Ai-based Supply Chain Risk Prediction System Using Machine Learning

Abstract

Supply Chain Systems Are Highly Vulnerable To Disruptions Caused By Factors Such As Transportation Delays, Traffic Congestion, Weather Conditions, And Inventory Fluctuations. Traditional Risk Assessment Methods Are Largely Manual, Time-consuming, And Often Fail To Provide Accurate And Timely Insights. This Project Presents An Intelligent Web-based System For Predicting Supply Chain Risk Using Machine Learning Techniques. The Proposed System Utilizes A Random Forest Classifier To Analyze Key Operational Parameters, Including Delay, Traffic, Weather, Inventory, Order Value, And Port Delay. Based On These Inputs, The System Classifies Supply Chain Risk Into Three Categories: Low, Medium, And High. The Application Is Developed Using The Flask Framework And Integrates A User-friendly Interface For Manual Data Entry, CSV-based Batch Prediction, And Real-time Analytics Through A Dashboard. The System Also Includes Data Storage Using SQLite And Visualization Features Such As Charts And Export Functionalities For Excel And Image Formats. Experimental Results Indicate Moderate Model Performance, With An Accuracy Of Approximately 61.9% And Balanced Accuracy Of Around 67%, Highlighting The Need For Further Optimization. Despite These Limitations, The System Demonstrates The Practical Application Of Machine Learning In Supply Chain Risk Prediction And Provides A Foundation For Future Enhancements In Predictive Logistics Systems.

Keywords