Driving sales with connective marketing

The ask

An international bank sold their financial products and recruited new
customers through marketing campaigns based on traditional CRM
selection techniques. After contemplating the opportunities of A.I.
and automation, the bank was curious to discover if the
technologies could be used to take a more innovative approach to
marketing, and if a higher ROI for their marketing budget could be
achieved.

 

 

KEY OBJECTIVE :
USE A.I. ENABLED
PROCESS AUTOMATION
TO ACHIEVE A
HIGHER ROI ON
MARKETING BUDGET
AND DRIVE SALES .


What we did

Using historical demographic data provided by the bank, we created an
A.I. enabled process automation solution capable of identifying customer
purchase patterns, automatically creating customer profiles, and making
predictions on the probability certain customers would engage with
particular products.

 

After training several different algorithms – which we call discovery
experiments – we defined a model to match customers to products. This
insight could then be used in marketing campaigns, allowing the client to
amplify sales among 156,000 customers.

 

 


The process

 

We built a customer-product predictive model which used past customer
transaction behaviour, purchase patterns, demographic data, promotional
activity data, campaign response history, dates and times to reveal trends
and patterns that were simply invisible to humans. This allowed us to
predict which individual customers would be likely to engage with and
purchase certain products.

 

After experimentation, we deployed the solution into production and began shadow testing, evolving the accuracy using live production data throughout the life of the solution.

 


Summary

CAMPAIGN SUCCESS
RATE RAISED TO
23%, WITH 35,117
SALES ACHIEVED BY
CONNECTING
CUSTOMERS TO THE
RIGHT PRODUCTS.

Before working with us, the bank carried out an initial campaign using
traditional methods with over 291,000 customers. They obtained 8,905
sales, or a 3% success rate, similar to what they had obtained in past
campaigns.

 

With this solution in place, the bank was able to use prediction to match
customers to products and then tailor their marketing actions accordingly.
This approach proved to be incredibly successful, and is a prime example
of taking action based on prediction.

 

When the client launched a new campaign using the connective power of
A.I., they returned 35,117 sales out of 156,000 customers, for a 23%
success rate.

 

 

Are you working on something similar?

Get in touch and we’d look to discuss how we can help you.



    Share on: Facebook Twitter LinkedIn