Affinity analysis and association rule learning* encompasses a broad set of analytics techniques aimed at uncovering the associations and connections between specific objects: these might be visitors to your website (customers or audience), products in your store, or content items on your media site.
In retail, affinity analysis is used to perform market basket analysis, in which retailers seek to understand the purchase behavior of customers. This information can then be used for purposes of cross-selling and up-selling, in addition to influencing sales promotions, loyalty programs, store design, and discount plans.
In a market basket analysis, you look to see if there are combinations of products that frequently co-occur in transactions. For example, people who buy chocolate compound and molds, also tend to buy wrapping paper and strings (as a high proportion of them are planning to prepare a goody bag of chocolates).
A retailer can use this information to inform:
- Store layout (put products that co-occur together close to one another, to improve the customer shopping experience)
- Marketing (e.g. target customers who buy flour with offers on eggs, to encourage them to spend more on their shopping basket).
Online retailers and publishers can use this type of analysis to:
- Inform the placement of content items on their media sites, or products in their catalog.
- Drive recommendation engines (like Amazon’s customers who bought this product also bought these products…)
- Deliver targeted marketing (e.g. emailing customers who bought products specific products with other products and offers on those products that are likely to be interesting to them).
Market basket analysis can be used to divide customers into groups. A company could look at what other items people purchase along with eggs, and classify them as baking a cake (if they are buying eggs along with flour and sugar) or making omelets (if they are buying eggs along with bacon and cheese). This identification could then be used to drive other programs. Similarly, it can be used to divide products into natural groups. A company could look at what products are most frequently sold together and align their category management around these cliques.
*Association rule learning is a method for discovering interesting relations between variables in large databases. It is intended to identify strong rules discovered in databases using some measures of interestedness. Based on the concept of strong rules, Rakesh Agarwal introduced association rules for discovering regularities between products in large-scale transaction data recorded by point-of-sale (P.O.S.) systems in supermarkets.