Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM67364
Volume:
10 |
9 |
Sep 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati

Computer Science & Engineering
P R Pote Patil College of Engineering and Management, Amravati
For distributors of pharmaceutical and beauty products, day-to-day efficiency and profitability depend heavily on how well inventory is managed, particularly because these product lines carry a limited shelf life, unpredictable customer demand, and suppliers whose delivery times are not always consistent. Conventional stock-control setups, built around fixed reorder thresholds and manual, spreadsheet-based tracking, generally cannot anticipate shifts in demand, factor in supplier lead time, or warn staff about products nearing expiry — gaps that translate into stock-outs, cash tied up in surplus inventory, and preventable losses from expired goods. This paper puts forward the design of an AI-Powered Smart Inventory and Procurement System that unifies machine-learning-driven demand forecasting, lead-time-sensitive reorder recommendation, automatic purchase-order generation, expiry tracking, OCR-based digitization of supplier invoices, and anomaly detection inside a single ERP-style web platform. Architecturally, the platform pairs a React.js front end with a Spring Boot back end over REST APIs, while a separate Python/FastAPI microservice houses the AI logic, all backed by a PostgreSQL database. The overall aim is to turn historical sales, stock, and purchasing records into forward-looking guidance, moving inventory decision-making away from a reactive stance and toward a proactive one.
KEYWORDS
Planned next steps include IoT-based smart shelves for sensor-driven stock updates, RFID tagging for tracking at the item level, blockchain-based record-keeping across the supply chain, more advanced deep-learning forecasting models, real-time analytics on supplier performance, cloud deployment across multiple warehouses, a companion mobile app, and ongoing automated model retraining. These limitations reflect where the project currently stands; once the remaining modules are completed, integrated, and thoroughly tested, a full evaluation of the system's functionality, security, evaluation accuracy, performance, and scalability will be possible.
[1] G. Princz, F. Reisacher, and S. Erol, “AI-based Procurement System: Optimization of Material Ordering and Inventory Management in Volatile Markets,” Procedia CIRP, vol. 134, pp. 873–878, 2025. [2] A. K. Vadaga, U. R. Dokuburra, H. Nekkanti, A. K. A. E. Reddy, S. D. V. S. R. A. R. M. Sekhar, and A. P. D. N. Ram, “Digital transformation in pharmaceuticals: The impact of AI on supply chain management,” Intelligent Healthcare Systems, vol. 1, Art. no. 100008, 2025. [3] D. Stalin David, N. Siva Virhush, V. Ajay, H. Kalai Selvan, and S. Manikandan, “AI-Driven Inventory and Demand Forecasting System with Automated Supplier Communication and Trend Analysis,” IJERT, vol. 15, no. 4, pp. 576–582, 2026. [4] D. Ni, Z. Xiao, and M. K. Lim, “A Systematic Review of the Research Trends of Machine Learning in Supply Chain Management,” Intl. J. Machine Learning and Cybernetics, vol. 11, no. 7, pp. 1463–1482, 2020. [5] M. Kohli, “Supplier Evaluation Model on SAP ERP Application Using Machine Learning Algorithms,” Intl. J. Engineering & Technology, vol. 7, no. 2.28, pp. 306–311, 2018. [6] V. H. Wilson, A. Prasad N. S., A. Shankharan, S. Kapoor, and J. Rajan A., “Ranking of Supplier Performance Using Machine Learning Algorithm of Random Forest,” IJARET, vol. 11, no. 5, pp. 298–308, 2020. [7] P. Srijaroon, P. Chiadamrong, and S. Krittanai, “A Supervised Learning-Based Supplier Classification Model for Supplier Performance Evaluation Problem in SAP ERP,” Thai J. Operations Research, vol. 9, no. 2, pp. 43–58, 2021. [8] A. R. Vila-Parrish, J. S. Ivy, and R. E. King, “A Simulation-Based Approach for Inventory Modeling of Perishable Pharmaceuticals,” in Proc. 2008 Winter Simulation Conference, pp. 1532–1538, 2008. [9] K. Khanchandani, A. Thakur, A. Shetty, C. Reddy, and R. Behera, “Automated Invoice Data Extraction: Using LLM and OCR,” arXiv:2511.05547, 2025. [10] P. D. Patel, “Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices,” arXiv:2507.07029, 2025.
Publication Date
9/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
8
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...