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{182222,
        author = {Mahek Kala and Prashant Kulkarni and Shubhangi Tidake},
        title = {Hybrid Forecasting Models for Trend-Dominant Time Series: A Case Study},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {1304-1307},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182222},
        abstract = {This study presents a rigorous evaluation of hybrid Prophet-GRU (Gated Recurrent Unit) models for forecasting monthly tractor sales, a quintessential trend-dominant time series. Leveraging a dataset spanning 2003 to 2014, we demonstrate how integrating Facebook Prophet’s interpretable decomposition with GRU’s nonlinear modeling capabilities achieves a 5.14% Mean Absolute Percentage Error (MAPE), significantly outperforming standalone Prophet (8.06% MAPE) and SARIMA (8.47% MAPE). Our methodology includes:
1.	Synthetic-to-real validation: Aligning real-world data with synthetic regimes (Thigh Smid Nlow normal) for robust model selection.
2.	Architectural innovation: A two-stage hybrid pipeline combining Prophet’s trend/seasonality extraction with GRU’s residual learning.
3.	Practical deployment insights: Computational trade-offs, hyperparameter tuning, and scalability for industrial applications.
The study further validates results on supplemental agricultural datasets, showing consistent 30–40% error reduction. We conclude with actionable guidelines for practitioners implementing hybrid forecasting in resource-constrained environments.},
        keywords = {Time series forecasting, Hybrid models, GRU, Prophet, Agricultural sales, Demand prediction},
        month = {July},
        }