تشخیص غیر عرفی غیر پارامتری: یک برنامه کاربردی برای رسانه های اجتماعی و اطلاعات مالی

In this work, we propose a novel framework for causal inference that does not require any assumption about a particular parametric form of the model expressing statistical relationships among the variables of the study and can effectively control a large number of observed factors. We apply our method in order to estimate the causal impact that information posted in social media may have on stock market returns of four big companies. Our results indicate that social media data not only correlate with stock market returns but also influence them.