Published Paper Details:

The rapid growth of digital platforms has led to a very large amount of customer interaction data being generated every second. This situation creates strong opportunities for organizations to engage with customers in real time. However, many existing analytics systems face problems related to scalability, high processing delay, and difficulty in using advanced artificial intelligence models on streaming data. To address these challenges, this paper proposes a simple and practical analytical framework for real-time customer engagement by combining big data technologies with AI-based analytics. The proposed framework is organized into four clear layers: data ingestion, data processing, analytics, and decision support. In the data ingestion layer, streaming data from digital platforms such as social media are collected using distributed messaging systems. The data processing layer handles large volumes of data through scalable big data frameworks that support real-time computation. The analytics layer applies machine learning and deep learning models to perform sentiment analysis, predict customer engagement levels, and identify behavioral patterns. The decision support layer converts analytical outputs into timely insights that can help organizations take quick and informed actions. The framework is evaluated using real-world social media datasets. Performance is measured using engagement prediction accuracy, sentiment classification results, system latency, and response time. The experimental findings show that the proposed approach provides better scalability and faster insights compared to traditional batch-based analytics methods. Overall, this study demonstrates the usefulness of integrating big data and AI for building efficient real-time customer engagement systems and offers a foundation for future research