Systematic Review on Advancing Decision-Making: Integrating Intelligent Data Science and Predictive Analytics for Real-World Applications

Abstract

The integration of intelligent data science and predictive analytics has revolutionized decision-making frameworks across diverse sectors, transitioning from intuition-driven approaches to data-driven methodologies. This systematic review investigates the evolution, methodologies, applications, challenges, and future opportunities of these technologies. Drawing on 85 peer-reviewed articles published between 2015 and 2024, the study highlights advancements in predictive analytics tools, including AutoML, deep learning, and time-series forecasting, which have democratized data utilization and enhanced decision-making precision. Real-world applications in healthcare, finance, and retail demonstrate the transformative potential of predictive models in optimizing resource allocation, risk management, and personalized strategies. Despite these advancements, challenges such as data quality issues, ethical concerns, and model interpretability persist. Emerging solutions, including explainable AI (XAI), federated learning, and quantum computing, promise to address these limitations, offering enhanced transparency, privacy, and computational capabilities. The review emphasizes the importance of collaboration among academia, industry, and policymakers to harness these technologies ethically and equitably. This research provides actionable insights into the current state and future trajectory of intelligent data science and predictive analytics, offering a foundation for advancing decision-making processes in real-world contexts.