Skip to main content
No Access

Optimising AIOps system performance for e-commerce and online retail businesses with the ACF model

Published Online:pp 412-429https://doi.org/10.1504/IJIPM.2023.134064

Artificial intelligence has changed the dynamics of e-commerce and the online retail business sectors forever. With natural language processing, machine learning, and predictive analysis, AIOps monitoring systems can use statistical methods to become an important element of business applications. The internet's rapid progress has helped this domain grow. This study examines the operations that make e-commerce an effective way to conduct business worldwide. We devise ways to optimise the existing system to add more value to e-commerce-related industries and improve customer satisfaction. We also show how businesses should emphasise system performance for higher success. While AIOps for e-commerce and online retail businesses have been studied, no holistic method can be widely used and effective. In order to give away, we reviewed the literature, found shortcomings in the present KB, CBR, and GBR methodologies, and proposed an enhanced ACF model that may provide suggestions based on similar consumer behaviour. Performance testing enhances e-commerce and online retail user experience, customer retention, targeted advertising and revenue.

Keywords

AIOps, performance testing, monitoring, machine learning, big data, artificial intelligence, predictive analysis, advertising, revenue, e-commerce, electronic commerce