LogoLogo
👋 Get in touch⭐️ GitHub
  • Welcome
  • Getting Started
    • Why Superlinked?
    • Setup Superlinked
    • Basic Building Blocks
  • Run in Production
    • Overview
    • Setup Superlinked Server
      • Configuring your app
      • Interacting with app via API
    • Supported Vector Databases
      • Redis
      • Mongo DB
      • Qdrant
  • Concepts
    • Overview
    • Combining Multiple Embeddings for Better Retrieval Outcomes
    • Dynamic Parameters/Query Time weights
  • Reference
    • Overview
    • Changelog
    • Components
      • Dag
        • Period Time
      • Parser
        • Json Parser
        • Dataframe Parser
        • Data Parser
      • Schema
        • Id Schema Object
        • Schema Object
        • Schema
        • Event Schema Object
        • Event Schema
      • App
        • App
        • Interactive
          • Interactive App
        • Online
          • Online App
        • Rest
          • Rest App
        • In Memory
          • In Memory App
      • Space
        • Custom Space
        • Exception
        • Has Space Field Set
        • Number Space
        • Image Space Field Set
        • Text Similarity Space
        • Input Aggregation Mode
        • Image Space
        • Recency Space
        • Space Field Set
        • Categorical Similarity Space
        • Space
      • Executor
        • Exception
        • Executor
        • Interactive
          • Interactive Executor
        • Rest
          • Rest Descriptor
          • Rest Handler
          • Rest Executor
          • Rest Configuration
        • In Memory
          • In Memory Executor
        • Query
          • Query Executor
      • Registry
        • Superlinked Registry
        • Exception
      • Storage
        • Mongo Db Vector Database
        • Vector Database
        • Redis Vector Database
        • In Memory Vector Database
        • Qdrant Vector Database
      • Index
        • Effect
        • Index
        • Util
          • Aggregation Node Util
          • Event Aggregation Node Util
          • Event Aggregation Effect Group
          • Effect With Referenced Schema Object
          • Aggregation Effect Group
      • Source
        • Data Loader Source
        • Interactive Source
        • Types
        • In Memory Source
        • Source
        • Rest Source
      • Query
        • Param
        • Typed Param
        • Query
        • Query Weighting
        • Query Descriptor
        • Nlq Param Evaluator
        • Space Weight Param Info
        • Query Param Information
        • Query Filters
        • Nlq Pydantic Model Builder
        • Clause Params
        • Param Evaluator
        • Query Mixin
        • Query Param Value Setter
        • Query Filter Validator
        • Natural Language Query Param Handler
        • Query Filter Information
        • Query Vector Factory
        • Query Clause
        • Result
        • Query Result Converter
          • Default Query Result Converter
          • Query Result Converter
          • Serializable Query Result Converter
        • Predicate
          • Binary Op
          • Query Predicate
          • Binary Predicate
        • Query Clause
          • Similar Filter Clause
          • Overriden Now Clause
          • Looks Like Filter Clause
          • Space Weight Map
          • Nlq System Prompt Clause
          • Nlq Clause
          • Radius Clause
          • Weight By Space Clause
          • Base Looks Like Filter Clause
          • Limit Clause
          • Select Clause
          • Looks Like Filter Clause Weights By Space
          • Single Value Param Query Clause
          • Hard Filter Clause
          • Query Clause
        • Nlq
          • Nlq Compatible Clause Handler
          • Exception
          • Nlq Clause Collector
          • Nlq Handler
          • Suggestion
            • Query Suggestion Model
            • Query Suggestions Prompt Builder
          • Param Filler
            • Query Param Model Validator
            • Query Param Model Validator Info
            • Query Param Model Builder
            • Query Param Prompt Builder
            • Nlq Annotation
            • Templates
  • Recipes
    • Overview
    • Multi-Modal Semantic Search
      • Hotel Search
    • Recommendation System
      • E-Commerce RecSys
  • Tutorials
    • Overview
    • Semantic Search - News
    • Semantic Search - Movies
    • Semantic Search - Product Images & Descriptions
    • RecSys - Ecommerce
    • RAG - HR
    • Analytics - User Acquisition
    • Analytics - Keyword Expansion
  • Help & FAQ
    • Logging
    • Support
    • Discussion
  • Policies
    • Terms of Use
    • Privacy Policy
Powered by GitBook
On this page
  • Overview
  • How does it work ?
  • Key features
  • Modalities:
  • Hard-filters
  • Item2vec
  • Real-Time Session-Based Recommendations
  • Get in touch and build this on your own data!

