ABSTRACT
In this study, customer engagement strategies in e-commerce platforms are explored through the application of selected cutting-edge technologies and advanced analytics. Specifically, this project involves the integration of blockchain technology, cloud computing techniques, and machine learning models to promote customer interaction, optimize inventory management activities, and facilitate business growth in the highly competitive online marketplace. To develop and evaluate the models, a substantial dataset of 3500 customer purchase and brand collection movements is applied. The analyzed models include Artificial Neural Networks , Random Forests , Support Vector Machines , and Decision Trees . As a common practice, the models were trained and tested on the 70/30 datasets. The results indicate a satisfactory level of performances across the models, with certain algorithms reaching very high accuracy, precision, recall, and F1 scores in predicting the future trends of sales by customers’ engagement. Specifically, the results of the ANN and RF models showcase their revolutionary capabilities in sales prediction and, being readily applicable, for informing managerial decision-making in the e-commerce environment. In addition, the dataset is securely and transparently stored in blockchain and accessible through a cloud service, which contributes to the overall reliability of the analysis. Therefore, the key finding of this research is that the integration of cutting-edge technologies into advanced analytics can facilitate higher levels of customer engagement and business success on e-commerce platforms. Overall, the results of this study provide a major contribution to the scholarly literature and offer substantial insights that can aid practitioners in their applications.
