Ganho Cumulativo Descontado Normalizado (NDCG) é uma métrica popular usada em recuperação de informações and sistemas de recomendação to evaluate the quality of ranked lists. NDCG takes into account the position of relevant documents in the ranked list, emphasizing the importance of higher-ranked items. The metric is especially useful in scenarios where the relevance of items is not binary but graded (e.g., on a scale from 0 to 3).
O cálculo do NDCG envolve duas etapas principais: primeiro, computing the Ganho Cumulativo (CG), which sums the relevance scores of the retrieved items based on their ranks. The second step is applying a Função de Desconto, often logarithmic, to reduce the weight of lower-ranked items, reflecting the principle that users are more likely to engage with items presented earlier in the list.
Para normalizar o CG, o NDCG usa um Ganho Cumulativo Descontado Ideal (IDCG), which represents the maximum possible gain for an ideal ranking de itens. A pontuação final do NDCG é calculada como:
NDCG = (DCG) / (IDCG)
This normalization ensures that NDCG values range from 0 to 1, making it easier to compare the effectiveness of different algoritmos de classificação. A higher NDCG score indicates better retrieval performance, as it means that relevant items are ranked higher.
NDCG is widely used in various applications, including search engines, recommendation systems, and aprendizado de máquina models, to assess how well a system meets user expectations and retrieves pertinent information.