Customer insighs is the key to the success of e-commerce. Therefore, factors affecting customer satisfaction leading to product purchase and re-purchase should be studied extensively. This study intends to identify the key drivers that influence the satisfaction and the model which can predict the likelihood of customer satisfaction. The outcome would provide insights to prioritise factors that are significant, as well as to provide advice to a wide range of sellers. Four classification machine learning algorithms decision tree, random forest, artificial neural network and support vector machine are evaluated to classify customer satisfaction based on a 3-year historical data from an e-commerce retailer. There were a few challenges with the dataset, such as imbalanced, skewed and missing. Data pre-processing was conducted, and different techniques were evaluated. Of the algorithms evaluated, the best result is achieved by Random Forest with the highest accuracy and reasonable processing time. Meeting the estimated delivery date and the number of days taken to deliver an order is found to be the top two important factors affecting customer satisfaction.
Recommender models for personalized marketing empower businesses to provide personalized recommendations of goods or services to customers to fulfil their requirements, thus ultimately improves the customer buying experience. Various recommender models powered by robust machine learning algorithms were reviewed on the methods and techniques to appraise its performance concerning the personalized marketing campaigns. Recommender models can be broadly categorized into four types such as content-based, collaborative-based, knowledge-based and hybrid-based. The content-based recommendation is suitable when the system, user or product is new where classification and regression algorithms are mostly implemented. The collaborative-based recommendation is suitable when a more accurate prediction is required where Neighbour-based models, Bayesian methods, rule-based models, decision trees, and latent matrix factorization models may be implemented in this scenario. Knowledge-based recommenders are well suited for recommendations that address explicitly defined user requirements. Different types of recommenders use different sources of data and inherently have different strengths and weaknesses. Selecting the suitable recommender model with the consideration of the scenario and domain of application is very crucial. Therefore, an in-depth research is required and done on the emphasis of the application of recommender models in the personalized marketing especially on the hybrid models with a more efficient deployment for mass applications in this contemporary data-driven business world.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.