Discounted cumulative gain
Discounted cumulative gain is a ranking metric that sums graded relevance gains while reducing the contribution of items at lower positions in a ranked list.
Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI
A ranking metric that scores results by graded relevance while discounting results at lower ranks.
- How it is used
- Evaluates ranked retrieval results and annotator rankings, giving greater weight to relevance near the top.
- How deep it goes
- Defines graded relevance and logarithmic discounting, then describes normalization without a worked numerical calculation.
- Examples
- Uses online shopping results and annotators ranking candidate responses to illustrate ranked relevance.
- What you can do after
- Evaluate ranked search results and annotator rankings using graded relevance and position.
AI Recommender Systems
Discounted cumulative gain is a ranking metric that sums relevance gains after reducing the contribution of items appearing lower in the list.
- How it is used
- Evaluates recommendation rankings by rewarding relevant items that appear near the top.
- How deep it goes
- Defines gain, logarithmic discounting, DCG, and normalization, then stops short of a complete derivation.
- Examples
- Uses recommendation lists with identical relevant items at different positions and compares metrics across cutoff values.
- What you can do after
- Evaluate recommendation lists with DCG or nDCG at selected cutoff positions.
Read how AI Recommender Systems explains discounted cumulative gain →
What to know first
- relevanceRelevance is the degree to which information, a result, or a response pertains to a query, task, purpose, or information need.
- precisionPrecision is the proportion of items predicted, selected, or retrieved as positive that are correct or relevant.
- recallRecall is the proportion of all relevant or actual positive items that a system successfully retrieves or correctly identifies.
Related concepts
- relevancemeasures · Relevance is the degree to which information, a result, or a response pertains to a query, task, purpose, or information need.
- gainuses · Gain is a relevance value assigned to an item, often binary or graded, that contributes to a ranking-quality score.
- normalized discounted cumulative gainused by · Normalized discounted cumulative gain is a ranking metric that discounts graded relevance by item position and normalizes the result against the ideal ranking.
- precisionalternative to · Precision is the proportion of items predicted, selected, or retrieved as positive that are correct or relevant.
- discount functionuses · A discount function reduces the contribution of a relevance value according to an item's position in a ranked list.
Questions about discounted cumulative gain
What is discounted cumulative gain?
Discounted cumulative gain is a ranking metric that sums graded relevance gains while reducing the contribution of items at lower positions in a ranked list.
Which Manning books explain discounted cumulative gain?
Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI and AI Recommender Systems.
What should I know before learning discounted cumulative gain?
Manning books that teach discounted cumulative gain usually introduce relevance, precision and recall first.
What is the difference between discounted cumulative gain and precision?
Discounted cumulative gain is a ranking metric that sums graded relevance gains while reducing the contribution of items at lower positions in a ranked list. Precision is the proportion of items predicted, selected, or retrieved as positive that are correct or relevant.
What is discounted cumulative gain also called?
Discounted cumulative gain is also called DCG.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

