# Buyer Propensity Model

This is a buyer propensity model that predicts which customers are most likely to buy bikes. It uses 2 binary classification algorithms.

This is a buyer propensity model that predicts which customers are most likely to buy bikes. This is a good example of a customer targeting model that is widely used in Marketing. It uses 2 binary classification algorithms namely Logistic Regression and Boosted Decision Trees.
**Inputs:**
The input data is the BikeBuyer dataset that has historical sales data on a set of fictitious customers. This dataset has 10,000 rows and 13 columns including demographic variables such as marital status, gender, yearly income, number of children, occupation, age, etc. Other input variables include home ownership status, number of cars, and commute distance.
**Outputs:**
The training data has one output - a single binary variable showing whether the customer bought a bike or not. The output of the model is the probability of purchase. So for a given customer the model shows the probability that the given customer will buy a bike.
More details on the model are available in the book: [Predictive Analytics with Microsoft Azure Machine Learning: Build and Deploy Actionable Solutions in Minutes.](http://www.amazon.com/dp/1484204468/ref=rdr_ext_tmb)
Created by a Microsoft Employee