Understanding Relevance Metrics: NDCG, Precision, and Hit Rate

girijesh s. · 2024-08-16T13:47:10.511Z

Hello, Any documents on relevance ndcg, precision and hit, explaining what it is?

NDCG (Normalized Discounted Cumulative Gain): Measures the ranking quality of retrieved documents, considering the position of relevant documents. Higher scores indicate better ranking. Source.

Precision: Fraction of relevant documents among the retrieved ones. Higher precision means more relevant documents were retrieved. Source.

Hit: Indicates if at least one relevant document was retrieved. A hit rate of 1 means at least one relevant document was found. Source.

Would you like more detail?

Sources: - https://github.com/arize-ai/phoenix/blob/main/src/phoenix/metrics/retrieval_metrics.py

💡 Hint: Mention RunLLM in the thread for followups.

Understanding Relevance Metrics: NDCG, Precision, and Hit Rate

1 comment

Understanding Relevance Metrics: NDCG, Precision, and Hit Rate

1 comment