Chateau Winery (A): Unsupervised Learning

Case Solution

Srikant M. Datar, Caitlin N. Bowler
Harvard Business School ()

This case follows Bill Booth, a marketing manager for an unsupervised regional wine retailer, applying data on his customers’ purchases to better understand their preferences. Specifically, he uses the Kmeans grouping technique to identify groups of customers who have bought any number of 32 specific Stand “Offers” during the year, differentiated by type of wine and country of origin and a minimum number of bottles to buy. The insights from this analysis can help you understand deal issues that may contribute to the development of new deals in the future. Topics include: unsupervised learning; Similarity and closeness; K stands for clustering, with measures for Euclidean distance and cosine similarity; Gaussian mixture models; Interpret the groupings.

We don‘t have the case solution, but we pay up to $50 for yours!

  • Set a reminder to receive an email after your university‘s case study deadline.
  • Upload your case study solution. We will review it for quality.
  • Get your money via PayPal or to your bank account.