Long short-term memory based movie recommendation
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
Research Article
Open Access Full Text Article
Long Short-Term Memory Based Movie Recommendation
Duy Bao Tran, Thi Thanh Sang Nguyen*
ABSTRACT
Recommender systems (RS) have become a fundamental tool for helping users make decisions
around millions of different choices nowadays – the era of Big Data. It brings a huge benefit for
Use your smartphone to scan this
QR code and download this article
many business models around the world due to their effectiveness on the target customers. A lot
of recommendation models and techniques have been proposed and many accomplished incred-
ible outcomes. Collaborative filtering and content-based filtering methods are common, but these
both have some disadvantages. A critical one is that they only focus on a user's long-term static
preference while ignoring his or her short-term transactional patterns, which results in missing the
user's preference shift through the time. In this case, the user's intent at a certain time point may be
easily submerged by his or her historical decision behaviors, which leads to unreliable recommen-
dations. To deal with this issue, a session of user interactions with the items can be considered as
a solution. In this study, Long Short-Term Memory (LSTM) networks will be analyzed to be applied
to user sessions in a recommender system. The MovieLens dataset is considered as a case study
of movie recommender systems. This dataset is preprocessed to extract user-movie sessions for
user behavior discovery and making movie recommendations to users. Several experiments have
been carried out to evaluate the LSTM-based movie recommender system. In the experiments,
the LSTM networks are compared with a similar deep learning method, which is Recurrent Neural
Networks (RNN), and a baseline machine learning method, which is the collaborative filtering us-
ing item-based nearest neighbors (item-KNN). It has been found that the LSTM networks are able
to be improved by optimizing their hyperparameters and outperform the other methods when
predicting the next movies interested by users.
Key words: Deep learning, Long Short-Term Memory, Recommender systems, Sequence mining
School of Computer Science and
Engineering, International University,
Vietnam National University Ho Chi
Minh City, Vietnam
provided to find out the best model.
In the following, next section presents Related work.
Section Research Methodology gives a problem de-
scription and approaches to the LSTM-based movie
recommender systems. Section Experimental results
and evaluation proposes an optimization solution of
the LSTM model for more effective movie recommen-
dation. Discussion are explained in Section Discus-
INTRODUCTION
Nowadays, there is a huge of information on the In-
ternet which leads to the difficulty of users for choos-
ing the suitable one with their limitation time and
thought. A lot of decisions must be given every day
from the smallest to the biggest. Many topics have
been given around the factor of making decisions, and
a recommender system is the most successful strat-
Correspondence
Thi Thanh Sang Nguyen, School of
Computer Science and Engineering,
International University, Vietnam
National University Ho Chi Minh City,
Vietnam
sion. Section Conclusions concludes this study.
Email: nttsang@hcmiu.edu.vn
egy up to now. Many RS models depend on the rela-
History
tionship between users and items, but the one in the
study relies on user sessions known as usage knowl-
edge. One session of a user is the historical interac-
tions of his/her on the items. In other words, one ses-
sion of a user consists of one or more items clicked
or rated by this person, so it can be described as the
sequential data. erefore, the deep recurrent net-
work such as Recurrent Neural Networks (RNNs) and
LSTM can demonstrate their effectiveness in process-
ing this data. In this approach, a LSTM-based model
is produced for building the movie recommender sys-
tem relying on the user interaction data (session).
Moreover, a comparison between the proposed ap-
RELATED WORK
• Received: 10-8-2019
• Accepted: 22-8-2019
• Published: 19-9-2019
commerce systems, which help customers do trans-
actions, such as, shopping or searching. Several
popular approaches to recommendation are collabo-
rative filtering models, content-based recommender
systems, knowledge-based recommender systems,
demographic recommender systems or hybrid and
ensemble-based recommender systems. In this study,
we consider the knowledge of user interactions with
information systems to gain items of interest. In
other words, this study aims to build knowledge-
based recommender systems by mining user ses-
DOI : 10.32508/stdjet.v3iSI1.540
Copyright
© VNU-HCM Press. This is an open-
access article distributed under the
terms of the Creative Commons
Attribution 4.0 International license.
proach versus RNN and a baseline method will be sions. As known, user behavior is interested much in
Cite this article : Tran D B, Nguyen T T S. Long Short-Term Memory Based Movie Recommendation.
