Forecasting Hog Prices with a Neural Network

Neural network models were compared to traditional forecasting methods in forecasting the quarterly and monthly farm price of hogs. A quarterly neural network model forecasted poorly in comparison to a quarterly econometric model. A monthly neural network model outperformed a monthly ARIMA model with respect to the mean square error criterion and performed similarly to the ARIMA model with respect to turning point accuracy. The more positive results of the monthly neural network model in comparison to the quarterly neural network model may be due to nonlinearities in the monthly data which are not in the quarterly data.


Issue Date:
1997
Publication Type:
Journal Article
DOI and Other Identifiers:
0738-8950 (Other)
PURL Identifier:
http://purl.umn.edu/90646
Published in:
Journal of Agribusiness, Volume 15, Number 1
Page range:
37-54
Total Pages:
18




 Record created 2017-04-01, last modified 2017-08-25

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)