STP Marketing: Segmentation, Targeting and Positioning Marketing for a leading entertainment company

  • August 21st, 2018


The world’s most diversified casino-entertainment provider wanted to improve its existing methodology of targeting customers by leveraging past behaviour.
Mu Sigma helped the client improve ROI on player reinvestment by providing a better understanding of customer base and streamlining targeting practices using a robust STP marketing model.

The STP marketing model – segmentation, targeting, and positioning involved developing a comprehensive customer segmentation framework and a scoring mechanism to predict a customer’s next trip spend. The right set of customers were then targeted with the right campaigns and offers to increase the next trip spend of customers.

The Problem

The client’s existing methodology to predict the customer’s average daily worth (ADW) was primarily based on the customer’s prior trip spend. This resulted in sub-optimal allocation of marketing spend, low ROI, and the wrong set of rewarded customers.

A big proportion of the client’s annual marketing budget of a billion dollars was spent on targeting programs based on their perceived ADW. This problem raised the need for an STP marketing model for improving ROI on marketing expenditure.

The Mu Sigma Approach

A structured framework was developed around STP marketing model comprising of the following:

•   In contrast to the current approach, a new definition of a ‘customer trip’ was created to account for frequent customers visiting multiple properties on the same trip
•   A customer segmentation model was developed based on the average daily potential spend value and frequency of trips
•   Supplement the retailer’s enterprise data sources with a 360-degree customer data mart
•   A customer segmentation model was developed based on the average daily potential spend value and frequency of trips

   o   Potential Spend Value
  – High Spenders
  – Medium Spenders
  – Low Spenders

   o   Frequency of trips
  – Low Engagement
  – Medium Engagement
  – High Engagement

•   A predictive model was built to calculate the probability of customers in each segment to fall into any of the pre-defined spend buckets
•   Inaccurately predicted customers from the predictive model were represented by certain zip codes. A reclassification algorithm was created using these zip codes

A scoring framework was created based on the learnings from customer previous trips such as previous trips spend, frequency of trips, etc. The score from the model implied the likelihood of the customer’s next trip spend and helped the client prioritize and target customers for different campaigns and offers accordingly to increase engagement

The Findings/Recommendation


•   Customers having medium trip frequency have a lower propensity to churn as compared to customers with high trip frequency
•   Females are less likely to churn as compared to the males

Instances of extreme luck (Good/Bad) in recent trips makes the player more vulnerable to decline.


•   More the compensation given to the customers during the time they stay at the hotel, the lower the chance of their decline in engagement
•   Existing target list of customers was refined to incorporate changes based on the STP model


•   The type of casino (Land / Racino / Riverboat) present in the market influences the share of wallet of a customer

•   Factors such as total days spent at a casino, lodging facilities at a casino, complimentary offers provided, etc significantly impacts share of wallet
•   Markets with a higher proportion of client casinos tend to have customers with a high share of wallet
•   The right set of customers must be positioned with the right campaigns and offers to increase their lifetime value

The Impact

•   The project resulted in an improvement of customer targeting accuracy by over 10% through a rigorous and algorithmic approach. This approach is easy to scale across geographies.
The STP marketing process is now being leveraged to get better estimates for all markets
•   This represents a $10MM cost savings and an estimated $20MM in additional revenue for the client

Click here to know about how Mu Sigma helped one of the leading airlines in the US run targeted marketing campaigns and increase response and conversion rate by 20 percent.