An Empirical Evaluation of Predictive Modeling Techniques Using Big Data in Industrial Applications

Abstract

The integration of big data analytics in industrial domains has significantly reshaped traditional predictive maintenance, quality control, and process optimization methods. This paper conducts an empirical evaluation of predictive modeling techniques using big data across various industrial applications, including manufacturing, energy, and logistics. A comparative analysis is presented on machine learning models such as Random Forest, Support Vector Machines (SVM), and Deep Learning architectures. We assess these models based on accuracy, computational efficiency, and scalability using publicly available industrial datasets. The study concludes with insights into model performance trends and practical recommendations for industry practitioners