IFOS: AN ML-POWERED REAL-TIME INTELLIGENT FILE ORGANIZATION SYSTEM

Abstract: This paper presents the Intelligent File Organization System (IFOS), a lightweight supervised machine learning solution that automatically classifies and sorts files into predefined folders the moment they are downloaded. On average, a typical user downloads over 500 files per month across diverse categories PDFs, images, videos, archives, executables all accumulating in a single downloads folder with no automatic organization. When IFOS detects a new file, it extracts a 13-dimensional feature vector comprising file extension, MIME type, binary magic number bytes (first 8 bytes), log-transformed file size, and Shannon entropy, and passes it to a trained Random Forest classifier. The predicted category triggers an automated file-move operation into the corresponding pre-existing directory, requiring zero user intervention. Unlike rule-based tools that fail on mislabeled or extension-less files, IFOS is content-aware and achieves 97.4% classification accuracy and 87 ms average end-to-end latency across a balanced dataset of 10,000 real-world files spanning 10 categories.

Keywords: Machine Learning, File Classification, Intelligent File Organization, MIME Type Detection, Magic Numbers, Shannon Entropy, Random Forest, File System Automation, Real-Time Monitoring, Download Manager, Supervised Learning, Edge Case Robustness, Cross-Platform Automation