Consumer basket analysis methods

    “What do our customers buy?” The answer to this question allows you to take a step (and sometimes a triple jump) in the direction of customer focus and business growth. We will analyze how to correctly and efficiently resolve this issue using numbers. I will make a reservation right away that we are considering the analytics of our own database. That is, we have a product line, customers and a transaction database, which reflects which client that bought. Additional data about customers (social networks, questionnaires), products (classifier, attributes) and orders (time, money, costs) will only benefit. We will move towards narrowing the audience, targeting.

    Shopping structure

    This is the simplest analysis. Fill in the table and draw a diagram with the shares of transactions by product or product category. In practice, the time-consuming task is the classification of goods. It’s also an important question that we consider: the share of customers, the share of transactions or the share of money.

    User group profile

    Now we want to determine the food preferences of the selected group of customers (men / women, visitors on Monday morning, etc.). We can look at the structure of purchases again, but it is much more interesting to see the difference in purchases of this group. To do this, we build a profile: the purchase structure for the entire base (general population) and the study group (sample). And compare these structures. For clarity, you can enter Indicator - the share of the product for the subgroup subgroup divided by the share of the same product in the purchases of all customers. If indicator is significantly greater than 1, then this is a characteristic product for the subgroup and vice versa. if you do not touch on the issue of representativeness, then only fractions are used from mathematics. The picture shows that the 2nd product is typical for the studied group and products 1 and 5 are not typical.

    A profile can also be built both by the number of customers, and by the number of transactions (orders) or money.

    Recommendation system

    We narrow the audience down to one client and create a system of personal recommendations. That is, we notice (of course, analytically) that the purchase of product A entails the purchase of B with a high probability. A joint purchase of C and D (although such a combination is not often found) entails the purchase of E. With a sufficient number of such rules, with proper automatic construction and ordering, we get recommendations for each individual, but more on that in future posts.

    This article is on my blog.

    Also popular now: