1. Learn
    2. /
  2. Courses
    3. /
  3. Machine Learning for Marketing Analytics in R
  • 1

    Modeling Customer Lifetime Value with Linear Regression

    Free

    How can you decide which customers are most valuable for your business? Learn how to model the customer lifetime value using linear regression.

  • 2

    Logistic Regression for Churn Prevention

    Predicting if a customer will leave your business, or churn, is important for targeting valuable customers and retaining those who are at risk. Learn how to model customer churn using logistic regression.

  • 3

    Modeling Time to Reorder with Survival Analysis

    Learn how to model the time to an event using survival analysis. This could be the time until next order or until a person churns.

  • 4

    Reducing Dimensionality with Principal Component Analysis

    CRM data can get very extensive. Each metric you collect could carry some interesting information about your customers. But handling a dataset with too many variables is difficult. Learn how to reduce the number of variables in your data using principal component analysis. Not only does this help to get a better understanding of your data. PCA also enables you to condense information to single indices and to solve multicollinearity problems in a regression analysis with many intercorrelated variables.

Initializing

Exercise

Model specification

The stepAIC() function gives back a reduced model, as you just saw in the previous video. Now you want to apply this method to the exercise dataset defaultData.

The prepared dataset is available in your environment. Additionally, the MASS package is loaded and the previously built logit model logitModelFull is defined for you. Also note that we've reduced the size of the dataset as performing stepwise model selection can take a long time with larger datasets and more complex models.

Instructions

100 XP
  • Make use of the stepAIC() function. Set trace = 0, as you do not want to get an output for the whole model selection process. Save the result to the object logitModelNew.
  • Then, use the summary() function to take a look at logitModelNew. You can ignore the warning message in this case. Go ahead and see what changed. Understand the results.
  • The formula is saved in an object so that you don't have to type the whole equation again when you want to use it later.