lifecycle:evaluation

Evaluation

Evaluation in the context of production machine-learning systems.

11

Lessons

Formal explanations, examples, simulations, and checkpoints.

Problem framing, statistics & evaluation

Predict decisions, not just labels

Use predict decisions, not just labels to move the evaluation production brief toward a defensible release.

Problem framing, statistics & evaluation

Labels, availability, and leakage

Use labels, availability, and leakage to move the evaluation production brief toward a defensible release.

Problem framing, statistics & evaluation

Baselines and honest splits

Use baselines and honest splits to move the evaluation production brief toward a defensible release.

Problem framing, statistics & evaluation

Metrics, thresholds, and calibration

Use metrics, thresholds, and calibration to move the evaluation production brief toward a defensible release.

Problem framing, statistics & evaluation

Uncertainty and online experiments

Use uncertainty and online experiments to move the evaluation production brief toward a defensible release.

Problem framing, statistics & evaluation

Metric selection by task and decision

Select metrics from the prediction target, decision, error costs, prevalence, slices, horizon, and deployment constraints—not from habit.

Unsupervised learning, anomalies & retrieval

PCA and representation geometry

Use pca and representation geometry to move the unsupervised & retrieval production brief toward a defensible release.

Unsupervised learning, anomalies & retrieval

Clustering as an operational hypothesis

Use clustering as an operational hypothesis to move the unsupervised & retrieval production brief toward a defensible release.

Unsupervised learning, anomalies & retrieval

Density clusters and novel anomalies

Use density clusters and novel anomalies to move the unsupervised & retrieval production brief toward a defensible release.

Unsupervised learning, anomalies & retrieval

Embeddings and similarity

Use embeddings and similarity to move the unsupervised & retrieval production brief toward a defensible release.

Unsupervised learning, anomalies & retrieval

Approximate retrieval under latency

Use approximate retrieval under latency to move the unsupervised & retrieval production brief toward a defensible release.