Propensity To Buy

Converting non-paying users to paying customers and encouraging paying customers to use more of the system and pay more for more functionality is key to a digital product’s success. Understanding those portions of the experience that customers use and avoid allows for design decisions ranging from designing the product layout to make the most important actions easy to find and execute to determining where to invest development resources to. Understanding which customers are most likely to make a purchase allows the sales and customer success teams to focus on those customers most likely to generate revenue.


Based on a customer's product and website usage, along with data about the customer, predict which customers are likely to convert to paying customers or make an additional purchase.


Will a customer make a purchase in a given time period?


The first challenge with sales predictions is defining within what time frame the purchase needs to occur.

The next challenge is joining and transforming the data contained in multiple different tables to create the training dataset. The CRM system will contain the purchase/payment information for the customer. The customer’s behavior within the product can be determined using the data in the product usage and web analytics DB. Further information can be gleaned from external enrichment data such as demographics for third party customer behavior and economics data for macro socio-economic influences. All this data needs to be cleaned, joined and transformed into valuable ML features before going into model training. This pre-modeling prep process can be frustrating and time consuming. We are here to help.

Modeling techniques and libraries

Multiple regression analysis

Allow more than the two choices across multiple dimensions. Models the target as a function of the independent variables.

  • Sklearn - linear_model
  • Statsmodels

Machine learning analysis

Build machine learning models to predict the target as a function of the independent variables. Use model interpretability packages to evaluate the impact of the independent variables on the prediction.

  • Sklearn
  • ELI5
  • LIME
  • SHAP

Related accelerators

No items found.

No-code/low-code data prep and visualization