Raw Grain Price Forecasting with Regression Analysis

DOI

10.2991/msbda-19.2019.58How to use a DOI?

Keywords

Grain price forecasting, Multivariate linear regression, Neural network, LSTM

Abstract

Grain price stability and food security are important in all countries. The accurate forecasting of grain price can help the farmer, grain processing enterprise and government make wise decision. A raw grain price dataset is formed with public available data and the raw grain purchase price index is set as the target variable to predict. Three regression models of multivariate linear regression, shallow artificial neural networks and long-short term memory(LSTM) are studied in this paper. Comparative analysis results show that artificial neural network model outperforms the other models in price forecasting on a small dataset. To improve the prediction accuracy of LSTM, the sampling frequency must be increased to get more data to learn the trend and seasonality of grain price.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Nan Liu
AU  - Junwei Yu
PY  - 2019/08
DA  - 2019/08
TI  - Raw Grain Price Forecasting with Regression Analysis
BT  - Proceedings of the 2019 International Conference on Modeling, Simulation and Big Data Analysis (MSBDA 2019)
PB  - Atlantis Press
SP  - 372
EP  - 378
SN  - 2352-538X
UR  - https://doi.org/10.2991/msbda-19.2019.58
DO  - 10.2991/msbda-19.2019.58
ID  - Liu2019/08
ER  -