Product recommendations. Squeeze more from your online store

Recommender systems (hereinafter PC) analyze the interests of users and try to predict what exactly will be most interesting for a particular user at a given time.

The recommendation system identifies the needs of visitors to your online store and at the right time makes interesting offers to them on the site, increasing the income of the online store due to the increase in conversion, the average check and the frequency of repeated purchases. According to the results of A / B tests, we can expect revenue growth of up to 50%
')
Such services analyze all available information:

1. user behavior on the site,
2. viewed products
3. order history
4. information about him from social networks.

In this article we will consider the main use of recommender systems - personal product recommendations , as well as two cases of connecting a PC to an online store.

There are also trigger e-mail newsletters, search personalization, and other technologies, which we will discuss in the following articles.

How it works

So how do the PC widget define “who is who”?

The fact is that the PC is connected to a large data system called BigData, where preferences, interests, and other various metrics of specific people are stored. Identification occurs by tags recorded in the browser’s cookies.

A new visitor on your site may have already visited other online stores before you, made purchases, looked through products, thus leaving a “trace” behind them. All his actions were saved in BigData under a special label, and this label was saved in the browser cookies. Even if the user has once changed the browser, or has lost a cookie, it is possible to find it in BigData by some parameters of its equipment.

How does it look on the site

In the product card in the Similar goods block there is a block of recommendations, which the system automatically deemed appropriate for the current product. Thus, we do not have to independently indicate the relationship between the goods, the intellectual system itself forms the connection between the goods .



On the main page there is a block of popular products that are most often ordered from your online store.



After placing the order and moving to the cart, the system also generates products suitable for the buyer (you may also be interested in), which are also available for adding to the cart. Thereby increasing the average check , by adding related products.

Product recommendations increase conversion in three main areas.

1. Product recommendations make it easier to navigate the site and increase conversion.
2. Product recommendations form cross-references to product cards, as well as increase the depth of viewing the site and the average session duration , which has a positive effect on positions in search engines.
3. Product recommendations allow you to sell more expensive products or related products with the help of cross-sell and up-sell mechanics.

Cases

Shell Motor Oil Online Store

What has been done: the integration of product recommendations on the main page, in the item card, in the basket.

Result: for the observation period (55 orders, 7 of which contained the recommended goods) about 6.6% of the money came from the service of product recommendations.

Online store of adult goods 18iposle

What has been done: a block of popular products has been introduced on the main page, a block of recommended products in the product card.

Result: exactly 50% of orders contained recommended goods, 26.3% of the money came from the recommendation service.

Online consumer goods store starshop.kz

What has been done: a block of popular products is connected on the main page, a block of similar products is displayed in the product card, a block of goods that may interest a potential buyer is integrated into the shopping cart.

Result: during the month of work, the increase in store revenue ranged from 30% to 50% (compared to the previous month). An increase in the average check was also recorded.

Let's sum up

For the PC is definitely the future. This is the WIN-WIN model, when we give the visitor exactly what he is looking for, of exactly that color and size, at the same time increasing profits from the business.

For our part, we are ready to discuss the connection to the referral system, consultation and information support with the owners of online stores. Interested? Write us!

_{Some materials are taken from the article.}