Notes on data engineering, AI and building things end to end.
“It works on my machine” is the most common way a portfolio project fails to impress a reviewer. Here’s why you should containerize your machine learning model, even for a small project — with real examples.
Read more →
The same model predictions can look excellent on an ROC curve and mediocre on a precision-recall curve. Here’s why that happens, and which one to trust — especially on imbalanced data — with real examples.
Read more →
A model that performed well at launch can quietly degrade every month afterward. Here’s what model drift actually is, how to detect it, and when retraining is (and isn’t) the right fix — with real examples.
Read more →
A model that scores 98% in testing and fails in production almost always has one cause: data leakage. Here’s how it happens, how to catch it, and how to sanity-check your results — with real project examples.
Read more →
An accuracy number with nothing to compare it to is a claim, not evidence. Here’s why a baseline model matters more than the headline metric, and how to pick the right one — with real project examples.
Read more →
A random train/test split lets a time series model peek at the future — which inflates its accuracy in a way that never holds up in production. Here’s how proper time series cross-validation actually works.
Read more →
Labeling the four boxes of a confusion matrix is the easy part. Here’s how to actually read one — what each cell costs, and how to tell if a model is genuinely good enough — with real project examples.
Read more →
New users and new items both break collaborative filtering the same way — no history to work with. Here’s why the cold start problem happens and the techniques that actually help, with real project examples.
Read more →
Most data portfolios run once on a laptop and stop there. Here’s why CI/CD — automated tests, reproducible environments, version tracking — matters for data pipelines just as much as application code, with real examples.
Read more →
SHAP plots look precise, which makes them easy to over-read. Here are the three most common SHAP misinterpretations — and what these values actually tell you, with a real project example.
Read more →