Contact Us

Price comparison for e-commerce, a woman uses a laptop to shop online

Price Comparison

CHALLENGE

WikiBuy is an online shop assistant that integrates as a browser add-on. They automatically make an online search for any product you are currently viewing and looks for a better price. The challenge asks how might we create a superior product matching system that includes large quantities of products but also product attributes and value.

SOLUTION

Developed a chrome extension for mobile web browsers that extract on-site data, mapping to product information from third-party sites. That data was processed using Random Forrest and NLP classification models to output lower price product comparisons. This new approach leverages a real-time human-in-the-loop system to maximize accuracy.

OUTCOME

Created a system that achieves 90-95% accuracy, 450% better than previous techniques.

NLP
Random Forest Technique
Machine Learning

Price Comparison

CHALLENGE

WikiBuy is an online shop assistant that integrates as a browser add-on. They automatically make an online search for any product you are currently viewing and looks for a better price. The challenge asks how might we create a superior product matching system that includes large quantities of products but also product attributes and value.

SOLUTION

Developed a chrome extension for mobile web browsers that extract on-site data, mapping to product information from third-party sites. That data was processed using Random Forrest and NLP classification models to output lower price product comparisons. This new approach leverages a real-time human-in-the-loop system to maximize accuracy.

OUTCOME

Created a system that achieves 90-95% accuracy, 450% better than previous techniques.

NLP
Random Forest Technique
Machine Learning

Download the Case Study

More case studies
The Waste Management Early Alert Rear Safety Device
Object Detection

Waste Management Early Alert Rear Safety Device

Realty Austin Case Study cover
Recommendation Modeling

Case Study: Realty Austin

Realty Austin needed to improve the available housing recommendations sent to its customers via email. Find out how KUNGFU.AI created the system that generated significantly improved email click-through rates.
Case Study: Natural Language Processing for Audio Search, a broadcaster records a podcast that will then be indexed and archived with NLP
Natural Language Processing (NLP)

NLP for Audio Search