Recommendations
Our product recommendations powered by Loomi AI enhance your website with a modern technique that tailors content to your customers as they shop. By analyzing customer behavior and product details through statistics, rules, or machine learning, these systems provide personalized suggestions that:
- Increase engagement.
- Foster brand loyalty.
- Encourage customers to purchase additional or related products.
This is a Standard tier feature powered by Loomi AI.
Example of recommendations on a website showing a panel with related products.
Dictionary
In the rest of this manual, we use the following phrases:
| User | Visitor, potential customer, or customer of your web page generating events. |
| Item | Product users can buy (these terms are used as synonyms). |
| Personalization | The effect of treating each user individually. For example, design texts or colors using Jinja or recommend relevant items to users according to preference. |
| Recommender system | Any approach to choosing items for users, usually in a personalized way. It is also known as the “recommendation model” or the “recommender system (RS).” |
| Placement | The location within the webpage where you can integrate recommendations, such as the homepage, product detail, or basket. |
| Engine | Deployed RS as a service with a unique ID. This ID can be found as the last part of the URL when you view the RS model in Bloomreach Engagement. For more information, see Where to find the ID campaign_id. |
| Fallback | Any (usually non-personalized) recommendation strategy when the main engine fails. A typical situation is when the engine is broken, or a new user appears (so no data has been tracked). |
| Similarity score | A number between 0 and 1 that expresses the similarity between 2 items. |
| Top N items | An ordered list of the top N items ranked by relevance based on the criteria or model used to generate the recommendations. |
| Interaction | The connection between user and item represented as foursome {user, item, time, action}. |
An example of interaction would look like this:
| user | item | time | action |
|---|---|---|---|
| user_123 | item_45 | 2019-01-01-12:00:00 | view_item |
Recommendation systems
We can define the recommendation problem in the e-commerce world as follows: “Given all data about users and items (metadata, interactions), find the best items for a given user to recommend that will maximize metric relevant for the business.”
Most of Bloomreach Engagement's algorithms are based either on catalog metadata (such as description or categories) or collected user-item interactions (events like purchase_item or view_item).
Recommendation systems can be divided into 4 segments according to their ability of personalization and whether they are based on some simple heuristics (rule-based) or machine learning (ML) algorithm (artificial intelligence (AI) model). For details, review the table below.
| Rule based | AI or ML models | |
|---|---|---|
| Non-personalized | Simple statistical methods of searching for the best items suitable for everyone. For example, top-selling or brand-new items. | Trained AI model mostly on catalog metadata. For example, attributes matching, text model, image model, and items bought together. |
| Personalized | Simple statistical methods are executed individually for each customer, such as analyzing last-seen items and recent interactions. | Trained AI model on user-item interactions, usually in combination with other RS. For example, collaborative filtering and factorization. |
Note
For all ML- and AI-based models where relevancy is calculated, the items are ordered based on it.
Related articles
Review more articles related to product recommendations.
Updated about 2 months ago