Case study: How Deep Learning Can Drive Customer Growth In The Banking Industry

30 June 2022

Lead generation is a complex, challenging, and arduous process, more so for the banking industry. Identifying consumers who need financial services is no easy task as these behaviors are very personal and varied. This post looks into how SoMin used deep learning to handle these nuances and drive consumer growth for Citibank CEE.

Wavemaker, a prominent WPP media agency was looking to better the lead generation campaigns of Citibank CEE.

2 key challenges:

  1. Identify the audiences who need financial services as these behaviors are very personal and varied in nature.
  2. Improve attribution for a business with a long sales cycle.

We started off by diving deep (and then deeper) into our client’s business to gather critical data on our audience and our competitors.

To understand our client’s business better, we used Somin’s proprietary omni-sourced machine learning algorithm - Omni-Sourced User Profiling to compile anonymized audience data from multiple sources.

The Omni-Sourced User Profiling analyzed more than 166.5K social accounts across multiple platforms that are associated with the brand and its industry.  From there it analyzed approximately 2,844,766 posts through both computer vision (CV) and natural language processing (NLP). This resulted in the collection of 5,604,442 data points used for the collaborative filtering (CF) process.

Through AI We Were Also Able To Better Understand Our Audience

We then used our AI User Analysis to help Citibank CEE’s campaign managers understand and cluster their audience personas better with machine-observed interests, behavior, and traits. They were then able to use these insights as a guide to inform their creatives and messaging.

Through the analysis of the data collected, we defined the targeting for 1 campaign through  124 ad sets with 525 ads. This was only made possible with AI.

Then We Identified Our Highest Value Audience That Would Help Us Achieve Our Business Goals

Personas were then grouped together through long-tail targeting based on their highest probability of conversion. Once these groupings were defined, they were tested through an automated A/B optimization process that was geared towards the brand’s goals.

Finally, We Let Our Platform Do All The Heavy Lifting. Freeing Up Our Clients To Focus On Other Important Matters. 

124 ad sets and 525 ads were optimized every 30 mins. Automated and tuned towards achieving our business goals. Listed are the number of actions taken by the platform and the estimated time saved to generate the improvements in campaign results.

The Outcome:
We successfully scaled up Citibank CEE’s customer acquisition without increasing their cost per lead and bursting their marketing budget

Citibank CEE increased their spends through SoMin by 2x and applied the technology to other lead generation activities such as personal loans.

Looking to take your digital marketing to the next level with AI? We are ready to embark on this journey with you.

Download the full case study here.

ABOUT THE AUTHOR

Prof. Aleks Farseev PhD

Aleks Farseev is a machine learning wizard who can teach a computer to sing "Bohemian Rhapsody" in binary code. He loves conjuring up new creations and is on a quest to figure out how machine learning can make the world a better place. When not tinkering with technology, Aleks can be found serenading his friends with his accordion skills, which he claims are only slightly less impressive than his machine learning prowess.

Want to have a chat about our products?

We're always happy to talk about how our tools can help people.

Book a Demo