E-commerce · Customer Data case study
Shinetech connected online and store customer activity in Salesforce Data 360, then used purchase history and buying frequency to inform customer segments. Those segments supported different product recommendations, while service could see selected purchase context.
The situation
Retail marketing needs to distinguish a first-time buyer, a regular customer and someone whose purchasing has slowed. Separate online and store records can hide those differences, leaving teams with broad campaign lists instead of a useful view of buying behavior.
When a customer contacted the service team about a purchase, the agent needed the relevant activity beside the case. The project therefore had to connect records carefully before either customer analysis or service used them.
The challenge
The business needed to decide which customers should receive which kind of follow-up. Moving data between systems was one part of the work; usable segments also required reliable customer relationships and agreed definitions of purchases and returns. Purchase recency, frequency and value can help distinguish those needs, but the analysis depends on linking the right customer records and interpreting purchases and returns consistently. A useful segment needs both a clear definition and a purpose in customer communication.
The solution
Shinetech mapped online account and store membership identifiers into Data 360 matching rules. Verified relationships supported a shared view; uncertain records stayed available for review rather than being joined by similar names alone.
Purchase history and buying frequency informed customer segments. Different segments could then guide different product recommendations. The agreed purchase and return definitions remained attached to the analysis, and Service Cloud received selected purchase context for customer conversations.
Workflow detail
Connected purchase activity supports customer analysis and selected service context. Each source keeps responsibility for its operational records.
Workflow detail
Keep the customer and purchase source references.
Use agreed purchase history and frequency definitions.
Check which customer group the behavior supports.
Use the segment for differentiated recommendations and selected service context.
Returns can change the behavioral view; communication preferences still govern any later outreach.
Workflow detail
Illustrative RFM-style planning examples, not the client’s exact segments or campaign rules. Recency describes how recently a customer purchased, frequency how often, and monetary value how much they spent.
| Behavior to examine | Business question | Possible follow-up |
|---|---|---|
| A recent first purchase | What would help this customer make a relevant next purchase? | Recommend a related category where product and preference data support it. |
| Frequent purchases over time | Which interests and purchase patterns deserve a different offer? | Use category history to make the recommendation more relevant. |
| Previously active, with no recent purchase | Is a renewed recommendation appropriate? | Review a re-engagement message against purchase history and communication preferences. |
How we work
The delivery method starts with the marketing decision: what customer behavior should lead to a different recommendation? Data owners then agree which source records can be linked, the purchase measures to use and how returns affect them. Identity matching supports that business decision.
Review follows a sample customer from purchase activity into a segment and its intended marketing use. It also checks the selected purchase information available to service staff. Uncertain matches and changed purchase history should remain explainable to the people using the data.
The result
Purchase behavior provides a basis for customer segments and differentiated product recommendations, with the matching and measure rules available to review.
Agents see selected purchase activity beside the request, with its source and refresh context.
Case taxonomy
Discuss your business systems
Get in touch
Tell us what you need to build, modernize, automate, or augment with AI. We can start with a focused discussion or a no-risk 1-week trial.
“A fantastic company to work with.” After the initial rapid development project, American Shipping Co. kept two Shinetech developers embedded for nearly four years, supporting internal and external tools and new AI initiatives.
CEO, American Shipping Co. - 5-star Google Review
