Amplified B2B sales with segmentation in retail
Context & Objectives
A growing Belgian food retailer’s poor quality CRM data limited their B2B sales expansion.
Obtaining more accurate customer insight was crucial for the retailer to better allocate acquisition and retention resources.
They turned to Agilytic to enrich the dataset of their prospective customers, clean their CRM, and segment prospects based on transaction behavior and firmographic characteristics. The desired outcome - to increase customers' average spend, grow customer loyalty, and acquire new customers.
With these objectives in mind, we set out to perform a segmentation of customers to understand their purchase habits and recommend ways to adapt the sales approach.
Approach
We worked with the retail client and their sales partner to maximize the relevance of the outcomes.
First, we began with a data cleaning to improve the quality of the analysis (e.g., remove duplicates based on cleaned TVA numbers).
Then, before developing the segments, we performed a data validation to validate the scope of the project. Additionally, we could exclude customers/transactions not relevant to the campaigns our client wanted to perform. Afterward, for data enrichment, we extracted BCE and BNB data to enrich the information on customers (e.g., BCE: to get sectors, start date, potential email and phone numbers, and BNB: to get financial reports giving the number of FTEs, gross operating margin or profit/loss).
Next came the segmentation. We identified features and tags based on transactions and created BCE and BNB information. Based on categories of high and low transactions on customers (based on average yearly spent amount), we identified the clusters in sectors, customers' ages, and customers' sizes where we had a higher probability of high transactions customers. We then extracted the lookalikes in the BCE dataset based on the identified clusters.
After this segmentation phase, we moved on to the consolidation of outputs for CRM import. For example, features, tags, and segments based on existing and prospective customers were consolidated into files to be imported into their CRM.
Finally, we delivered documentation to transfer knowledge to our client's team and help them take ownership. We wrote documentation to describe the approach and scripts used to build the segmentation. The documentation also included the procedure for applying the segmentation to new data.
Results
At the end of the project, we delivered:
Enriched and consolidated dataset of their customers
Segments assigned to their customers
Enriched and consolidated dataset of prospective customers (lookalike)
Description of identified segments
Documentation on approach and procedure to create the outputs
After completing the project in 12 days, the client quickly understood the necessary subsequent actions to increase its commercial potential. Our model allowed the client’s sales partner to use the segments to inform future sales campaigns.
