City-Market Clustering

June 23, 2015
The City-Market Clustering experiment is a simple K-Means Clustering model that attempts to group different cities together based on a series of demographic, economic, and geographic attributes. This experiment is intended to serve as a resource for hands-on labs and training.
“Where should I open my next restaurant location?” This question is often very difficult to answer. The right choice will likely lead to increased revenue and profit, where the wrong choice can mean watching a major investment go down the drain. Trying to make this decision by manually sifting through hundreds or even thousands of possible cities or neighborhoods can be almost impossible. Machine learning can help with this task by analyzing large volumes of data about different locations, finding common characteristics among locations, and grouping those like-attributed locations together. These groups can then be compared to previously successful restaurant locations to help narrow the choices for where to open next. This is exactly the type of scenario the City-Market Clustering experiment can help with. This experiment is a simple, end-to-end model that: 1. Inputs a dataset with cities and their attributes 2. Normalizes the numeric features in the dataset 3. Trains a K-Means Clustering algorithm to group like-attributed cities 4. Assigns a cluster number to each city 5. Outputs the cluster assignments to a dataset to be visualized