es.uam.eps.ir.ranksys.metrics.basic

Class NDCG<U,I>

java.lang.Object

es.uam.eps.ir.ranksys.metrics.AbstractRecommendationMetric<U,I>

es.uam.eps.ir.ranksys.metrics.basic.NDCG<U,I>

Type Parameters:

U - type of the users

I - type of the items

All Implemented Interfaces:

RecommendationMetric<U,I>

public class NDCG<U,I>
extends AbstractRecommendationMetric<U,I>

Normalized Discounted Cumulative Gain metric. See: Kalervo Järvelin and Jaana Kekäläinen. 2000. IR evaluation methods for retrieving highly relevant documents. In Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval (SIGIR '00). ACM, New York, NY, USA, 41-48. DOI=10.1145/345508.345545 http://doi.acm.org/10.1145/345508.345545

Author:

Saúl Vargas (saul.vargas@uam.es), Pablo Castells (pablo.castells@uam.es)

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	NDCG.NDCGRelevanceModel<U,I> Relevance model for nDCG, in which the gains of all relevant documents need to be known for the normalization of the metric.

Constructor Summary

Constructors

Constructor and Description
NDCG(int cutoff, NDCG.NDCGRelevanceModel<U,I> relModel) Constructor.

Method Summary

Modifier and Type	Method and Description
double	evaluate(Recommendation<U,I> recommendation) Returns a score for the recommendation list.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

NDCG

public NDCG(int cutoff,
            NDCG.NDCGRelevanceModel<U,I> relModel)

Constructor.

Parameters:

cutoff - maximum length of evaluated recommendation lists

relModel - relevance model

Method Detail

evaluate

public double evaluate(Recommendation<U,I> recommendation)

Returns a score for the recommendation list.

Parameters:

recommendation - recommendation list

Returns:

score of the metric to the recommendation