Analysis of models, methods and technologies for creating personalized content in B2B e-commerce systems

Abstract

The increasing financial significance and structural complexity of the B2B e-commerce market segment, along with the imperative to enhance its efficiency, necessitate a systematic analysis of models, methods, and technologies used for personalized content creation within such systems. The study has identified the unique characteristics of B2B commerce and compared B2B and B2C systems based on key performance indicators. An analysis of existing models, methods, and technologies for personalized content creation in B2B e-commerce systems has been conducted, including: аlogarithms for finding frequent item sets (e.g., Apriority, FP-Growth, Eclat), which enable the detection of product combinations frequently ordered together. Metrics for evaluating the quality of association rules (Support, Confidence, Lift, Conviction), which are essential for assessing the significance and utility of the discovered patterns in product orders. The need to develop affinity analysis models of transactional and behavioral data, in combination with customer classification methods, is substantiated to enhance the personalization of product, informational, and recommendation content within B2B e-commerce systems.