AI BriefingFacial Recognition and Hyper-Personalized Kiosks — Isn't a Hackathon Enough?
Key point
A team of non-developers from Kakaopay used **AWS Gen AI** to build a facial recognition-based hyper-personalized kiosk, winning 3rd place at a hackathon.
Details
Team 'Face Five', consisting of 5 non-developers from Kakaopay's technical support team, took 3rd place at the 2nd Kakaopay Hackathon using AWS Gen AI. To overcome the limits of their development capabilities, they chose a strategy of focusing on 'what to develop'—the planning and impact of the idea—rather than the technical implementation itself.
The solution is a facial recognition-based hyper-personalized kiosk that provides customer identification, customized menu recommendations, and sales analysis for store owners. Using AWS Bedrock and OpenSearch, they implemented facial recognition and personalized recommendation features, designing the system with the goal of innovating and scaling offline payment services.
The system's structure receives customer information collected at the kiosk via API Gateway and stores it in RDS, S3, and OpenSearch. It recognizes the customer's facial image to recommend menus combining purchase history, weather, and regional information, and analyzes payment data to provide marketing strategies to store owners.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
GS Retail and AWS Enhance GS SHOP Search and Recommendation Development Process with AI-DLCImproving OpenSearch Search Quality for AI Agents (Part 2)
Booking.com Reveals Why It Chose Weaviate Over OpenSearch as Its Vector DBAWS Weekly News: EC2 Application Status Checks, IAM Role Manager, OpenAI Daybreak on Amazon Bedrock, and More (August 17, 2026)