Large Language Model-Augmented Machine Learning Pipelines for Automated Predictive Intelligence

Abstract

Data-driven applications across healthcare, manufacturing, finance, transportation, cybersecurity, smart cities, and Industrial Internet of Things (IIoT) require intelligent predictive systems that are accurate, explainable, and capable of real-time decision-making. While conventional machine learning (ML) pipelines effectively automate tasks such as data preprocessing, feature engineering, model training, and deployment, they often lack contextual reasoning, adaptive intelligence, and explainability when handling heterogeneous and multimodal data. Recent advances in Large Language Models (LLMs) offer new opportunities to enhance ML pipelines through semantic reasoning, intelligent feature generation, automated model optimization, and explainable predictions. This research proposes a Large Language Model-Augmented Machine Learning Pipeline (LLM-MLP) that integrates data acquisition, intelligent preprocessing, semantic feature engineering, automated model selection, hyperparameter optimization, explainable AI, continuous monitoring, and feedback-driven refinement within a unified framework. By combining LLM-based reasoning with traditional ML techniques, the proposed architecture improves predictive accuracy, interpretability, scalability, and computational efficiency. The framework supports continuous learning through reinforcement-based optimization and is applicable to diverse domains, including healthcare diagnosis, predictive maintenance, financial risk assessment, cybersecurity, customer analytics, and smart infrastructure management. Overall, the proposed LLM-MLP provides an adaptive, trustworthy, and scalable predictive intelligence framework for next-generation AI-driven decision support systems.