A Convolutional Neural Networks-based Model for Sales Prediction

Abstract

Big data is a term used to describe information assets which feature high volume, variety, velocity, and veracity, and which require specific technology and methods for conversion to value. A new generation of scalable-data technologies is needed to collect, store, manage and reveal the insights and meaning of big data. One of the ways companies can use their "big data" is applying prediction algorithms to their past sales numbers to make future sales predictions and then act accordingly to increase their business value. In this research, a convolutional neural networks-based model is presented. The model is used to predict future sales for a pharmaceutical company using their real large-scale sales data. The prediction results are evaluated based on the mean absolute error and mean absolute percent error metrics, which are used to determine the accuracy and show the effectiveness of our model.