caravan

The contains \(5822\) customer records from an insurance company, each described by \(86\) variables. These include \(43\) sociodemographic features based on zip codes and \(43\) indicators of product ownership. The final variable, <code>Purchase</code>, indicates whether a customer bought a caravan insurance policy. Collected for the CoIL 2000 Challenge, the data was designed to address the question: Can you predict who would be interested in buying a caravan insurance policy and explain why?

datasets

Provides a collection of helper functions and illustrative datasets to support learning and teaching of data science with R. The package is designed as a companion to the book <https://book-data-science-r.netlify.app>, making key data science techniques accessible to individuals with minimal coding experience. Functions include tools for data partitioning, performance evaluation, and data transformations (e.g., z-score and min-max scaling). The included datasets are curated to highlight practical applications in data exploration, modeling, and multivariate analysis. An early inspiration for the package came from an ancient Persian idiom about "eating the liver," symbolizing deep and immersive engagement with knowledge.

Abdolreza Mohammadi

liver

Foundations Toolkit and Datasets for Data Science

Reza Mohammadi

Kevin Burke

caravan function

A data frame with \(5822\) observations (rows) and \(86\) features (columns).

caravan: Caravan insurance data set

Description

Usage

Arguments

Format

Details

References

See Also

Examples