Project Synopsis
A large cosmetics retailer wanted to roll out a loyalty program for its customers. The complication was that their product were sold by large retail stores and they did not have direct access to their customers. They wanted a solution to help them connect with their customers and target promotions based on their past purchases.
The developed solution was expected to have the following features:
- Ability to recognize this brand’s products from receipts including mixed purchases.
- Solution to build predictive models based on customer purchases to match customers with new offers and products.
- Automatic validation of the expenses against the submitted expense claim.
Rare Mile Solution
We designed and developed the complete solution using our text analytics engine and IP. The delivered solution had the following features:
- Extraction of brand’s products from mobile picture of a receipt including over all amount spent, amount spent on brand’s products, products purchased.
- Building machine learning solution to predict customer’s related purchases and offers of interest.
- OCR recognition and validation of extracted text
- Algorithms for image enhancements and clean up before processing
Project Highlights
- Created an ability to recognize non conclusive OCR scan by augmenting them with statistical model
- Developed a mobile application to capture shake free, sharply focused images
- Created new algorithms for processing receipts which could not be read by the OCR engine in the first pass
- Dashboard with targeting information for offers.
