Skip to main content

Authors: Manish Jha, Jialin Qian, Michael Weber, Baozhong Yang


Wecreate afirm-level ChatGPTinvestmentscore, based onconference calls, that mea sures managers’ anticipated changes in capital expenditures. We validate the score with interpretable textual content and its strong correlation with CFO survey responses. The investment score predicts future capital expenditure for up to nine quarters, controlling for Tobin’s q and other determinants, implying the investment score provides incremen tal information about firms’ future investment opportunities. The investment score also separately forecasts future total, intangible, and R&D investments. High-investment-score f irmsexperience significant negative future abnormal returns. We demonstrate ChatGPT’s applicability to measure other policies, such as dividends and employment.

Scroll to Top