Data Science Approaches to Analyze B2B User Engagement: A Compositional Time-Series Perspective

Authors: Preetham Reddy Kaukuntla

DOI: https://doi.org/10.5281/zenodo.14838600

Short DOI: https://doi.org/g84g66

Country: USA

Full-text Research PDF File:   View   |   Download

Abstract: In this paper, the data science approach for the analysis of the B2B users’ engagement based on the compositional time-series approach is examined. The focus is on detecting the long-term trends of users’ activity due to some specific features, such as product engagement, content engagement, etc. The paper uses new techniques like decomposition of times series data, machine learning algorithms and statistical compositional analysis to describe some patterns and offer recommendations for B2B interactions. The paper also discusses issues, for example, data scarcity and the high dimensionality problem and response like feature extraction and the process of adjusting models respectively. The features of real-life cases analyze how compositional time-series analysis can be used in B2B ecosystems.

Keywords: Business To Business User, Temporal Data Analysis, Part-Whole Data, Analytics, Artificial Intelligence, Engagement Metrics

Paper Id: 232107

Published On: 2024-02-05

Published In: Volume 12, Issue 1, January-February 2024

Share this