E-shops need to be able to learn from their users, collecting data about their tastes and preferences.
Over time and with enough data, we can use machine learning algorithms to perform useful analysis and deliver meaningful recommendations. Other users’ inputs can also improve the results, enabling the system to be retrained periodically.
Roughly the steps of this process are outlined below:
Step 1: Combines data from purchases, wish lists, shopping cart
Step 2: Uses collaborative filtering and product similarity for recommendations
Step 3: Exposes predictions to customers when browsing or buying
We can recommend relative products, products that might interest a visitor, products that have been purchased from a customer that are now on sale.
We can use recommendations in various places/zones/areas on an E-commerce site.
MAIN PAGE RECOMMENDATIONS
The main page is the first thing than users coming from direct traffic see when they visit a site. As these visitors don’t necessarily come looking for anything in specific, main page recommendations serve the purpose of informing customers about latest deals and discounts, and showcasing product portfolio.
POPULAR PRODUCTS ON MAIN PAGE
This is a very basic, yet powerful recommendation logic that works splendidly in nearly all eCommerce stores. The popularity of a product is determined most easily by the number of times it has been purchased (weighted with how long it’s been available).
We could also incorporate other logic/event, in order to serve even more accurate recommendations (clicks, views, add-to-cart events, etc.)
RATING-BASED RECOMMENDATIONS
Another critical indicator of popularity can be high user ratings on specific products. Those products will appear on the main page and will be different for each user. It is worth pointing out personalized recommendations require considerable amounts of behavioral data on users, which a system does not have in the case of new visitors. It is something that will benefit the store owner when ratings appear on the system.
RECOMMENDATIONS ON THE PRODUCT PAGE
The product page is where visitors find detailed descriptions of a product and its features and can choose to add it to their cart or order it right away.
The main aim of recommendations on these pages is to display the most relevant items and therefore provide a “next step” in their search to the visitor and keep them browsing your site.
In most cases, the more time they spend in an e-shop, the higher the chances they’ll actually make a purchase. Both time spent on site, and pages viewed have good, positive correlations with conversions. There are various recommendations that already exist and can be taken to the next level with AI algorithms.
• Similar Products / Cross Sell Suggestions
• Products from the same brand
• Products from the same category
• Customer who bought this viewed this
• Collaborative recommendation – a recommendation logic that basically determines the similarity of two products by looking at how often they’re present together
CART RECOMMENDATIONS
Recommending products similar, or related to the content of the visitor’s cart on cart pages can be a very effective way of boosting average order quantities and values.
Cart page recommendations reach the customer in a very favorable psychological state, where he most likely already decided to make a purchase, therefore he’ll be more willing to say yes to further offers. There are a couple of recommendation logics that are a very good fit for this task.
In our experience, cart page recommendations tend to provide well above average results.