Cohort analysis is a new practical method for e-commerce customers’ research, trends in their behavior, and experience during the COVID-19 crisis. The purpose of the research is to validate the efficiency of this method on the e-commerce records data set and find out the critical factors associated with customer awareness and loyalty levels. The cohort analysis features engineering, descriptive statistics, and exploratory data analysis are the main methods used to reach the study purpose. The research results showed that cohort analysis could answer various business questions and successfully solve real-world problems in e-commerce customer research. It could be extended to analyze user satisfaction with a platform’s technical performance and used for infrastructure monitoring. Obtained insights on e-commerce customers’ awareness and loyalty levels show the likeliness of a user to make a purchase or interact with the platform. Key e-business aspects from a customer point of view are analyzed and augment the user-experience understanding to strengthen customers’ relationships in e-commerce.

The Covid-19 crisis lockdown caused rapid transformation to remote working/learning modes and the need for e-commerce-, web-education-related projects development, and maintenance. However, an increase in internet traffic has a direct impact on infrastructure and software performance. We study the problem of accurate and quick web-project infrastructure issues/bottleneck/overload identification. The research aims to achieve and ensure the reliability and availability of a commerce/educational web project by providing system observability and Site Reliability Engineering (SRE) methods. In this research, we propose methods for technical condition assessment by applying the correlation of user-engagement score and Service Level Indicators (SLIs)/Service Level Objectives (SLOs)/Service Level Agreements (SLAs) measurements to identify user satisfaction types along with the infrastructure state. Our solution helps to improve content quality and, mainly, detect abnormal system behavior and poor infrastructure conditions. A straightforward interpretation of potential performance bottlenecks and vulnerabilities is achieved with the developed contingency table and correlation matrix for that purpose. We identify big data and system logs and metrics as the central sources that have performance issues during web-project usage. Throughout the analysis of an educational platform dataset, we found the main features of web-project content that have high user-engagement and provide value to services’ customers. According to our study, the usage and correlation of SLOs/SLAs with other critical metrics, such as user satisfaction or engagement improves early indication of potential system issues and avoids having users face them. These findings correspond to the concepts of SRE that focus on maintaining high service availability.

An approach to use Operational Intelligence with mathematical modeling and Machine Learning to solve industrial technology projects problems are very crucial for today’s IT (information technology) processes and operations, taking into account the exponential growth of information and the growing trend of Big Data-based projects. Monitoring and managing high-load data projects require new approaches to infrastructure, risk management, and data-driven decision support. Key difficulties that might arise when performing IT Operations are high error rates, unplanned downtimes, poor infrastructure KPIs and metrics. The methods used in the study include machine learning models, data preprocessing, missing data imputation, SRE (site reliability engineering) indicators computation, quantitative research, and a qualitative study of data project demands. A requirements analysis for the implementation of an Operational Intelligence solution with Machine learning capabilities has been conducted and represented in the study. A model based on machine learning algorithms for transaction status code and output predictions, in order to execute system load testing, risks identification and, to avoid downtimes, is developed. Metrics and indicators for determining infrastructure load are given in the paper to obtain Operational intelligence and Site reliability insights. It turned out that data mining among the set of Operational Big Data simplifies the task of getting an understanding of what is happening with requests within the data acquisition pipeline and helps identify errors before a user faces them. Transaction tracing in a distributed environment has been enhanced using machine learning and mathematical modelling. Additionally, a step-by-step algorithm for applying the application monitoring solution in a data-based project, especially when it is dealing with Big Data is described and proposed within the study.

No abstract

No abstract