Hybrid model of gas price prediction using moving average and neural network

The accurate prediction of gas price is very crucial for the producer and consumer. Producer can maximize their profit and manage short term operation and long term planning with the accurate price prediction. Meanwhile, consumer can maximize their utilities efficiently. This paper presents hybrid model for gas price prediction using back-propagation neural network along moving average approach. The actual data from 1998-2015 is extracted from American energy information ad- ministration (EIA) and multi-layer neural network is train with Levenberg-Marquardt algorithm.