PROJECT TITLE :

Study on Daily Demand Forecasting Orders using Artificial Neural Network

ABSTRACT:

In recent decades, Brazil has undergone several transformations, from a closed economy to a market economy. Transport, processing and distribution of orders remained follow these trends. Thus, the delivery parcel service has become highly complex and competitive. During this context, the forecast demand of orders comes as differential, leading structured productivity and high level of client service. The paper aims to provide for the daily demand of orders in an Orders Treatment Centre for fifteen days using Artificial Neural Network (ANN). The methodological synthesis of the article is the event of a Artificial Neural Network Multilayer Perceptron (MLP), trained by error back-propagation algorithm. The info for the experiments were collected for sixty days, forty five days to coaching and 15 days for testing. Experiments were performed with four totally different topologies of RNA by changing the subsequent parameters: range of hidden layers, variety of neurons in the hidden layers, learning rate, momentum rate and stopping criteria. The results obtained with use of RNA in daily demand forecast orders showed smart adhesion to the experimental information within the training and testing phases.