FTSE All share index stocks are classified by ICB classification system which groups them in Industry,Super Sector, Sector and Sub Sector based on its business activities. Brief bussiness activity/summary is collected for all stocks in FTSE All share index and topics from them is extracted for each sub sector.
Topic analysis is done for each subsector. The document is a concatenated text containing bussiness descriptions of all stocks in a subsector.
The note book explores the corpus data using NLP with focus on answering these questions - How well does each sub sector stocks match ? Are there any outliers/misclassification ? etc.