Sci. Tech. Dev. J. – Engineering and Technology; 3(S1):SI1-SI9.
SI1
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
most recommender systems. Data mining algorithms For solving the problem, the approach of session par-
rangement for the sessions is created. Aꢀer that, the
first interaction of the first X sessions forms the in-
put of the starting mini-batch (the ideal output be-
come the second interactions of the active sessions).
e next mini-batch’s appearance is from the second
interaction and so on. In reality, the system can un-
derstand when the session of user ended, from that
state, the next available session will be put in place.
In this model, sessions are assumed to be indepen-
dent, so the appropriate hidden state is reset when this
switch occurs. For more details, the session-parallel
which are oꢀen applied are sequence mining algo-
ing (DL). Tree-based algorithms have achieved high
performance in terms of recommendation precision
and saving memory for storing tree-based knowledge
advantages in terms of accuracy but takes much mem-
the buying session data which is extracted from the
clickstream data of an e-commerce site can be learned
using Deep Belief Networks and Stacked Denoising
auto-Encoders. By experiments, it has been shown
that the learned results can make purchase predictions
with high accuracy, greater than 80%. In the study of
ployed to the collaborative filtering process in order
Deep recurrent network (LSTM) for session-
based movie recommender system
to make movie recommendations. e Movielens 1M LSTM - a straightforward solution of RNN is found
and Netflix datasets were used, and it has been found by Sepp Hochreiter and Jürgen Schmidhuber in 19977
can tackle the vanishing and exploding gradient prob-
lem. e term “memory” is used instead of “neural”
to perform the size and complexity in the structure of
LSTM. e computational unit of the LSTM network
is called the memory cell, memory block, or just cell
for short, and there are many more computation tasks
than the one in RNN.
In LSTM network, there are four main components
including three gates, block input, memory cell, out-
put activation function. For a complex structure of
LSTM, each gate plays a specific role in computation:
+ Forget gate: chooses which information to discard
from the cell.
+ Input gate: decides what values from the output to
update the memory state.
+ Output gate: exposes the contents of the memory
cell (or not) from the output of LSTM unit.
e output of the LSTM block is recurrently con-
nected back to the block input and all of the gates for
the LSTM block. e input, forget, and output gates
in an LSTM unit have sigmoid activation functions
for [0, 1] restriction. e LSTM block input and out-
put activation function (usually) is a tanh activation
function. As same as RNN or other Neural Networks,
form the learning model.
that LSTM (a particular case of RNNs) overcomes
the Markov chain model, the collaborative filtering
using user-based nearest neighbors (user-KNN), and
Bayesian Personalized Ranking – Matrix Factoriza-
tion (BPR-MF).
As seen, RNNs are efficient for sequence mining in
recommender systems. erefore, this study focuses
on RNNs and sequential pattern discovery, particu-
larly, the user sessions of watching movies are dis-
covered to build movie recommender systems. e
following presents sequence model construction and
deep recurrent neural networks for session-based
movie recommender systems.
Sequence model construction for session-
based movie recommender system
A session can be used as an ingredient to be fed under
sequential data. In order words, a session is the list of
movies rated by a specific user arranged in an order
of timestamps, which is commonly used in sequences
of mini batches. It is possible to use a sliding win-
dow as same as its application for words in sentences
in natural language processing then put all windowed
fragments next to each other in order to form mini-
batches. However, that does not fit to the purpose of
RS due to two reasons:
+ e length of the sessions is different between some
users, it does not run steadily as same as the sentence
structure sequence model: some sessions contain only
one interaction (click, view, or rate) by one user, while
others range more than hundreds.
RESEARCH METHODOLOGY
Problem description and approaches to
the proposed LSTM-based movie recom-
mender system
+ e purpose for mining movie sessions is to cap-
In this section, we present problems and approaches
ture how it evolves over a period, so splitting them to the proposed LSTM-based movie recommender
into fragments makes no sense.
system.
