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{199682,
        author = {Harissh S and Harish M and Mohamad Faiz and R Subhashini},
        title = {Dynamic Box Office Revenue Forecasting via Hybrid Machine Learning and Retrieval-Augmented Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {14982-14990},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199682},
        abstract = {The task of box office revenue prediction is highly complex due to changing audience interest and market competition. Traditional machine learning models have been based primarily on static metadata information, which is not able to capture real-time market dynamics in the weeks preceding a film’s release. This paper proposes a novel solution that integrates Retrieval-Augmented Generation (RAG) concepts to optimize continuous variable predictions. By using a combination of static machine learning ensemble and real-time dynamic market information, this model is able to retrieve social buzz information in real-time, assess immediate competitor threats, and retrieve historical financial analogues using a FAISS vector database. A Ridge Regression model is used to combine this information. Experimental results have been presented that show that this model can reduce Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) compared to traditional static models. This model is highly adaptive and can be used for highly accurate box office revenue prediction.},
        keywords = {Box Office Prediction, Retrieval-Augmented Generation, Ensemble Learning, Vector Databases, Market Forecasting},
        month = {April},
        }