Case study

Pricing Strategy Machine Learning Tool

Media, Telecommunications

A Strategic Pricing Tool allows our client to build revenue maximising strategies using personalised pricing scenarios and will play a significant role in pricing strategy going forward.


Our client is a provider of subscription television, internet and mobile services. They have an international reach totalling over 22 million customers, and a history of developing innovative products and entertainment content.


The client had an existing modelling and simulation suite to describe customer behaviour in response to annual price increases. The in-house functionality using an internal risk bucket system (four) and logistic regression did not provide the granularity needed to move towards a more personalised pricing strategy. Partly, the objective of the project was to identify opportunities to increase the net yield of a price increase by allowing mitigation strategies for subsets of customers.

Key deliverables and functionality of the solution included:

  • Machine Learning modelling suite of behaviour at the customer level, writing in Python and trained using cloud computing resources (Google Cloud Platform).
  • Micro-segmentation of customer base using key demographic, behavioural, contractual metrics, coupled with estimated risk scores and sensitivities.
  • Strategic Pricing Tool that allows for real-time simulation of the financial impact of variations on the pricing schedule, using ML models describing behaviour.
  • Identification of small groups of customers for which proactive or reactive mitigation strategies would be profitable.


Forecast worked with stakeholders from the finance team and the decision science team to decide on an appropriate modelling framework and identify key deliverables. In addition to the key KPIs modelled for the Planning Tool, Forecast worked closely with the finance team to build predictive models around longer-term Net Revenue impact.

Forecast delivered an end-to-end solution, with responsibilities for the data engineers to build out the data pipeline required for the modelling of the various KPI. Responsibilities for the scientists involved working closely and iteratively with the in-house finance team to build a solution that answers the right questions. Forecast worked to a tight deadline where the dates that customers can receive price increase notifications is fixed.


The final modelling suite and Strategic Pricing Tool enable stakeholders to better understand customer behaviour in response to price increases and provides them with the tools to build revenue maximising strategies. In general, the framework is a leap forwards when it comes to more personalised pricing and will play a significant role in pricing strategy going forward.

Like this article? You’re one step closer to making data-driven decisions.

Reach out to us to start a conversation – we welcome an opportunity to understand your data needs, challenges and aspirations. We utilise an expert toolkit of data capabilities and services to help take guesswork out of your decision making.

More like this

Case study

Media, Telecommunications

Campaign Effectiveness Tool

Case study

Financial Services

Targeting Strategy For Car Finance Proposition

More of our case studies Contact Us