Robotics + ISM: Autonomous Vehicle Liability

At a glance

Task: classification  |  Headline: accuracy = 0.9976

Summary

Project

Config-driven data science pipeline for high-fidelity industrial domains.

What was investigated

The engagement modelled the target 'liability_class' as a classification problem in the Robotics + ISM: Autonomous Vehicle Liability domain, using 2000 records across 23 columns (data source: Synthetic sandbox). The pipeline audited data quality, engineered features, split the data honestly into train/test, and compared several models by cross-validation.

Outcome

The selected model was XGBoost, with f1_macro = 0.9833 on the held-out test set. Supporting metrics: accuracy=0.998, balanced_accuracy=0.993, precision_weighted=0.998, recall_weighted=0.998, f1_weighted=0.998, precision_macro=0.975, recall_macro=0.993, cohen_kappa=0.990, matthews_. Full results, the deployment gates and the audit trail are in the run's report.

Figures

Artifacts

Data source: Synthetic sandbox

Audit SHA-256: ea61f0c3deb87b0f1760d375473b24ed23c555f2d332207d38b2940c080ed53f