Causality plays a critical role in people’s daily behavior and decision-making. It is of great interest in many domains, including finance, where understanding causal relationships can provide significant opportunities for economic benefits. Much interesting information appears as natural language text, which must be processed and analyzed to derive valuable knowledge. This project aims to build a financial causality knowledge base by analyzing a large online financial text trying to capture the causal strength of different finance-related events. The rules in this knowledge base can be used to predict financial events and generate alerts in financial trading.
The goal of this project is to build a knowledge base (KB) of financial events, and their causal relationships, that could be useful for many downstream applications. Such a knowledge base can be used to improve the efficiency of financial transactions. Consider a new event such as “US bombs Syria” occurs and a trader needs to list all possible resulting events. Using the knowledge base the trader can find these events rapidly and comprehensively, saving him more time to take the adequate measures. Additionally, financial editors can generate a summary of the news using automatic, KB-based text generation tools, alleviating the effort involved in writing the news from scratch. A financial causal knowledge base could be useful for several such scenarios.