Demand modelling

Selecting and acquiring the right customers is the lifeblood of a retail pricing team. From protecting the loss ratios, to optimising the profit margins, to hitting the business financial forecasts are all essential tasks that can only be achieved with strong predictive models. Knowing who will buy, what they will buy, and how long they will buy for is an area that we specialise in. From conversion to cancellation, from breakdown to bad debt, we have vast experience in them all. And we can completely rebuild your LTV algorithm whilst we are at it.

The Benefits

  • Allows you to identify who your customers will be, and the impact from your proposed price changes.
  • Enables optimisation and ensures that financial plans are accurate and can account for changing circumstances ahead.
  • Improves loss ratio by calculating the correct margins, and in turn which customers are more profitable.

The Models

  • Combining GLM and GBM models to cover the weaknesses of each other, and combine accuracy with consistency.
  • Highly advanced model builders in both python and other software systems allows us to build best in class models.
  • Proven track record of success, building demand models for motor, home, and pet for our clients.

The Elasticity Problem

  • Elasticity is not like other models; being more the difference between multiple models than the output of a single model.
  • Ensure that you favour consistency over precision; elasticity models do not need to be as granular but they do need to be robust.
  • A three-stage post model process to get the best our of the information, especially in smaller customer segments.

The Process

  • The first step is always to ensure that your data schema is fit for purpose and to apply feature engineering.
  • The second step is to ensure your retail structure is fit for purpose so that each model is doing the right thing in the right place.
  • Only then do we rebuild the models and have them all aligned to fit the final vision.


More service options