Do Machine Learning Models Hold the Key to Better Money Demand Forecasting?

Abstract

Significant evidence in the literature points to money demand instability and therefore inaccurate forecasting. In view of this issue, this chapter seeks to use a method, innovative for money demand literature, that is, the machine learning model to predict money demand. Specifically, this chapter uses Random Forest Regression to predict money demand using monthly data in the Indian context over the period April-1996 to December-2018 using the variables usually used in literature. The chapter finds that in money demand prediction, the Random Forest Regression performs fairly well. The results are also compared to traditional models and it is found that the Random Forest Regression model has the potential to enhance the prediction of money demand over what traditional models predicts.

Citation

Ghosh, T. and Agarwal, S. (2021), "Do Machine Learning Models Hold the Key to Better Money Demand Forecasting?", Barnett, W.A. and Sergi, B.S. (Ed.) Environmental, Social, and Governance Perspectives on Economic Development in Asia (International Symposia in Economic Theory and Econometrics, Vol. 29A), Emerald Publishing Limited, Leeds, pp. 21-36. https://doi.org/10.1108/S1571-03862021000029A017