Menu
Customer Lifetime Value
Objective
- Develop customer analytics, inclusive of purchase behaviors, store vs. eCom engagement and source channel usage
- Demonstrate the scalability and elasticity of MS Azure cloud services for data management and analytics
Industry: Shipping and Delivery
Services: Technology Innovation
Technology: Graph Analytics & Machine Learning
Established customer identification as a critical step in the client’s data and analytics journey.
Provided a roadmap for operationalizing the customer identification methodology developed as part of this proof-of-concept.
Outlined an initial engagement that would kick-off the data and analytics journey recognizing the learnings generated by this proof-of-concept engagement.
Our Client
Our client is a multinational company that provides transportation, e-commerce, and business services. This global logistics company operates a vast network facilitating the transportation and delivery of parcels, documents, and freight worldwide. Renowned for its innovative approach to logistics and commitment to customer satisfaction, it plays a pivotal role in connecting people and businesses across the globe.
Challenge
- The client recognizes that its journey to a data-empowered organization must begin with understanding its customers.
- Retailers who can wrap their arms around identifying their customer and beyond that, their customers’ journeys, will be able to capitalize on that knowledge to deliver on their strategic objectives.
Approach
- Employ customer transaction data, customer payment data and associated customer identities captured in interactions, to isolate a business ontology of the customer data domain.
Outcomes
- 64% of transactions contained personal identifying data, yielding ~4% shrinkage on customer IDs.
- 1% spend stretch among top 20% customers, contributes 0.74% incremental revenues
- Converting 5% of customers within the bottom 80% to make an additional visit, will contribute an incremental 1.5% – 2.5% revenues to the client’s top line
- Clustering on RFM & NADR features yielded segments that indirectly differentiated customers by other characteristics that were not exposed to the algorithm, but inferred through profiling post model training
- Among customers who made 2+ purchases Recency and Frequency feature variants explained majority of the variance in customers’ likelihood to return
Impact
Established customer identification as a critical step in the client’s data and analytics journey.
Provided a roadmap for operationalizing the customer identification methodology developed as part of this proof-of-concept, and leveraging the same to develop relevant customer analytics capabilities.
- Outlined an initial engagement that would kick-off the data and analytics journey recognizing the learnings generated by this proof-of-concept engagement.
Enjoy this story? Share it to your network.
View more Case Studies
Issues (Risk) Correlation & Consolidation Analysis
Hybrid Cloud Analytics
Data Strategy Implementation
Ready to transform your business?
Explore Our Services and Unleash Your Potential Today!