Optimise Your Campaigns with Predictive Customer Analytics
A Philippines Telecommunications giant needed to build a platform to increase the effectiveness and efficiency of its CRM campaigns and planning process.
The key component of this strategy was the availability of statistically sound predictive models (machine learning) to feed into their campaign offer optimisation engine.
Originally the client brief was to offer individual product promotions to customers (e.g.: SMS, voice, data etc.). BusinessMinds worked with the client to create a new innovative strategy demonstrating how effective predictive modelling would create individual bundled offers (i.e. several products in one offer). This is – a much more efficient strategy for the company and one that addresses all of a customer’s needs at once (rather than them receiving several disparate, confusing offers).
Insightful decision making from your data.
BusinessMinds create strategies, manage, design and implement:
Management and Control
GoalsMaintain customer loyalty and increase customer satisfaction by offering personalised bundled products tailor-made for the customer’s digital lifestyle. Build statistical models to accurately assess customer behaviour and preferences. Enhance the productivity of marketing campaigns and promotions for both prepaid and post-paid business segments. Build propensity models to improve the customer response rate to promo offers, hence increasing revenue.
BusinessMinds provided a process to combine different machine learning techniques to achieve the client’s goals.
Customer segmentation divides a customer base into smaller groups so that data within any segment are similar while data across segments are different.
Market basket analysis is a modelling technique based upon the theory that if you buy a certain group of items, you are more (or less) likely to buy another group of items.
A propensity model is a statistical scorecard that is used to predict the behavior of your customer or prospect base. Propensity models are often used to identify those most likely to respond to an offer, or to focus retention activity on those most likely to churn.
Specific Customer Analytics Modelling
Post Paid Propensity Models
Post-paid Propensity Models were designed as part of the customer retention objective. The requirement was for the Post-paid Brand Team to be able to create, communicate and deliver the optimal plan combination for each subscriber specific usage patterns.
Prepaid Promo Propensity Models
The Promo Propensity Models identify prepaid subscribers who are most likely to respond to prepaid promos. In line with the refined strategy the BusinessMinds team built intelligent propensity models for each promo group based on a unique combination of service type(s) and price point(s).
Top-up/Reload Propensity Models
The Top-up Propensity Models predict the likelihood of a prepaid subscriber reloading a specific amount enabling the business to efficiently target specific customers depending on their final top-up decisions.
Data Upsell Propensity Model
The Data Upsell Propensity Model identifies current data promo subscribers who are most likely to respond to higher data promo offers. The Telco can thereby leverage their data services and increase the penetration of the prepaid mobile data market.
BusinessMinds provided a comprehensive modelling strategy customised for each prepaid and post-paid subscriber that ensures customers receive offers they are interested in and suit their needs, including
Trend analysis of current mobile service usage.
Market basket analysis to identify product bundles
Predictive modelling to present the next best offer for each subscriber.
Business BenefitsStreamlined business strategy (offering bundled products vs single offerings).
Increased promo take up (in prepaid and postpaid segments).
Happy customers – decreased churn.
Optimised campaign spend.
Increased market penetration for the brand.