Data Required

Your business will provide both customer attribute data (e.g., age, income level, education level, gender, etc.) as well as historical spending data (i.e., when the customer last bought, how often they buy, how much they spend, on which products, etc.). Students will use these data to develop a statistical predictive model to predict which type of customers will likely come to your store and make a purchase. For example, the model might predict that a 28-year-old woman with a university degree living in Barrie has a 75% likelihood of visiting your store and make a purchase, whereas a 32-year-old man with a college degree living in Collingwood has only a 35% likelihood.

Statistical Analysis

Students will develop an appropriate model to predict how likely it is that a customer will visit your store or predict other quantities you are interested in. The analysis will include the following:

• Perform the appropriate statistical modeling techniques (such as multiple linear regression, logistic regression, decision trees, naive Bayes' classifier, time series analysis, neural nets, support vector machine, k-nearest neighbors, random forests & boosted trees, and uplift modeling)
• Determine which data attributes provided are predictive.
• Interpret the model output.
• Provide the formula from the statistical model that predicts the likelihood a customer will visit your store and make a purchase.

Final Project Output

The final project output would include the following:

• Descriptive statistics on the data attributes, including an app for data visualization
• Methodology, including creating the appropriate models
• Detailed results
• A model equation that predicts which customers will likely buy from your business or a forecast of future revenue
• Recommendations that include how to deploy the model from a business perspective within the company
• Conclusion