AI-Based Pharmaceutical Demand Forecasting for Sustainable Production: A Hybrid BiLSTM–Transformer Approach to Prevent Overproduction
Sustainability · 07.11.2026 · 18 (21) · 11372
DOI: 10.3390/su182111372 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sustainability, online erschienen am 07.11.2026. Verfasst von Mares-Carreño Jesús und 6 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Polytechnic Institute.
Abstract (Originalsprache)
Accurate pharmaceutical demand forecasting is essential to align production with actual market needs, reduce overproduction, prevent stockouts, and improve resource efficiency. This study develops a hybrid bidirectional long short-term memory (BiLSTM)–Transformer model to support sustainable pharmaceutical production through data-driven demand forecasting. We trained the model on real monthly sales and inventory data from a nationwide pharmaceutical company in Mexico, along with epidemiological, climatic, demographic, and economic variables. The study analyzed thirteen sodium naproxen and oseltamivir phosphate pharmaceutical products over forecasting horizons of 3, 6, and 12 months. We evaluated robust scaling and logarithmic transformation during preprocessing and compared the Adam, RMSprop, Nadam, and SGD optimizers. Nadam generally produced the lowest forecasting errors, especially at short- and medium-term horizons. Six of the thirteen evaluated pharmaceutical products achieved cumulative percentage errors below 10% at the three-month forecasting horizon. Compared with the Seasonal Naïve baseline, the proposed model achieved lower cumulative forecasting errors for 11 of 13 products at the 3-month horizon and 9 of 13 products at both the 6- and 12-month horizons, although the baseline performed better for certain products. Performance became more heterogeneous over longer horizons and for products with irregular or highly volatile demand, revealing important limitations for operational use. The findings suggest that hybrid AI-based forecasting may support production planning and inventory management decisions, provided that model selection accounts for product-specific characteristics and forecasting horizons. However, potential benefits related to reduced overproduction, excess inventory, product expiration, and environmental impacts remain prospective applications rather than outcomes directly demonstrated in this study.
Förderung
- National Polytechnic Institute
Zitieren
APA
Jesús, M., Diego-Iván, A., Yunuén, L., Juan, C., Stephany, A. G., Vladimir, V. M., & Gutiérrez-Galicia, F. (2026). AI-Based Pharmaceutical Demand Forecasting for Sustainable Production: A Hybrid BiLSTM–Transformer Approach to Prevent Overproduction. Sustainability, 18(21), 11372. https://doi.org/10.3390/su182111372
Vancouver
Jesús M, Diego-Iván A, Yunuén L, Juan C, Stephany AG, Vladimir VM, et al. AI-Based Pharmaceutical Demand Forecasting for Sustainable Production: A Hybrid BiLSTM–Transformer Approach to Prevent Overproduction. Sustainability. 2026;18(21):11372. doi:10.3390/su182111372
BibTeX
@article{Jess2026,
author = {Jesús, Mares-Carreño and Diego-Iván, Arce-Gil and Yunuén, López-Grijalba and Juan, Cruz-Castro and Stephany, Abarca-Jiménez Griselda and Vladimir, Vega-Blanco Manuel and Gutiérrez-Galicia, Francisco},
title = {AI-Based Pharmaceutical Demand Forecasting for Sustainable Production: A Hybrid BiLSTM–Transformer Approach to Prevent Overproduction},
journal = {Sustainability},
year = {2026},
volume = {18},
number = {21},
pages = {11372},
doi = {10.3390/su182111372}
}
EUVIMED