Customer Satisfaction

Understanding the business’ customer’s experience and satisfaction is key to maintaining and growing the business. Surveys are the key method to measure this, but not all customers respond and surveys are expensive to design and run so don’t often reach all customers and happen infrequently. Using the characteristics of the customers and the responses to satisfaction surveys, an estimate of every customer’s current satisfaction can be developed.


Use customer data and past surveys to predict the current satisfaction level of all of your customers.


Customer’s reported satisfaction level.


The data from the survey is the target, but as much data about the customer’s interactions with the company needs to be gathered as possible to enable a complete view of the customer as it relates to the survey. This data tends to be scattered across multiple databases including the CRM system, web analytics database, and the survey database. In addition, if the customer’s social media accounts are known, the sentiment of their posts could be linked to the rest of the customer data. 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

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