Detection of financial rumors using big data analytics: the case of the Bombay Stock Exchange

Market regulators and stock exchanges around the globe need to ensure that investors trade in a fair and efficient manner. The main motive for market surveillance is to make the market more efficient and free from rouge elements. Identification of financial rumors is vital for orderly functioning of the stock market. Social media platforms allow spread of unverified information to a large mass quickly due to their interconnected nature and large number of participating members. Due to the deluge of data over various media channels including social media, manual scanning of financial rumors is inefficient. This necessitates the use of a big data infrastructure for collection, storage, and analysis of financial news related data. In this paper, we introduce a framework for automated detection of financial rumors using big data. Our framework is based on extant research on knowledge-based discovery in databases and detection of fraudulent financial activities. We describe an in-depth descriptive case study of the world's fastest stock exchange, the Bombay Stock Exchange. Through the case, we highlight the importance of analytics for detection of financial rumors and the importance of the big data infrastructure to carry out such a task. We identify several critical factors that lead to successful identification of financial rumors. We believe the framework can be used by market regulators, stock exchanges, and security research agencies to identify information-based market manipulation using a systematic data-driven approach over a big data infrastructure.