VQD-CTS, Software Engineering, Dataset

# VQD-CTS Dataset: Software Engineering Metrics for Cost-to-Serve Prediction

This dataset contains synthetic enterprise software engineering metrics for predicting Cost-to-Serve (CTS) using Velocity, Quality, and Developer Experience (VQD) indicators. 

#Package ContentsThis ZIP file contains 4 files:- *vqd_cts_dataset.csv`** - Main dataset (654 software projects, 25 features)- *README_DATA.md`** - Complete usage instructions and documentation- *`data_dictionary.pdf`** - Detailed variable definitions and descriptions  - *LICENSE`** - CC BY 4.0 International license terms

#Dataset Overview- **Records:** 654 software projects from enterprise environments- **Features:** 25 engineering and financial metrics + target variable- **Target Variable:** `cost_to_serve` - Total cost to serve/support each project- **Format:** CSV (comma-separated values)- **Size:** ~200 KB uncompressed

# Feature Categories

##Velocity Metrics- `story_points_completed` - Agile story points delivered- `cycle_time` - Time from start to completion- `deployment_frequency` - Deployment cadence- `lead_time` - Time from concept to delivery- `commits_per_dev` - Developer productivity

### Quality Metrics  - `defect_density` - Defects per code unit- `escaped_defects` - Production defects- `test_coverage` - Code test coverage percentage- `technical_debt_ratio` - Technical debt measure- `code_smell_density` - Code quality issues

# Developer Experience Metrics- `developer_satisfaction` - Team satisfaction (1-5 scale)- `onboarding_hours` - New developer ramp-up time- `tool_efficiency` - Development tool effectiveness- `context_switch_frequency` - Task switching rate

# Financial & Contextual Metrics- `infrastructure_cost_share` - Infrastructure cost percentage- `average_hourly_rate` - Developer cost rates- `project_context` - Project type (Greenfield, Maintenance, etc.)- `team_size` - Development team size- `domain_complexity` - Business domain complexity

# Intended Use Cases- Software engineering economics research- DevOps performance analysis- AI/ML model training for cost prediction- Engineering efficiency benchmarking- Academic research in software metrics

# Related PublicationThis dataset supports the research paper:**"VQD-CTS Prediction Model: An AI-Driven Framework for Predicting Cost-to-Serve Using Engineering Velocity, Quality, and Developer Experience

 Reproduction CodeComplete reproduction code available at: [Your GitHub Repository URL]

 Important Notes- This is a **synthetic dataset** designed to reflect real enterprise patterns while preserving privacy- Data generation ensured realistic correlations between engineering and financial metrics- Suitable for machine learning, statistical analysis, and research purposes

 Usage Instructions1. Download this ZIP file2. Extract all files3. Use `vqd_cts_dataset.csv` for analysis4. Refer to `README_DATA.md` for detailed documentation5. Consult `data_dictionary.pdf` for variable definitions

 LicenseCreative Commons Attribution 4.0 International (CC BY 4.0)