SI2
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
Figure 1: Session-based model consideration on Movie RS
Overall architecture of the LSTM-based
movie recommender system
At the beginning, the input contains interaction data
(sessions) of users under sequential type converted
from a mini-batch model, which will be discussed
briefly in the next section. e next task is to set
up a presentation type for sequential data. In this
approach, the sequence of sessions is zipped under
Interaction, which is the numeric representation of
users and items by timestamp. In general, a sequence
interaction object consists of three factors:
+ e identifier of a user who made the interactions.
+ e tensor consists of several vectors of movie items,
which are interacted by that user.
+ e maximum length of the sequence existed in the
object.
Aꢀer that, each sequence in the sequence interaction
object is gone through an embedding layer, which is
used to represent the weight of movie items followed
by the order of the movie items in the sequence. e
last item in the sequence receives the higher weight
than others due to its up-to-date. en, each embed-
ded sequence is put through an amount of LSTM lay-
duce the factorization matrix which is the predicted
score on each movie. e sorted score can be used
for recommendation. e overall architecture for this
Figure 2: Overall workflow of the LSTM-based
movie recommender system
SI3
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
plays the same role as unsupervised learning. In
fact, there is no ensure that the list of movies recom-
mended to user is correct or not. us, the used eval-
uation method is a statistical measure to visualize the
distribution of the testing test and validation test.
Choosing a golden splitting ratio is an indispensable
process in data splitting. It is usually called a cross val-
idation process. e 80 – 20 or 90 – 10 (percentage)
has been a golden ratio in both theoretical and prac-
tical applications. In this study, the 80% for training
data, 10% for testing data and 10% for validation data
are applied for cross validation.
Gradient Optimization for LSTM model in the
movie recommender system
In this study, stochastic gradient descent (SGD) ap-
proach is used to optimize the gradient in the LSTM
network due to its performance much faster in com-
parison with Mini-batch gradient descent. Specifi-
LSTM networks. Adam is the abbreviation of adap-
tive moment estimation, which has a little bit differ-
ent in comparison to classical SGD, it only needs first-
order gradients thus there is an increment of perfor-
mance in reality. e method computes individual
adaptive learning rates for different parameters from
estimates of first and second moments of the gradi-
Framework for detecting the appropriate
data and evaluating the learning model in
instead of others, due to its ability to minimize cost.
Adam keeps parameter’s magnitude update is invari-
ant to the rescaling of the gradient. erefore, to keep
Adam update efficiently, the choice of stepsize is com-
pulsory. erefore, there are several tests when defin-
ing a hyperparameter stepsize in order to return the
best result of LSTM. More details, in Adam structure,
four basic configuration parameters are mentioned
as the learning rate α, two exponential decay rates
β1, β2 in bounded [0, 1) and epsilon ε that is really
small ( < 10−7 ) to avoid zero division.
mately 10 million interactions is used. At the begin-
ning, from the movie dataset, some features are cho-
sen to build the proposed RS. en, data preprocess-
ing is applied to clean and convert user sessions to se-
quences. Aꢀer that, the dataset splitting is applied to
define three sets. e training set is fed into the model
and do some tests to choose the best hyperparameter
which can minimize the loss. Finally, the evaluation
on the validation and testing sets by using Mean Re-
ciprocal Rank (MRR) and other evaluation metrics as
Precision@k, Recall@k and F1-Score@k is to confirm
the used model is effective or not. e overall work-
flow of detecting the best model and the evaluation is
Regularization methodology for the movie
recommender system
e work of data handling in most of the data min-
ing model is important. To handle data efficiently,
there is one successful approach that is used widely
in almost applications – dataset splitting. In this ap-
proach, the goal is whatever any group of splitting
movie data is, the curve of the error function between
them must fluctuate in an acceptable range, which is
usually called appropriate fit.
