Authors : Manisha Dhage; Atharva Hemant Phadtare; Vedant Jayram Kawthalkar; Harsh Amit Mehta; Lobhas Niraj Nivsarkar

Volume/Issue : Volume 10 - 2025, Issue 3 - March

---

Google Scholar : https://tinyurl.com/3cbxx8ca

Scribd : https://tinyurl.com/r8v69avf

DOI : https://doi.org/10.38124/ijisrt/25mar231

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : Effective inventory management is critical for the dynamic fashion retail industry, particularly in men’s T- shirts. This paper presents an AI-driven solution to address overstocking and understocking, utilizing machine learning techniques to analyze product images and sales data. Key innovations includeResNet-50-based image embeddings for visual analysis, cosine similarity, and FAISS for product matching, combined with predictive modelling for demand forecasting. This approach reduces operational inefficiencies and aligns inventory levels with real-time trends, improving business profitability and sustainability.

Keywords : Inventory Optimization, Fashion Retail, Machine Learning, ResNet-50, FAISS, Demand Forecasting, Seasonal Trends, AI-Driven Inventory.

References :

1. Cheng, T.C.E., Choy, P.W.C., and Wong, R.L.M. (2024). Fast Fashion Supply Chain Management in China: Critical Success Factors and Their Supply Chain Performance Implications. IEEE Engineering Management Review, 52(1).
2. Guo, Ziyue, et al. (2023). AI Assisted Fashion Design: A Review. IEEE Access, 11 Aug. 2023, doi:10.1109/ACCESS.2023.3306235.
3. Liu, X., Sun, Y., Liu, Z., & Lin, D. (2021). Learning Diverse Fashion Collocation by Neural Graph Filtering. IEEE Transactions on Multimedia, 23.
4. Jing, P., Cui, K., Guan, W., Nie, L., & Su, Y. (2023). Category-Aware Multimodal Attention Network for Fashion Compatibility Modeling (FCM-CMAN). IEEE Transactions on Multimedia, 25.
5. Chen, H.-J., Shuai, H.-H., & Cheng, W.-H. (2022). A Survey of Artificial Intelligence in Fashion. IEEE Multimedia, 9(4).
6. Dong, X., Song, X., Zheng, N., Wu, J., Dai, H., & Nie, L. (2024). TryonCM2: Try-on-Enhanced Fashion Compatibility Modeling Framework. IEEE Transactions on Neural Networks and Learning Systems, 35(1).
7. Ding, Y., Ma, Y., Wong, W. K., & Chua, T. S. (2022). Modeling Instant User Intent and Content-Level Transition for Sequential Fashion Recommendation. IEEE Transactions on Multimedia, 24, 2687-2701.
8. Jing, P., Cui, K., Zhang, J., Li, Y., & Su, Y. (2024). Multimodal High-Order Relationship Inference Networkfor Fashion Compatibility Modeling in the Internet of Multimedia Things. IEEE Internet of Things Journal, 11(1), 353-365.
9. Cossatin, A. G., Mauro, N., & Ardissono, L. (2024). Promoting Green Fashion Consumption Through Digital Nudges in Recommender Systems. IEEE Access, 12,6812-6827.
10. Hosseini-Motlagh, S.-M., Johari, M., Zirakpourdehkordi, R., & Choi, T.-M. (2024). Sustainable Operations for Fashion Manufacturing: A Dynamic Time-Varying Framework. IEEE Transactions on Engineering Management, vol. 71, 11375-11387.
11. Lu, Z., Hu, Y., Yu, C., Jiang, Y., Chen, Y., Zeng, B. (2023). Personalized Fashion Recommendation With Discrete Content-Based Tensor Factorization. IEEE Transactions on Multimedia, vol. 25, 5053-5064.
12. Guo, S., Sun, X., Lam, H.K.S. (2023). Applications of Blockchain Technology in Sustainable Fashion Supply Chains: Operational Transparency and Environmental Efforts. IEEE Transactions on Engineering Management, vol. 70, no. 4, 1312-1323.