Integration of Big Data and Artificial Intelligence into the marketing campaign management system of online businesses

Abstract

The study aims to identify the patterns of integrating Big Data and artificial intelligence technologies into the management system of marketing campaigns of online enterprises and to assess their impact on the effectiveness of digital communications. The methodological framework is based on the combination of system analysis, a functional-structural approach, machine-based modelling, and comparative evaluation of the technical parameters required for implementing intelligent modules. The research applies parametric analysis of marketing processes, a review of machine-learning algorithms, examination of digital-platform architectures, and performance-assessment methods for personalization, forecasting, and audience-segmentation models. The findings demonstrate that combining large-scale datasets with artificial-intelligence algorithms forms the basis for adaptive decision-making in marketing management. Intelligent models enhance the accuracy of consumer-behaviour forecasting, reduce data-processing time, optimize advertising-budget allocation, and significantly expand the capabilities of content personalization. The study outlines the key technical requirements for deploying Big Data systems, including training-set volumes, data-refresh frequency, user-attribute depth, and critical performance thresholds. The functional role of recommendation mechanisms, dynamic-pricing models, attribution systems, and automated hypothesis-testing tools is analysed. The study confirms that the integration of Big Data and artificial intelligence transforms traditional approaches to managing marketing campaigns, increases the speed of decision-making, and generates sustainable competitive advantages for online enterprises in a dynamic digital environment. The analysis identifies promising directions for further research, including the development of methods for evaluating model accuracy under volatile conditions, improving adaptive-pricing mechanisms, examining ethical constraints of automated decisions, and designing comprehensive architectures capable of operating within high-volatility digital markets.