Development of Novel Convolutional Neural Network-Based Model for Sales Forecast in an Electronic Retail Store during Festive Seasons and Comparison of Prediction Accuracy with Deep Belief Network

Abstract

Aim: The aim of this paper is to implement a Novel Convolutional Neural Network based has model for Sales forecast in an Electronic Retail Store during Festive seasons and a comparison of prediction accuracy with a Deep Belief Network. Materials and Methods: Deep Belief Network (N=10) and Novel Convolutional Neural Network algorithm (N=10), n is iterated at different times for predicting the accuracy percentage of accidents that happened. Two sample groups are taken into consideration and tested, G-power is a calculation that contains two different groups, alpha (0.05), and power (80%). Results: It was observed that the Deep Belief Network algorithm obtains an accuracy of 77.14% and the Novel Convolutional Neural Network has 84.86%. This Deep Belief Network appears to have a significance of p=0.019 than the Novel Convolutional Neural Network, that is p<0.05 using an independent sample forT-test analysis. Conclusion: The Deep Belief Network technique appears to have more significance than the Novel Convolutional Neural Network algorithm. The analysis generally works in a variety of end-use industries, and the results demonstrate that this strategy is important. The result proves that the Novel Convolutional Neural Network approaches to predict the retail sales store prediction.