A Knowledge Representation System for the Indian Stock Market

Bikram Pratim Bhuyan (1) , Vaishnavi Jaiswal , Amar Ramdane Cherif (1)

1 LISV - Laboratoire d'Ingénierie des Systèmes de Versailles

Investors at well-known firms are increasingly becoming interested in stock forecasting as they seek more effective methods to predict market behavior using behavioral finance tools. Accordingly, studies aimed at predicting stock performance are gaining popularity in both academic and business circles. This research aims to develop a knowledge graph-based model for representing stock price movements using fundamental ratios of well-known corporations in India. The paper uses data from 15 ratios taken from the top 50 companies according to market capitalization in India. The data were processed, and different algorithms were used to extract tuples of knowledge from the data. Our technique involves guiding a domain expert through the process of building a knowledge graph. The scripts of the proposed knowledge representation and data could be found here: GitHub. The work can be integrated with a deep learning model for explainable forecasting of stock price.

Domaines: Informatique [cs]

Bikram Pratim Bhuyan, Vaishnavi Jaiswal, Amar Ramdane Cherif. A Knowledge Representation System for the Indian Stock Market. Computers, 2023, 12 (5), pp.90. ⟨10.3390/computers12050090⟩. ⟨hal-04083441⟩