Algorithm Configuration List

Baseline

ConstantGuessRecommender

rec.recommender.class=constantguess

GlobalAverageRecommender

rec.recommender.class=globalaverage

ItemAverageRecommender

rec.recommender.class=itemaverage

ItemClusterRecommender

rec.recommender.class=itemcluster
rec.pgm.number=10
rec.iterator.maximum=20

MostPopularRecommender

rec.recommender.class=mostpopular
rec.recommender.isranking=true

RandomGuessRecommender

rec.recommender.class=randomguess

UserAverageRecommender

rec.recommender.class=useraverage

UserClusterRecommender

rec.recommender.class=usercluster
rec.factory.number=10
rec.iterator.maximum=20

Collaborative Filtering (item ranking)

AOBPRRecommender

rec.recommender.class=aobpr
rec.item.distribution.parameter = 500
rec.iterator.learnrate=0.01
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=100
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnrate.bolddriver=false
rec.learnrate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

AspectModelRecommender

rec.recommender.class=aspectmodelranking
rec.iterator.maximum=20
rec.recommender.isranking=true
rec.recommender.ranking.topn=10
data.splitter.cv.number=5
rec.pgm.burnin=10
rec.pgm.samplelag=10
rec.topic.number=10

BPRRecommender

rec.recommender.class=bpr
rec.iterator.learnrate=0.01
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=100
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnRate.bolddriver=false
rec.learnRate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

CLIMFRecommender

rec.recommender.class=climf
rec.iterator.learnrate=0.001
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=100
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnrate.bolddriver=false
rec.learnrate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

EALSRecommender

rec.recommender.class=eals
rec.iterator.maximum=10
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

# 0：eALS MF; 1：WRMF; 2: both
rec.eals.wrmf.judge=1

# the overall weight of missing data c0
rec.eals.overall=128

# the significance level of popular items over un-popular ones
rec.eals.ratio=0.4

# confidence weight coefficient, alpha in original paper
rec.wrmf.weight.coefficient=4.0

FISMaucRecommender

rec.recommender.class=fismauc
rec.iterator.learnrate=0.01
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=10
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnrate.bolddriver=false
rec.learnrate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

rec.fismauc.rho=2
rec.fismauc.alpha=1.5

FISMrmseRecommender

rec.recommender.class=fismrmse
rec.iteration.learnrate=0.01
rec.iterator.maximum=100
rec.recommender.isranking=true

rec.fismrmse.rho=1
rec.fismrmse.alpha=1.5

GBPRRecommender

rec.recommender.class=gbpr
rec.iterator.learnrate=0.01
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=100
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnrate.bolddriver=false
rec.learnrate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

ItemBigramRecommender

rec.recommender.class=itembigram
data.column.format=UIRT
data.input.path=test/ratings-date.txt
rec.iterator.maximum=100
rec.topic.number=10
rec.recommender.isranking=true
rec.recommender.ranking.topn=10
rec.user.dirichlet.prior=0.01
rec.topic.dirichlet.prior=0.01
rec.pgm.burnin=10
rec.pgm.samplelag=10

LDARecommender

rec.recommender.class=lda
rec.iterator.maximum=100
rec.topic.number = 10
rec.recommender.isranking=true
rec.recommender.ranking.topn=10
rec.user.dirichlet.prior=0.01
rec.topic.dirichlet.prior=0.01
rec.pgm.burnin=10
rec.pgm.samplelag=10
data.splitter.cv.number=5
# (0.0 may be a better choose than -1.0)
data.convert.binarize.threshold=0.0

ListwiseMFRecommender

rec.recommender.class=listwisemf
rec.iterator.learnrate=0.01
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=100
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnrate.bolddriver=false
rec.learnrate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

PLSARecommender

rec.recommender.class=plsa
rec.iteration.learnrate=0.01
rec.iterator.maximum=100
rec.recommender.isranking=true
rec.topic.number = 10
rec.recommender.ranking.topn=10
# (0.0 may be a better choose than -1.0)
data.convert.binarize.threshold=0.0

RankALSRecommender

rec.recommender.class=rankals
rec.iterator.learnrate=0.01
rec.iterator.learnrate.maximum=0.01
rec.iterator.maximum=100
rec.user.regularization=0.01
rec.item.regularization=0.01
rec.factor.number=10
rec.learnrate.bolddriver=false
rec.learnrate.decay=1.0
rec.recommender.isranking=true
rec.recommender.ranking.topn=10

rec.rankals.support.weight=true