Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191859,
        author = {Abhilash S},
        title = {Predictive Analytics with AI: Real-Time Forecasting Using Big Data Streams},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {8122-8130},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191859},
        abstract = {The rapid growth of real-time data generated from sources such as IoT devices, social media platforms, financial transactions, and industrial systems has created a strong demand for intelligent predictive analytics capable of operating on continuous data streams. Traditional batch-oriented analytics methods are inadequate for handling the velocity, volume, and variability of big data streams. This paper presents an AI-driven framework for real-time forecasting using big data streams, integrating advanced machine learning and deep learning models with scalable stream-processing architectures.
The proposed approach employs online learning and incremental model updating techniques using algorithms such as Long Short-Term Memory (LSTM) networks, temporal convolutional networks, and reinforcement learning-based adaptive predictors. Stream-processing platforms including Apache Kafka and Apache Spark Streaming are utilized to enable low-latency data ingestion, real-time feature extraction, and continuous model inference. The framework addresses key challenges such as concept drift, data noise, and scalability through adaptive windowing, drift detection mechanisms, and automated model retraining.
Experimental evaluation on real-world streaming datasets demonstrates significant improvements in prediction accuracy, latency, and system throughput compared to traditional batch-based predictive models. The results highlight the effectiveness of AI-powered predictive analytics in enabling timely decision-making across applications such as smart cities, financial markets, healthcare monitoring, and industrial automation. This study emphasizes the role of real-time AI-driven forecasting as a critical enabler for next-generation data-driven systems},
        keywords = {Big Data, artificial intelligence, ML and DL, AI-driven forecasting},
        month = {January},
        }