Was this helpful?

Edit on GitHub
  1. Recipes
  2. Recommendation System

E-Commerce RecSys

PreviousRecommendation SystemNextOverview

Last updated 1 month ago

Was this helpful?

🚀 Try it out:

Overview

In modern retail and e-commerce websites, personalized and immediate product recommendations can significantly boost customer engagement and drive sales conversions. In this demo, we showcase an example of such a website that uses Superlinked's ability to do real time recommendations. When a user lands on the store’s website, they are greeted by a web interface displaying various products. As they move around the page, whether clicking product details, scrolling through suggested items, or switching categories, every interaction is tracked in real time.

These live signals help build a continuously updated profile of the user’s current interests. The system then quickly refreshes its recommendations to reflect the user’s changing intrests, so new and similar items appear without delay. This approach allows retailers to show the right products at the right time, enhancing the shopping experience and increasing the likelihood of a purchase.

Additionally, we use which introduces a collaborative aspect by capturing product relationships from collective user interactions. All of these approaches showcase how we can leverage Superlinked in an e-commerce application to deliver real-time, session-based recommendations. It is adaptable to your own product data as well, so you can tailor this setup to your specific product relationships and consumer behaviour.

How does it work ?

Key features

  • Example of how to train item2vec on your event data: - Use events data to extract custom product realtions.

  • Events based system: - Have a session based recommendation that adjust recommendations in realtime while user surfs the site.

  • Multi modal features: - Support images, text and categories out of the box with SL.

image

Modalities:

  • Images product images

  • Text product description

  • Categories product type, brand, category

  • Numbers product popularity, price.

Hard-filters

  • Stock - use is_active indicator that will make sure only in stock products are recommended.

The user events reach a Wrapper API, which sits on top of the main Superlinked server. It:

  • Records which products users click or view.

  • Builds and updates a live session context that captures the user’s evolving interests.

  • Fetches updated recommendations from the vector database (e.g., Redis) based on these interactions.

Under the hood, the Superlinked server connects to a vector database (Redis in this example). Each product is stored with multi-modal embeddings that include images, descriptions, categories, and numeric properties.

Item2vec

To enhance these recommendations, the system leverages an item2vec model trained on user event data. For instance, if many shoppers who click Product A also end up exploring Product B, item2vec embeddings capture that relationship, increasing B’s rank when someone else shows interest in A. You can train your own item2vec model using the provided scripts and adapt it to your data.

Real-Time Session-Based Recommendations

As the user continues to click and browse, the system instantly:

  • Updates the session context in the Wrapper API.

  • Runs fresh queries to the vector database with each new interaction.

  • Sends back updated recommendations to the UI, so the user sees new suggestions without reloading the page.

If the user starts exploring a particular category, brand, or price range, the system tailors the recommended items accordingly, keeping the shopping experience engaging and personalized. Because the system processes events as they happen, shoppers get the sense that the site is learning their preferences in real time. Highly relevant products show up first, while items that are somewhat related appear further down. This approach can boost engagement and sales, as visitors are guided toward products that align with their interests.

Get in touch and build this on your own data!

We will soon publish the repo so you can host an app like this yourself, however if you want early access in the meantime, please contact our developer realtions team at:filip@superlinked.com

🚀 Try it out:

e-commerce-recsys-recipe.superlinked.io
e-commerce-recsys-recipe.superlinked.io
item2vec