FITTING A REGRESSION MODEL TO UNDERSTAND THE KEY DRIVERS OF CUSTOMER SATISFACTION.

In this analysis, I will walk you through the steps of fitting a regression model to understand the key drivers of customer satisfaction on an e-commerce platform. By following the CRISP-DM methodology, we can gain valuable insights into the factors that most impact customer satisfaction and develop data-driven solutions to improve the overall customer experience, while efficiently allocating resources.

Below are the steps of the CRISP-DM methodology applied to fitting a regression model to understand key drivers of customer satisfaction for a fictional online retailer:

Business Understanding: The first step is to define the business problem and identify the goals of the project. In this case, the online retailer is struggling to understand the key drivers of customer satisfaction and needs to allocate resources effectively to improve overall satisfaction.

Data Understanding: The second step is to collect and analyze the data that will be used to solve the business problem. In this case, I have collected relevant data on customer satisfaction surveys, as well as data on customer demographics and purchasing behavior.

Data Preparation: The third step involves cleaning, transforming, and formatting the data in preparation for analysis. This may involve removing missing values, checking duplicated values, and exploratory data analysis to understand the variables of the data sets better.

Modeling: The fourth step is to apply a regression model to the data to identify the key drivers of customer satisfaction. This involved using the Ordinary least squares (OLS) technique to identify the variables that have the most impact on customer satisfaction.

Evaluation: The fifth step involves evaluating the models developed in the previous step to determine their effectiveness in solving the business problem. This may involve using metrics such as R-squared, beta coefficient, and p-value to assess the goodness-of-fit of the model.