Realigning Analysis in Banking – The Case of Market Basket Analysis
Can one of the most common applications in Retail sector, determine Next Best Offer in Banking, personalize inbound campaigns, and drive profitability?
Most people can easily understand the concept of Market Basket Analysis, even if they have never worked with data or analytics before. It’s all about analysing customer’s purchasing behaviour (Market Basket), understanding consumer’s needs and planning inventory, sales and marketing activities accordingly. The aim is to generate sales and drive profitability by increasing the size and the value of possible purchases.
Typically, Banks develop cross-selling and up-selling Models (propensity models) in order to identify customers with high probabilities to respond to marketing campaigns for targeted products or services.
However, there are limitations and disadvantages with this approach, mainly related with the effort and the resources required to develop and maintain such models for all products and services available, and the effort required to deploy targeted campaigns into sales channels in an operational way.
And when it comes to decide on the right channel and the right time to contact a customer, there is always a high probability to contact customers that do not want to be contacted, or in contrast, to waste resources by contacting customers that would have bought even without making an offer or a promotion through a campaign.
All the above does not mean that such models cannot help anymore, and certainly selling additional to existing customers is always critical to drive profitability. But rather than deploying multiple, and often costly cross-selling and up-selling models, is there an alternative approach that is worth trying?
The answer is Yes!
Market Basket Analysis, a less common application in Banking, can be used as an alternative approach to successfully answer some of the above limitations and provide personalized customer experiences and targeted offers, enhancing customer loyalty and generating sales.
Here are the most important reasons why:
Market Basket Analysis is a quick, simple, and straightforward technique:
- Data Preparation, Modelling and Testing/Evaluation are significantly less time-consuming and less expensive processes, when compared to propensity modelling
- There is no need to develop different models for different products or services, as one model includes different account types or services that customers have recently bought (i.e. portfolio analysis)
- It does not require in depth, advanced statistical knowledge and can be easily explained, visualized and communicated to non-technical users and the upper management
- It helps Banks to adopt a customer-centric approach for selling additionally, as it combines focus on customers and analysis of their portfolio
- It provides a comprehensive way to understand different banking behaviours within a customer base and the relative time sequence of such behaviours
- It aids new product design and creation of bundles services to meet customers’ needs
Manulife Financial offers Canada’s flexible mortgage account by using analytics to bundle deposits and credit accounts and the net balance to calculate the interest.
- It’s easy to include business criteria, based on market dynamics, and control the number of rules and offers produced, so that are meaningful, manageable and overall support your strategic objectives
- Offers produced can be re-ordered, based on risk and profitability weights or adjustments to meet regulations, incorporate profit considerations and address operational costs
- More than one recommendation (offer) is generated following an order.
- These can be deployed as Next Best Offers (promotions) to sales channels and contact points, so that are available during customers’ interactions as inbound campaigns (e.g. a banner during a session in web banking)
Westpac bank operating in Australia and New Zealand using next best offer is able to subscribe extra banking products to 37% of its customers through its branch staff and 60% through its call centre staff.
- It will overall provide personalized experiences, restore customer trust and show interest on individual customers, without spending too much to identify when they should be contacted
- Responses can also be incorporated into the analysis to help banks form a customer loyalty and lifetime value strategy
To conclude, whether your Bank operates in a volatile macroeconomic environment where marketing expenditures are constrained and the available analytical resources are allocated on risk control operations, or your Bank is expanding and targeting consumers quite massively with a wide range of products and services, there is always a need to generate sales by producing personalized offers, through a quick and simple marketing approach that will maximise return on investment.
In First Tennessee Bank, the use of Advanced Analytics led to a 3,1% higher response rate. Marketing costs could be decreased by almost 20%.
Version 1’s experienced consultants are on hand to help you understand your SPSS needs – from consultancy and training to finding the best software and license type for your analytical and usage requirements. Contact us to discuss your requirement and identify the best SPSS solution for you.
Take a look through our SPSS Articles covering a broad range of SPSS product and data analytics topics.
What’s New in IBM SPSS Statistics v29?
Looking to quickly learn what’s new in IBM SPSS Statistics 29? Rather than reading a list of changes and new procedures, there is a quick way to tour what’s new and access help. Read our post for more info.
What’s New in SPSS Statistics v27?
SPSS Statistics v27 was launched in June 2020 with the biggest change compared to v26 being the inclusion of Data Preparation and Bootstrapping as standard functionality, as part of the SPSS Base module. This post will take a high-level look at these changes plus cover off the key enhancements in v27.