TY - GEN
T1 - Research on sales forecasting based on ARIMA and BP neural network combined model
AU - Ji, Shenjia
AU - Yu, Hongyan
AU - Guo, Yinan
AU - Zhang, Zongrun
N1 - Publisher Copyright:
© 2016 ACM.
PY - 2016/12/23
Y1 - 2016/12/23
N2 - A single ARIMA model cannot meet higher standards of prediction accuracy. Moreover, it can only deal with small prediction periods in the forecasting work. For the sake of prediction accuracy, we combined an ARIMA model with BP neural network. Firstly, an ARIMA forecasting model is established. Secondly the BP neural network is used to improve the single ARIMA model.The residual of ARIMA model is trained and fitted by BP neural network. Finally, more accurate results are given through combination with the forecast results of ARIMA model. The practice turns out that, compared with single ARIMA model, the prediction accuracy of new ARIMA model improved by BP neural networks is obviously enhanced, with an average error of forecast decreasing 10.4% by a large margin. Thus, the combined model proposed by this paper can be used in future prediction researches and industrial data analysis.
AB - A single ARIMA model cannot meet higher standards of prediction accuracy. Moreover, it can only deal with small prediction periods in the forecasting work. For the sake of prediction accuracy, we combined an ARIMA model with BP neural network. Firstly, an ARIMA forecasting model is established. Secondly the BP neural network is used to improve the single ARIMA model.The residual of ARIMA model is trained and fitted by BP neural network. Finally, more accurate results are given through combination with the forecast results of ARIMA model. The practice turns out that, compared with single ARIMA model, the prediction accuracy of new ARIMA model improved by BP neural networks is obviously enhanced, with an average error of forecast decreasing 10.4% by a large margin. Thus, the combined model proposed by this paper can be used in future prediction researches and industrial data analysis.
KW - ARIMA Model
KW - BP Neural Network Model
KW - Composition Model
KW - Prediction
UR - http://www.scopus.com/inward/record.url?scp=85015658259&partnerID=8YFLogxK
U2 - 10.1145/3028842.3028883
DO - 10.1145/3028842.3028883
M3 - Conference contribution
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 2016 International Conference on Intelligent Information Processing, ICIIP 2016
PB - Association for Computing Machinery
T2 - 2016 International Conference on Intelligent Information Processing, ICIIP 2016
Y2 - 23 December 2016 through 25 December 2016
ER -