Predictions Of Consumer Behaviour And Their Impact On Visual Merchandising Using Combined Machine Learning Concept

Abstract

Visual merchandising (VM) has grown in popularity recently as a quick and economical technique to renovate retail businesses. The strategy that will enhance sales and profits while also directly influencing customer traffic and their experiences is the best visual merchandising technique. The number of customers that visit your store is greatly influenced by your extensive and dynamic visual merchandising. Due to the intense rivalry in today's supermarkets, the study's goal is to acquire insight into the pertinent theoretical knowledge on visual merchandising and into current information on customer behaviour identification using the deep machine learning algorithm with precise references. Conclusions on the relationship between VM and brand image, customer purchasing behaviour, and competitive advantage of a certain brand will be drawn using this insight. This study aims to investigate the connection between visual merchandising and customer impulse buying habits using Artificial intelligence (AI) namely the Machine Learning concept. Due to the shortcomings of the conventional K-means approach, consumer segmentation theory, a new adaptive GA+K-means-ANN algorithm based on Genetic algorithm (GA) deep artificial neural network (ANN) combined along with classic K-means algorithm is projected, which can be applicable to e-commerce customers’ segmentation for visual management techniques. Additionally, efforts have been made to comprehend the visual merchandising strategy that has the greatest influence on consumers. This study also aims to shed light on the reasons why visual merchandising should be regarded as a crucial element of a strategic marketing plan in order to boost sales and enhance the reputation of a business.