in shopping malls – tells us that it’s a good idea to place a Guess store close to the movies.”

It’s golden nuggets such as these that Nedbank uses to open new revenue streams. Rather than only using these insights to inform internal decision-making, it sells the data back to its clients, in essence providing information as a service.

In this way, Nedbank is moving into the business intelligence market. “Our customers generally don’t have big BI shops, and customers that do, generally don’t have this kind of data.”

At the same time, Nedbank’s BI department also analyses data for internal use, with the intention of generating profit.

For example, the data scientist team will work out that if an SMS costs 15c, a call centre agent call costs R50, and a campaign has a budget of R500 000, which channel will be the most cost effective to generate a return?

“Different business areas have different business needs – sales, services, research – and across a database of millions, it’s important that we co-ordinate our efforts so that we manage the offers that are presented to our clients. This centralised leads management allows for campaign planning, execution, post-campaign reporting as well as avoiding duplication in a client-centric approach,” says Marland.

He says that since centralised leads management begun in the bank, statistical modelling has allowed them to acquire more accounts with fewer leads. “We have all the information we need to create deeper relationships with clients.”

As a SAS user, Nedbank’s BI department is clearly breaking ground with data science, using the tools not only to deliver revenue-generating information to their internal departments, but also to sell it to customers who otherwise wouldn’t have access to such insights.



Finding value in endless, fragmented data streams.


SAS Office Analytics
SAS Enterprise Miner


  • Nedbank has been able to use the insights it has gained through data analysis to create revenue for itself and its clients
  • Campaigns have been optimised through centralised leads management, generating the highest returns possible
  • The bank has acquired more accounts with fewer leads
  • Ability to provide personalised service
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.