SUPPLY CHAIN DISRUPTION ANALYSIS USING LONG SHORT - TERM MEMORY NETWORKS

Authors:

J. Prem Kumar, A. Siddharth, V. Sharash Chandra, Mr. G. Satish kumar

Page No: 1072-1079

Abstract:

Supply chain disruptions pose significant challenges to industries worldwide, impacting production efficiency, cost management, and customer satisfaction. Traditional supply chain risk management relies on historical data, rule-based models, and expert-driven decisions, which often fail to predict disruptions caused by dynamic and unforeseen factors such as geopolitical instability, climate change, and demand fluctuations.

Description:

.

Volume & Issue

Volume-14,Issue-4

Keywords

Supply Chain Disruption, Long Short-Term Memory (LSTM), Machine Learning, Predictive Analytics, Risk Management, Random Forest Classifier (RFC), Temporal Data Analysis, Supply Chain Resilience, SMOTE (Synthetic Minority Over-sampling Technique), Hybrid Deep Learning Models..