Efficient Prediction of Demand for Electronics Items in a Retail Store During Festive Seasons Adopting Novel Resnet Algorithm and its Performance Comparison Over Deep Belief Network

Abstract

Aim: The aim of this paper is the efficient prediction of demand for Electronics Items in a Retail Store during festive seasons by adopting Novel ResNet Algorithm and its performance comparison over Deep Belief Network. Materials and Methods: At different stages, the Deep Belief Network and Novel ResNet algorithms were iterated in order to predict the accuracy percentage of accidents that occurred. Two sample groups are considered and tested, and G-power is a computation that includes two groups, alpha (0.05), and Power (80%). Results: It was observed that the Novel ResNet algorithm obtains an accuracy of 83.16% and the Deep Belief Network has 77.24%. This DBN appears to have a better significance of P=0.016 than the Novel ResNet, that is p<0.05 using the independent T-test sample for the analysis. Conclusion: This study contains analyses that target the sparsity in the income facts with the aid of converting a wide variety of product attributes. The result proves that the Novel ResNet Algorithm approaches predicting the retail store prediction during the festival season.