Boost your revenue and AOV with AI-powered Product recommendations. Not only do recommendations solve the task of putting the right product in front of the right customer, but it also improves the store navigation for customers browsing things they are, or could be, interested in. Our recommendations drive an increase in AOV and revenue that is often noticeable within a few weeks, along with increase in engagement and time spent in the store.
Customers that interacts with smart product recommendations are more likely to convert, and spend more on average.
Product recommendations drive additional revenue through a smart, non-intrusive, way to introduce products that are likely to be of interest to the visitor. It allows merchants to showcase more of their product catalog to their visitors and the personalized touch increase the customer experience.
Engage runs on a number of AI models that can be combined and used in combination with other, non-smart, models to design almost any type of product recommendation. Use our solution to:
- Display products that are similar in context. Our AI selects the products that are relevant, and similar, to each other.
- Display products that are likely to sell together. Based on customers browsing and purchase history, our AI recommends products that the visitor is likely to buy.
- Display products that are visually similar. Our AI index your product catalog based on visual similarity and derives the ones that are most similar.
- Display recently viewed products, either during the current session or when the visitor returns to your store.
- Display a set of products derived through logic and rules, and sort them based on what is most likely to sell, did sell most in the past or are most similar.
Product recommendations are perfectly suited for automation. Not only is it tedious work to select products for cross sell and up sell, the performance of manual product recommendations are generally worse than the automated ones that are based on actual data. Furthermore, the update frequency is constrained using a manual update approach whereas automated recommendations can be updated according to events in the store.
Our product recommendation solution utilize our tracking system to capture and measure the effectiveness of the recommendations. See how your models perform and follow the improvements over time. We measure and report on:
- Generated revenue from recommendations
- AOV and AOV change when using recommendations
- Repurchase rate for customers interacting with recommendations
- Conversion rate for visitors interacting with recommendations
The product recommendations can be customized to fit any need. May it be design adjustments, rules, filters or sort order. Most can be achieved out of the box, but we are also always here to help should you require some extra support.
This destination requires one of the following sources/plugins to be installed and active,
The data requirements varies depending on the type of product recommendation. Product similarity models generally only requires product data, while any recommendations based on behavioural data requires that to be available.
Engage integrates to major e-commerce platforms such as Shopify, WooCommerce and Prestashop. Which makes it easy to share the data required. In addition, you may share data using our APIs, a Google Product Feed or any of the other listed source integrations.
A common question we get is how much data is required to run proper recommendations. And in most cases we can get started right away with only the data available via the integrations. Behavioural based models improve with more data, but this can be added along the way. For similarity models, the product data is typically enough to get off to a good start.