This application leverages curl requests, media APIs, and regular expressions for NLP. The first layer of this application performs the unstructured data sourcing and cleaning. The second layer of this application - currently in development - employs natural language processing for predictive modelling. Financial markets (FX, Equities, Fixed Income, Commodities) are of interest in this project.
Repository Components:
- Application Architecture (forthcoming)
- Unstructured data sourcing script: req.py
- Pre-processing of unstructured data
- Text Search (Rank / Sort)
- Machine Learning and Natural Language Processing (NLP)