NextBUY: An AI-Driven Smart Retail Inventory Optimization Platform Using Advanced Machine Learning Techniques

Nithishvaran S; Rubhesh S R; Farhan M; Dominic Francis E

NextBUY: An AI-Driven Smart Retail Inventory Optimization Platform Using Advanced Machine Learning Techniques

Author(s)	Mr. Nithishvaran S, Mr. Rubhesh S R, Mr. Farhan M, Mr. Dominic Francis E
Country	India
Abstract	Retail inventory management faces critical challenges including stockouts, overstocking, and revenue leakage, collectively costing the industry approximately $300 billion annually according to the National Retail Federation. Traditional inventory systems rely on manual spreadsheet tracking, rule-based forecasting, and isolated data silos, leading to suboptimal decision-making and cognitive bias. This paper presents NextBUY, an AI-driven smart retail inventory optimization platform integrating predictive analytics, prescriptive recommendations, and real-time adaptation capabilities. The proposed system employs XGBoost for demand forecasting, Apriori algorithm for product recommendations, Long Short-Term Memory (LSTM) networks for time-series prediction, and Reinforcement Learning (Q-learning) for automated replenishment. Advanced techniques including Synthetic Minority Over-sampling Technique (SMOTE) with Tomek Links for class imbalance, Generative Adversarial Networks (GANs) for cold- start scenarios, federated learning for privacy preservation, and digital twin integration for supply chain stress testing are incorporated. The system was validated on retail transaction datasets comprising 5 million records spanning three years across 100 SKUs. Experimental results demonstrate 25% reduction in stockouts, 20% decrease in excess inventory, 15% increase in sales, 30% improvement in inventory turnover ratio, and forecast accuracy exceeding 90% for top SKUs. The platform achieves Mean Absolute Percentage Error (MAPE) of 7.12% and provides estimated profit uplift of $1.2M annually for mid-sized retail chains. This work provides a reproducible foundation for AI-driven retail optimization with documented training configurations, hyperparameters, and evaluation protocols.
Keywords	Keywords: Retail inventory optimization, demand forecasting, XGBoost, LSTM, reinforcement learning, federated learning, digital twin, recommendation systems, AutoML, Green AI.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-29

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

NextBUY: An AI-Driven Smart Retail Inventory Optimization Platform Using Advanced Machine Learning Techniques

Share this