From the course: Advanced Data Processing: Batch, Real-Time, and Cloud Architectures for AI

Unlock this course with a free trial

Join today to access over 25,400 courses taught by industry experts.

Real-time AI architecture example: Problem

Real-time AI architecture example: Problem

From the course: Advanced Data Processing: Batch, Real-Time, and Cloud Architectures for AI

Start my 1-month free trial Buy for my team

Real-time AI architecture example: Problem

“

- [Instructor] Having discussed the key considerations for real-time AI architectures, let's now build an architecture for a real-time use case. The use case is called Dynamic Discounts. Imagine an online store that sells various products to customers. The store wants to offer discounts to help sell products. It wants to dynamically change the discount rate for products based on customer demand, available inventory, and competitor pricing. For example, if the inventory goes up, discounts go up. If demand goes up, discounts go down. Let's discuss this use case in detail. This is a classification use case to predict a target discount rate, like 10%, 20%, or 40%. This can also be modeled as a regression use case. The use case has several input data sources. Sales transactions are available in real-time through a Kafka queue. Current inventory of products is available through an RDBMS. Competitor pricing is published by a real-time competition analysis application through a Kafka queue…

Contents