E-commerce Recommendations engine that is unified with Apptus eSales Search, Navigation and Ads capabilities
Recommendations represent an important component of an e-commerce site. Reports show that up to 27% of the revenue in digital retailing may come from Recommendations. Shoppers that have clicked on Recommendations are 4.5 times more likely to create a shopping cart, and 4.5 times more likely to complete their purchase. They also spend 5 times as long per visit.
Apptus eSales offers a holistic approach for the four pillars of e-commerce: Search, Recommendations, Navigation and Ads. The four capabilities are integrated in a unified set of algorithms and enrich each other with behavioural data.
By working in synergy, Apptus eSales Recommendations avoids cannibalisation effects that otherwise inherently occur. This is a strength contrasting to many competing tools, which often bear only a singular focus. Apptus eSales offers a unique edge to your site.
Apptus eSales provides real-time recommendations for every step of your customer’s journey.
It suggests products based on the collective interest of all your site visitors and in correlation to the visitor’s click-and purchase-history.
Personalised recommendations are based on what the current visitor has clicked on or bought previously, on what other customers have bought, as well as on items currently in the cart or that were previously abandoned.
All Recommendations panels can be filtered to only include particular type of products.
Apptus eSales Recommendations engine is designed to feed the e-commerce site with both alternatives as well as supplementary product recommendations, to increase the average order value.
The Recommendations capability can be used omnichannel.
This is a site-wide type of recommendations displaying real-time popular and trending products.
Suitable types of pages for using these recommendations include: the start page welcoming the visitor to the site, category pages showing popular products for the specific type of products, as well as the No Results page.
These are customer based recommendations of products from the customer’s abandoned cart.
Apptus eSales 'remembers' the visitor's previous intentions and gives a new chance for these products.
Another type of customer-based recommendations of recently viewed products, which help the customer navigate and find the products of interest.
This works as a reminder for previous viewed items and allows the customer to return to the product, after they have viewed similar products.
The traditional and well-used recommendations those who bought also bought is available in Apptus eSales to use on a product detail page.
Inspiration from people with similar tastes is one of the main drivers for purchases.
A more advanced variant of product recommendations is the recommendation based on product. This uses visitors’ behaviour from the whole site to select product recommendations.
Recommendations for both alternatives and supplementary products to the product of interest are provided.
While the visitor is reviewing the cart or has started to check out there is a golden opportunity to recommend products based on the items in the cart.
Cart-based recommendations are used for both cross-sell and up-sell related products.
Another way to use cart-based recommendations is to push over certain order values, by offering for example free shipping or discounts while recommending products with values that pass the threshold.
More often that we think, customers decide what goes together.
Inspire your visitors by offering them products that other people bought after looking at the same product.
Recommend products that people found after viewing the same product.
This inspiration will benefit your visitors and increase your sales.
We’re looking forward to doing even more testing and use of automation in the future, especially now that we’ve seen how well it can work!
Apptus eSales has given us the ability to use real-time customer data as the fuel for behavioural search, faceted navigation and trend sensitive contextual recommendations.
