Confidential client, name withheld under NDA

AI-Driven Search & Recommendation System for The Client Auction Platform

Quick answer: A Python AI engine behind FastAPI endpoints can add natural language search and personalized bid suggestions to a legacy SQL Server auction site. Bacancy Technology built this for a US collectibles auction platform and its platform in the US.

Outcomes deliveredDelivered in 3 months by a team of 4 developers
30%

Faster lot discovery

Natural language search for lots

20%

More bids on recommended lots

Suggestions based on user behavior

25%

Fewer zero-result searches

Semantic search across varied inputs

Client name withheld under NDA. To honour our non-disclosure agreement and compliance obligations, we describe this client by industry and region only. The project scope, technology and outcomes are shared without details that could identify them.

About the Client

The client is a US online stamp auction platform that runs on SQL Server and its infrastructure. It wanted AI search and recommendations while keeping that infrastructure in place.

The legacy system lacked natural language search and personalized suggestions for bidders. Its data came from large, varied sources, including bidding history, lot descriptions and metadata.

A 4-developer Bacancy Technology team built a Python AI engine that connects through FastAPI without disrupting the existing platform. Engineers cleaned the data and trained semantic search and recommendation models with OpenAI and HuggingFace embeddings. Collectors now search in natural language and get lot and bidding suggestions based on their activity. The modular engine can support image search later.

Client type
Online stamp auction platform
Industry
Collectibles and auction technology
Location
United States
Team
4 developers
Timeline
3 months
Project size
Non-disclosable

Challenges & Solutions

Our AI experts added modern search to a legacy platform without touching its core.

Challenge 1: Integrating AI into environment

New AI features had to run alongside the existing SQL Server and the client infrastructure.

Solution: Our AI experts built a lightweight Python AI engine and exposed it through FastAPI REST endpoints. The platform gained modern features with no disruption to existing operations.

Challenge 2: Handling large and varied data sources

Bidding history, lot descriptions and metadata came in many formats.

Solution: Our data engineers cleaned the bidding history, lot descriptions and metadata. They used OpenAI and Hugging Face embeddings to train semantic search and recommendation models that work across inputs.

Challenge 3: Building personalized search and recommendations

Collectors needed relevant lots and bidding suggestions instead of generic results.

Solution: Our team built AI algorithms that analyze user activity and preferences and return relevant lots and bids in real time. The models keep learning from user behavior.

Challenge 4: Preparing for vision-based lot search

The client wanted to add image search in a later phase.

Solution: Our engineers made the AI engine modular, so it can accept image embeddings from tools such as Google Vision and OpenCV in future releases.

How the Platform Works

The client AI search and recommendation system for stamp auctions

Core Features

  • Natural language searchCustom-trained NLP models understand how collectors describe lots.
  • Personalized recommendationsLot and bid suggestions based on user behavior and item metadata.
  • Secure API integrationFastAPI endpoints connect AI to the legacy platform.
  • Scalable ML pipelineModels are trained and retrained as new bidding data arrives.
  • Ready for visual searchModular design supports image-based lot search later.

The stack behind the AI engine

Backend
Python | FastAPI | Flask
AI and ML
OpenAI API | Hugging Face Transformers | spaCy | scikit-learn
Database
SQL Server
Frontend
HTML | CSS

Ready to start?

2500+ projects delivered by Bacancy Technology

Get access to an experienced team of developers and engineers from Bacancy Technology, handpicked to ace your goals. Kickstart within 48 hours, no-risk trial.

Book A 30 Min Call
14+Years of business experience
1458+Happy customers
30+Countries with happy customers
1050+Agile-enabled employees

More Case Studies

View All Case Studies