Cognitive system for Product authentication in CPG industry

For a US based disruptive start-up, we developed a real time cognitive system to authenticate a range of food products like edible oils and alcohol.

Predictive models to determine authenticity of products were built and deployed in the cloud using ML and AI techniques. The end-to-end system, consisting of a proprietary Raman Spectrometer, a mobile application to communicate with the spectrometer, and a processing system deployed in the AWS cloud, predicts authenticity in near real time. The system collects structured and unstructured spectrometer data through a mobile application to build Predictive Models which were deployed on AWS. The system included a cloud-based Decision Engine that utilized the AWS deployed predictive models to make predictions and communicate results back to the user on the mobile device.

The new system significantly eliminated human-centric workflow to less than 5% of existing levels, and delivered breakthrough competitive advantage over alternate solutions currently available.