Curated Projects
This page highlights a selective portfolio of projects that have been reviewed for provenance, methodology, reproducibility, data boundaries, and claim quality. Older notebooks and course exercises are not promoted simply because they exist.
Each featured project links to the maintained reconstruction in the DataForSolution curated portfolio, where the source, tests, audit notes, dependencies, and limitations are documented.
Healthcare & Medical Imaging
PETQuant Reliability
PET quantitative-ML reconstruction focused on small-sample limits, data-quality contracts, and defensible validation claims.
Chest CT Classification
Medical-imaging transfer-learning reconstruction emphasizing overfitting analysis, split integrity, and deterministic evaluation.
Pima Diabetes ML Evaluation
Leakage-safe SVM/MLP retrospective with clinically relevant missing-measurement handling and sensitivity/specificity reporting.
Responsible & Explainable AI
SHAP + LIME Explainability
Class-aligned explanation workflow with corrected label ordering, scaled modeling, and defensible attribution aggregation.
Fairness Evaluation
Explicit group-fairness metrics and threshold analysis with fixed reference labels and documented AIF360 provenance.
Adversarial Robustness
Bounded PGD and defense-evaluation reconstruction with preprocessing, threat-model, and denominator corrections.
Applied Machine Learning & NLP
Automobile Insurance Fraud Classification
Temporal, imbalance-aware evaluation showing why high overall accuracy can coexist with zero minority-class recall.
Restaurant Review Sentiment Evaluation
Leakage-safe NLP model comparison using fold-local TF-IDF pipelines and a clearly licensed UCI Yelp data source.
CIFAR-10 Generated-Image Analysis
Classifier-response diagnostics for generated images with a clear separation between classifier confidence and perceptual realism.
Data Engineering
AWS Glue + EMR PySpark Ingestion Validation
Catalog-resolution and ingestion-quality engineering based on a historical embedded-header defect discovered in an EMR/Glue run.
Why only these projects?
The broader archive contains tutorials, course templates, duplicate notebooks, experiments with untraceable data, and projects whose original methodology does not support a strong public claim. Those materials are retained only when useful as historical evidence; they are not presented as equivalent to the maintained portfolio above.