Guizhou Cigarette Sales Prediction based on Seasonal Decomposition MLP

DOI

10.2991/isss-15.2015.49How to use a DOI?

Keywords

Cigarette Sales; Prediction; Multilayer Perceptron; Seasonal Decomposition.

Abstract

We combine with seasonal decomposition method, and employ multi-level sensor prediction (MLP, Multilayer Preceptor) method, take prediction of 2014 cigarette sales in Guizhou as example, monthly and quarterly cycle MLP prediction models were put forward, results of the prediction precision were analyzed, through the prediction accuracy of each model, the importance of the independent variables and the average relative error rate, can be drawn on the quarterly MLP model is highest accuracy, it better suited to predict cigarette sales in Guizhou.

Copyright

© 2015, 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  - Jian Tan
PY  - 2015/08
DA  - 2015/08
TI  - Guizhou Cigarette Sales Prediction based on Seasonal Decomposition MLP
BT  - Proceedings of the 1st International Symposium on Social Science (isss-15)
PB  - Atlantis Press
SP  - 196
EP  - 200
SN  - 2352-5398
UR  - https://doi.org/10.2991/isss-15.2015.49
DO  - 10.2991/isss-15.2015.49
ID  - Tan2015/08
ER  -