Our customer is one of the most important Oil & Gas companies in Romania with a presence of over 20 years in the market.
Here are the main business challenges we addressed in our Solution:
- The organisation needed to increase average revenue per customer
- Also, the customer needed to stimulate cross-sell and upsell
- The customer requirements called for an increase in the utilization rate of loyalty points across a nationwide marketing program.
Solution
In response to our customer’s request, we have formulated a Customer Clustering & Segmentation: Next Best Buy algorithm in the form of a pilot project running for a duration of 3 months.
To increase the average revenue per client of our customer we used the following advanced analytics techniques: Customer Clustering & Segmentation, “What if” Analysis applied to previous marketing campaigns and the overall positioning strategy, store clustering and “next best buy” algorithm based on clusters and shopping patterns.
To stimulate the cross-sell and upsell of our customer we made a Customer Analysis & Segmentation, leveraging the “Next best buy” algorithm based on clusters and shopping patterns and on a set of analytics techniques aimed at uncovering connections between specific objects: visitors to our customers’ website and the products in the store.
Furthermore, to enabled our customer to increase the utilization rate of loyalty points, we used Customer Clustering as well as the techniques mentioned previously.
In terms of technology, the solution was deployed using advanced analytics to identify products that represent a Next Best Buy, as well as specific algorithms on customer clustering & segmentation and store clustering.
Customer Benefits
Store Clustering uses loyalty card transaction data and surveys data to identify similar stores that form a cluster based on shopper demographic data and their shopping patterns.
This way our customer could tailor specific promotional campaigns, assortment, planogramming, pricing and promotion strategies, store formats and layouts for servicing each of the identified clusters.
