🛒 Retail & E-commerce · Data Flow
Product Recommendation Engine
How an online store builds 'recommended for you' and 'frequently bought together': click and order data, model training and a fast serving layer.
Drawing diagram…
What this diagram shows
- Clicks, carts and orders are collected as events
- Models are retrained daily in batch
- Recommendations are served from a low-latency cache
Prompt used
Data flow for a recommendation engine: the website and app send view, search, add-to-cart and purchase events to an event stream, which lands in a data lake. A daily training job builds collaborative filtering and 'bought together' models, writes item and user embeddings to a feature store and precomputed lists to Redis. A recommendation API combines them with real-time session events and business rules (in stock, margin) and serves results to product and home pages.
Mermaid code
flowchart LR APP[Website and App] -->|Views, searches, carts, orders| ES[Event Stream] ES --> DL[(Data Lake)] DL -->|Daily| TR[Model Training] TR -->|Embeddings| FS[(Feature Store)] TR -->|Precomputed lists| RC[(Redis Cache)] ES -->|Session events| API[Recommendation API] FS --> API RC --> API CAT[(Catalog: stock, margin)] -->|Business rules| API API -->|Recommended products| APP
Related templates
E-commerce Microservices Architecture
An online store split into microservices: catalog, cart, orders, payments and search, with Kafka events connecting them to shipping and notifications.
Checkout and Payment Sequence
What happens when a shopper clicks Pay: stock is reserved, the payment is authorised, the order is created and stock is released again if payment fails.
Order Lifecycle State Machine
Every status an online order moves through, from placed to delivered, including cancellations, returns and refunds.
Product Catalog Database Schema
A flexible product catalog: categories, products with variants (size, colour), prices, stock per warehouse and images.
Omnichannel Inventory Sync
How stock stays in sync across stores, warehouses and marketplaces so the same item isn't sold twice.
Returns and Refunds Workflow
How an online store handles a return: eligibility, pickup, quality check at the warehouse and the refund or replacement.