Glossary · Analytics

nDCG

Normalized discounted cumulative gain — the standard offline metric for ranking quality.

nDCG scores a ranked list against an ideal one: relevant items earn gain, discounted logarithmically by position, and the result is normalized so 1.0 is a perfect ranking. It rewards putting the most relevant item first, which is exactly what a search page needs.

You compute it against a golden query set — queries with judgements about which results should rank. AACSearch's quality lab keeps those sets, scores every proposed change offline, and flags runs that drop mean nDCG before anything ships.

Related terms

Golden query set A/B testing

Test AACSearch on your own problem

The best way to evaluate a search platform isn't reading one more comparison table.

Upload your own data.
Run real queries.
Look at the Query Trace.
Compare relevance.
Work out the cost.

Only then make the decision.

Start free Open Playground See the documentation