With the growth of internet usage, social networking among consumers and their rated products form a complex network. A huge amount of data is generated for various products as a result of user's interactions on social sites, forum and blogs. Organizations deploy Machine Learning (ML) techniques (supervised or unsupervised) to analyze customer attitude that may be presents in comments, review (e.g., Amazon, Flipkart) or posts (e.g., Facebook or Twitter). Machine learning techniques can automate a number of mundane tasks like risk mitigation and improve the organization operational efficiency though quick analysis of big data in real-time. This chapter explores a comprehensive review of Machine learning methods being deployed on e-commerce websites, which correlates the impact of Machine learning on organizations profits, on the consumer sentiments and on product recommendations based on consumer-product interactions. There are number of ways and opportunity for the industry to adopt Machine learning application in the e-commerce. Companies can mine data from customer actions, transactions, and social sentiment to identify customers who are likely to leave. As a result, businesses can use machine learning to create useful customer profiles, increase sales and improve brand loyalty. This chapter discusses the advantages of machine learning and its role in e-commerce. The applications for machine learning for the analysis of customer interactions have been presented along with specific examples.
CITATION STYLE
Lange, H., & Sippel, S. (2020). Machine Learning Applications in Hydrology (pp. 233–257). https://doi.org/10.1007/978-3-030-26086-6_10
Mendeley helps you to discover research relevant for your work.