An improved advertising CTR prediction approach based on the fuzzy deep neural network.
Combining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from adv...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2018-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC5935396?pdf=render |
id |
doaj-bd18d2c6b4aa42d5bed89b72ab363f98 |
---|---|
record_format |
Article |
spelling |
doaj-bd18d2c6b4aa42d5bed89b72ab363f982020-11-25T00:02:10ZengPublic Library of Science (PLoS)PLoS ONE1932-62032018-01-01135e019083110.1371/journal.pone.0190831An improved advertising CTR prediction approach based on the fuzzy deep neural network.Zilong JiangShu GaoMingjiang LiCombining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from advertising datasets. Next, fuzzy restricted Boltzmann machine (FRBM) is used to construct the fuzzy deep belief network (FDBN) with the unsupervised method layer by layer. Finally, fuzzy logistic regression (FLR) is utilized for modeling the CTR. The experimental results show that the proposed FDNN model outperforms several baseline models in terms of both data representation capability and robustness in advertising click log datasets with noise.http://europepmc.org/articles/PMC5935396?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zilong Jiang Shu Gao Mingjiang Li |
spellingShingle |
Zilong Jiang Shu Gao Mingjiang Li An improved advertising CTR prediction approach based on the fuzzy deep neural network. PLoS ONE |
author_facet |
Zilong Jiang Shu Gao Mingjiang Li |
author_sort |
Zilong Jiang |
title |
An improved advertising CTR prediction approach based on the fuzzy deep neural network. |
title_short |
An improved advertising CTR prediction approach based on the fuzzy deep neural network. |
title_full |
An improved advertising CTR prediction approach based on the fuzzy deep neural network. |
title_fullStr |
An improved advertising CTR prediction approach based on the fuzzy deep neural network. |
title_full_unstemmed |
An improved advertising CTR prediction approach based on the fuzzy deep neural network. |
title_sort |
improved advertising ctr prediction approach based on the fuzzy deep neural network. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2018-01-01 |
description |
Combining a deep neural network with fuzzy theory, this paper proposes an advertising click-through rate (CTR) prediction approach based on a fuzzy deep neural network (FDNN). In this approach, fuzzy Gaussian-Bernoulli restricted Boltzmann machine (FGBRBM) is first applied to input raw data from advertising datasets. Next, fuzzy restricted Boltzmann machine (FRBM) is used to construct the fuzzy deep belief network (FDBN) with the unsupervised method layer by layer. Finally, fuzzy logistic regression (FLR) is utilized for modeling the CTR. The experimental results show that the proposed FDNN model outperforms several baseline models in terms of both data representation capability and robustness in advertising click log datasets with noise. |
url |
http://europepmc.org/articles/PMC5935396?pdf=render |
work_keys_str_mv |
AT zilongjiang animprovedadvertisingctrpredictionapproachbasedonthefuzzydeepneuralnetwork AT shugao animprovedadvertisingctrpredictionapproachbasedonthefuzzydeepneuralnetwork AT mingjiangli animprovedadvertisingctrpredictionapproachbasedonthefuzzydeepneuralnetwork AT zilongjiang improvedadvertisingctrpredictionapproachbasedonthefuzzydeepneuralnetwork AT shugao improvedadvertisingctrpredictionapproachbasedonthefuzzydeepneuralnetwork AT mingjiangli improvedadvertisingctrpredictionapproachbasedonthefuzzydeepneuralnetwork |
_version_ |
1725439027292667904 |