Thesis Proposal

AI has long been applied to the problem of predicting nancial markets. Recently, developments in both AI and nancial economics have opened up the possibility for close collaboration between the two elds. First, a line of economics research has emerged that uses AI market forecasting as a form of applied econometrics. Just as importantly, an entirely new source of nancially relevant data has become available and amenable to computational analysis: text. Access to text data { and the associated AI techniques for analyzing it { not only hold out the hope of improved prediction on the AI side, but also enable nancial economics to ask new kinds of questions about how markets react to events. I propose a line of research that develops a set of AI tools, speciically adapted to nancial markets, to exploit this convergence for both economics and AI. This research has three main elements. The rst thread takes representations from technical analysis { a semi-rigorous method of nancial analysis { and combines them with search techniques and rule learning methods from AI to produce domain speciic prediction algorithms. Second, I plan to adapt text classiication and related techniques for nancial market forecasting based on text from internet stock chat boards and news stories. And nally, I plan to adapt traditional economics techniques such as event studies to take advantage of the possibilities that text data ooers.