Project Description
A shopping list management solution with a rather catchy and suggestive name, The Sortifier mobile app helps users manage all their expenses in one place by scanning (taking a photo) of their receipts.
Employing Python for the backend side, neural networks (Random Forest) and a word-embedding linguistic model from Facebook (FastText), the app stands out through its ability of learning new words, data and product classification methods.
Technical Description
- Trainable OCR, language and classification ML models for extracting and processing text from images
- React Native mobile application for image capturing and visualizing results
- Backend software for the user, machine learning and data management (PostgreSQL)
- AWS cloud storage for real-time data retrieval and update
Project beneficiaries
- End-user customer, interested in learning insight of their expenses
- Banks, for software integration with their mobile banking apps
- Product providers, for sharing their offers as trusted partners
Future Developments
- Continuous learning model improvements through data corrections from users
- Exploring other expense segmentation possibilities
- Integrate users’ feedback regarding their necessities
- Create a B2B-only version for payments-invoice correlation
