Machine Learning Algorithms for Predictive Analytics in Big Data

Machine Learning Algorithms for Predictive Analytics in Big Data

Ayda Firouzibostanabad1

1) Departmant of Data Science , Istinye universitesi , Istanbul , Turkey

IOI Code : AAGF-AAGDZA
Publication : 9th International Conference on Applied Researches in Science & Engineering (carseconf.com/9th)
Abstract :
    The rapid growth of Big Data (BD) has created unprecedented opportunities for organizations to extract valuable insights and enhance decision-making through Predictive Analytics (PA). Machine Learning (ML) algorithms play a crucial role in analyzing large-scale, heterogeneous, and high-dimensional datasets by identifying patterns, trends, and correlations that are often hidden in traditional analytical methods. This paper explores the application of ML algorithms in PA within BD environments, focusing on their scalability, efficiency, and predictive accuracy. The study highlights widely used algorithms such as Support Vector Machines (SVM), Random Forests (RF), Gradient Boosting (GB), and Deep Learning (DL) models, emphasizing their strengths and limitations when applied to massive and dynamic data streams. Moreover, the integration of distributed computing frameworks, such as Hadoop and Spark, is discussed to address challenges related to volume, velocity, and variety of BD. Experimental analysis and comparative evaluation demonstrate that hybrid and ensemble-based ML models significantly improve predictive performance in BD analytics. The findings provide a comprehensive understanding of how ML-driven PA can support data-driven strategies and enhance competitiveness in diverse domains, including healthcare, finance, and e-commerce.

Keywords : machine learning predictive analytics big data deep learning random forest support vector machine