Tools & technologies
Machine learning pipelines
From raw data to a trained model, with a process you can repeat: data preparation, leakage-free validation, model comparison and honest evaluation.
From raw data to a trained model, with a process you can repeat: data preparation, leakage-free validation, model comparison and honest evaluation.
Leakage-free, from the start
Preprocessing lives inside the pipeline, so it is fit only on the training data in each cross-validation fold. What I measure in validation is what I can expect on new data, not an inflated number.
Evaluation that tells the truth
Metrics that fit the problem, not just accuracy: ROC-AUC and PR-AUC on imbalanced data, probability calibration and per-segment error analysis to see where the model fails and why.
Operating locations
Studying in Madrid
Based in Madrid, learning in public: projects, open-source tools and collaborations, inside and outside Spain.
Info graphic
Decision flow
Reproducible, not a loose notebook.
Info graphic
Friction map
Leakage-free validation.
Info graphic
Journey shape
Honest evaluation.
Next projects:
MLOPSFASTAPIDOCKERMONITORING
Credit Risk Platform
End-to-end MLOps platform for credit-default scoring: reproducible training with a versioned model registry, a FastAPI inference API with input validation, PSI drift monitoring and a Prometheus and Grafana observability stack, all containerised with CI. Code at github.com/delcenjo/credit-risk-platform.
View project
PYTORCHTRANSFORMERSNLP
Transformer from scratch
A GPT-style language model implemented from scratch in PyTorch: multi-head attention, causal masking and residual blocks written by hand, plus a byte-pair tokenizer and an ablation study. Code at github.com/delcenjo/transformer-from-scratch.
View project
NEXT.JSWEBASSEMBLYCLOUDFLARECI/CD
This very site
This portfolio is hand-built with Next.js and deployed on Cloudflare Workers, with a model lab that runs entirely in the browser and continuous deployment on every commit. Code at github.com/jmweb-org/jmweb-pag-web.
View project
SCIKIT-LEARNCALIBRATIONTABULAR
Credit Risk Model
Credit-default risk model with rigorous evaluation: a leakage-free pipeline, cross-validated model comparison, calibrated probabilities, a cost-based decision threshold and per-segment error analysis. Code at github.com/delcenjo/credit-risk.
View project