Analytical Approaches to Macroeconomic Forecasting: A Study of Profits through Machine Learning and Deep Learning

Giacoman Favela, Ana K.

Student Work

Analytical Approaches to Macroeconomic Forecasting: A Study of Profits through Machine Learning and Deep Learning

Öffentlich

With a basis on the analytical framework of Levy and Kalecki’s Corporate Profits Equation, this MQP uses Machine Learning and Deep Learning to provide a forecast for aggregate corporate profits in the United States. The tool used to deliver this forecast was the RapidMiner Software and the data source was the Federal Reserve Bank of St. Louis. The independent variable was Aggregate Profits for the following quarter and the dependent variables were Investment, Dividend, Household Saving, Net Government Saving, ROW Saving and the Statistical Discrepancy. Making use of these predictions and relying on economic theory, this paper explores the repercussions of assumptions made through the Cambridge Controversies until today, regarding the relationship between the working class and the elite.

This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator