Project Overview
CVE Forecast is a self-improving automated platform that leverages advanced hyperparameter optimization and 25+ time series forecasting models to predict Common Vulnerabilities and Exposures (CVEs). The system provides data-driven insights into future vulnerability disclosure trends through an intelligent, continuously-evolving forecasting pipeline.
π§ Self-Improving AI
Comprehensive tuner learns from previous runs and continuously optimizes 25+ models across statistical, ML, and deep learning categories.
β‘ Dynamic Optimization
Intelligent timeout redistribution and adaptive search strategies maximize resource utilization during hyperparameter exploration.
ποΈ Production Architecture
Modular design with 5 core modules ensures maintainability, extensibility, and enterprise-grade reliability.
System Architecture
CVE Forecast employs a sophisticated, self-improving architecture that combines 25+ forecasting models with intelligent optimization capabilities.
ποΈ Core Components
- main.py: Orchestrates entire forecasting workflow
- data_loader.py: Processes 300K+ CVE JSON files
- model_trainer.py: Trains and evaluates models
- utils.py: Logging and configuration management
- comprehensive_tuner.py: Hyperparameter optimization
π Model Categories (25+ Models)
π§ Self-Improving Optimization
Revolutionary Workflow: The comprehensive tuner learns from previous runs, only updating configurations when improvements are found, creating an intelligent system that evolves over time.
- Dynamic Timeout Redistribution: Unused time from fast models redistributed to slower ones
- Adaptive Search Strategies: Grid/random search selection based on model complexity
- Dual-Config Management: Updates both production and tuner configurations
- Performance Tracking: Maintains optimization history and automatic backups
π Evaluation System
Dual-Metric Evaluation:
- MAPE: Primary ranking metric for model selection
- MAE: Intuitive error measurement in original CVE units
Deployment & Automation
The system features fully automated CI/CD pipeline with daily updates and intelligent optimization integration.
π GitHub Actions Workflow
- Daily scheduled execution (midnight UTC)
- Automatic CVE data fetching and processing
- Model training and forecast generation
- Intelligent hyperparameter optimization
- Automated deployment and configuration updates
β‘ Production Features
- Processes 300K+ CVE JSON files daily
- Dynamic forecasting through January 2026
- Self-improving optimization workflow
- Automatic configuration backups
- Comprehensive validation and error handling
Change Log
π v.07 - Security Summer Camp Prep ποΈ (August 2025)
Fixed critical month transition bug in cumulative total calculations, ensuring accurate data representation across month boundaries
π οΈ Bug Fix Details
- Replaced hard-coded month references with dynamic month detection
- Ensured cumulative totals properly build upon the previous month's values
- Fixed inconsistencies in cumulative statistics when crossing month boundaries
- Implemented future-proof solution that works reliably for all calendar transitions
- Added comprehensive logging to track cumulative total calculations
v.06 - KarlΕ―v mos π¨πΏ (July 2025)
Revolutionary self-improving forecasting system with intelligent hyperparameter optimization
π§ Intelligent Optimization
- Comprehensive hyperparameter tuner for 19+ models
- Self-improving workflow that learns from previous runs
- Adaptive grid/random search selection
- Intelligent timeout management and progress tracking
π Automated Infrastructure
- Daily GitHub Actions integration with tuner
- Automatic configuration backup and management
- End-to-end validation pipeline
- Complete self-optimization workflow
- Support for 25+ models across Statistical, Tree-Based, and Deep Learning categories
- Enterprise-grade modular architecture with 7 focused modules
- Enhanced model stability with comprehensive error handling
- Dynamic forecasting with automatic period adaptation
v.05 - Adolfo SuΓ‘rez Madrid-Baraja πͺπΈ
- Fixed a critical bug that prevented the cumulative graph from rendering due to an incorrect data structure in
data.json. - Restored frontend compatibility by correcting the data generation logic, ensuring all charts now load correctly.
v.04 ORD βοΈ MAD
- Enhanced model stability with improved error handling.
- Added input validation and scaling for better numerical stability.
- Optimized for CPU-only environments.
- Implemented dynamic forecast period calculation.
- Improved model selection based on MAPE scores.