Case Study
BeerBoard – NLP Based PLU Automation
Client
US-based Beverage Enterprise

Technology
Have a similar project in mind?




Business Challenges
The client synthesizes Poured and Sold data available in a bar and give insights for their customer through SmartBar app. Due to unavoidable reasons, on a regular basis, the PLU(Product lookup) available at POS and SmartBar is not in Sync, which is leading to erroneous capturing of sold data in SmartBar.
Our Solution
We proposed to build an NLP based Machine learning algorithm which will identify incorrectly mapped PLU at POS and do correct mapping of PLU in SmartBar. It identifies the mismatches and
automatically suggests the correct mapping and sent will for experts review
Salient Features
- NLP (Natural Language processing ) technique in identifying Miss mapped Products
- The Algorithm gives 80% of detection accuracy,
- Algorithm improves the accuracy by retraining using historic data.
- Reduces human intervention by 10x times
- Adaptive learning from experts correction.
Product / Service Description
We Built a model using machine learning algorithms and NLP Techniques. An application was developed in Python for Syncing PLU between POS and SmartBar & deployed on AWS for scalability. The Algorithm gives 80% of detection accuracy, and it can be further improved over some time by training the algorithm.
Result
Highly accurate results

The client wants web application for bar admins to track the bar performance and work order details of their respective

The client wants to completely redesign their mobile application with certain feature enhancements for iOS and Android

BeerBoard requires various dynamic content templates to display beer menu, advertisements, etc. at bars, pubs, and