Mining for Oil Forecasts

52 Pages Posted: 28 Dec 2020

See all articles by Charles W. Calomiris

Charles W. Calomiris

Columbia University - Columbia Business School; National Bureau of Economic Research (NBER)

Nida Çakır Melek

Federal Reserve Bank of Kansas City

Harry Mamaysky

Columbia University - Columbia Business School

Date Written: December 23, 2020

Abstract

We study the usefulness of a large number of traditional variables and novel text-based measures for in-sample and out-of-sample forecasting of oil spot and futures returns, energy company stock returns, oil volatility, oil production, and oil inventories. After carefully controlling for small-sample biases, we find compelling evidence of in-sample predictability. Our text measures hold their own against traditional variables for oil forecasting. However, none of this translates to out-of-sample predictability until we data mine our set of predictive variables. Our study highlights that it is difficult to forecast oil market outcomes robustly.

Keywords: Asset Pricing, Commodity Markets, Energy Forecasting, Model Validation

JEL Classification: C52, G10, G14, G17, Q47

Suggested Citation

Calomiris, Charles W. and Çakır Melek, Nida and Mamaysky, Harry, Mining for Oil Forecasts (December 23, 2020). Federal Reserve Bank of Kansas City Working Paper No. 20-20, Available at SSRN: https://ssrn.com/abstract=3755487 or http://dx.doi.org/10.2139/ssrn.3755487

Charles W. Calomiris

Columbia University - Columbia Business School ( email )

3022 Broadway
601 Uris, Dept. of Finance & Economics
New York, NY 10027
United States
212-854-8748 (Phone)
212-316-9219 (Fax)

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Nida Çakır Melek (Contact Author)

Federal Reserve Bank of Kansas City ( email )

1 Memorial Dr.
Kansas City, MO 64198
United States

Harry Mamaysky

Columbia University - Columbia Business School ( email )

3022 Broadway
New York, NY 10027
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
32
Abstract Views
166
PlumX Metrics