Market Basket Analysis - Data Mining For Retailers

Market basket analysis (MBA or association-rule mining) is a research technique for retailers that is used to discover customer purchasing patterns. The information obtained from the analysis is used in forming marketing, sales, service, and operation strategies.

If you shop at Amazon.com, then you’ve seen recommendations like . . . ,“ Customers who bought this item also bought. . .”, . . .,“ We also recommend. . .”, “ Buy these two items together and save . . . .” Amazon.com has become extremely successful by using this analytical marketing strategy to generate incremental business through product promotion, cross-selling and product placement.

This particular technique, known as Affinity Analysis or Market Basket Analysis (MBA), is used to determine the likelihood that a set of items will be bought together. There are natural product affinities in the retail environment. For example, people who buy cold medicine typically buy Kleenex and vitamin C tablets. People who buy hamburger patties frequently buy hamburger buns, ketchup and mustard. Although some product affinities are obvious, others are often unexpected. A classic example involves an affinity between diapers and beer.

Progressive companies use these techniques to develop promotions and generate incremental sales. Unfortunately, this procedure requires large processing capabilities to analyze transaction-level (individual market basket) data. Our servers and algorithms can quickly define the likelihood of two (or more) items being purchased together. We can identify the products that drive customers to your store and that should always be in stock. We can also analyze the contents of each basket and classify the shopping trip into a category: weekly grocery trip, special occasion, etc. Finally, we can perform store-to-store comparisons based on units sold per customer, revenue per transaction, number of items per basket, etc.

Market Basket Analysis can revolutionize your retail business and gather important information about your customers and their behaviors. This information can then be leveraged to provide better assortments, design better planograms and devise attractive promotions that generate more traffic and greater profits.