In this study, Mean Reciprocal Rank (MRR) is used
as a statistical method evaluating the model. In gen-
eral, the Reciprocal Rank information retrieval mea-
sure calculates the reciprocal of the rank at which the
across queries, the MRR is calculated. e formula
of MRR is described as follows:
|Q|
More details, the data splitting approach consists of
three sets as follows:
1
1
MRR =
∑
|Q| i=1 ranki
+ Training set: the part of data is applied in the task of
building training set, it can be used to config some hy-
perparameters of the LSTM network such as the batch
size, learning rate, the l2 loss penalty rate,… for check-
ing regularization. In reality, one DL application has
to be passed more than hundreds of hyperparameter
configurations before publishing.
+ Validation set is usually used in model consider-
ation and providing the frequent evaluation of the
model in comparison to the training set.
Where ranki refers to the rank position of the first rel-
evant item in the ith query; Q is the number of items.
e model computes MRR score for both validation
and testing. en, the model is evaluated to be good
when MRR scores given on both testing and vali-
dation set is approximately same. Other evaluation
metrics used in this approach is Precision@k and Re-
on k highest ranking items, which are the reasonable
evaluation measures for emphasizing returning more
+ Testing set is also used in evaluation. Specifically,
unlike classification problem, evaluation in RS model relevant items earlier. e key point of this method is
SI4
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
to take all the precisions at k for each the sequence in model. In this study, an automatically testing pro-
the testing set. More details, the sequence of length n
is splitted into two parts: the sequence of length k for
comparison and the other sequence of length n – k put
into the predicting function, and then the sorted fac-
torization matrix scores are retrieved. If any item in
top k highest scores matches the one in the sequence
of length k, the number of hits is increased by 1. en,
the precision at k for one sequence of length n is given
by the number of hits divided by k, which stands for
the number of recommended items. For the recall, k
stands for the number of relevant items. In facts, k in
recall is usually smaller than the one in precision. Fi-
nally, the mean average precision and recall at k are
calculated for all sequences in the testing set. In gen-
eral, the formulas of the precision, recall and F1-score
at k are described as follows.
gram with some random hyperparameters is built and
takes three days consecutively to find the best hy-
perparameter. Some hyperparameters used in the
configuration are embedding dimension, number of
epochs, random state (shuffling number of interac-
tions), learning rate, batch size... e loss function is
kept same in the experiments.
Loss function
Several loss functions are applied to find the most ap-
propriate model, the formulas of them are listed in Ta-
Model efficiency evaluation
In this study, LSTM, RNN and another baseline
method are chosen to compare the evaluation met-
rics. e common baseline is Item-KNN, which con-
siders the similarity between the vectors of sessions.
is baseline method is one of the most popular item-
to-item solutions in practical systems. e MRR, Av-
erage Precision, Average Recall at 20 are measured to
find out the efficiency of the LSTM versus the others.
relevant_items in top k
Precision@k =
Recall@k =
k
relevant_items in top k
relevant_items
Precision@k×Recall@k
F1−score@k = 2× Precision@k+Recall@k
EXPERIMENTAL RESULTS AND
EVALUATION
Hyperparameter optimization
e experiment is taken by running 10 trials on the
randomly selected hyperparameters which are de-
fined in the fixed list as follows:
+ Learning rate: [0.001, 0.01, 0.1, 0.05]
+ l2: [1e-6, 1e-5, 0, 0.0001, 0.001]
+ Embedding dimension: [8, 32, 64, 128, 256]
+ Batch size: [8, 16, 32, 64, 128]
e loss function used in this experiment is BPR and
the number of epochs for each trail equals 10. e loss
e best result of the experiment is chosen for the
model. In facts, the model requires a big system for
training faster with more epochs, but the current one
is not enough for training longer. erefore, there
should be more time for training a complete model.
Figure 3: Overall workflow of detecting the best
model for the movie recommender system
LSTM model Optimization
Loss function
Hyperparameter optimization for LSTM
model.
is experiment compares the efficiency of some loss
functions mentioned in the previous section. e hy-
perparameter is chosen from the best one in the pre-
vious experiment. e results of the experiment on
the training set in four types of loss aꢀer 10 epochs
LSTM hyperparameter
ere is not a good methodology to choose an ideal
hyperparameter for the neural network up to now.
SI5
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
Table 1: Loss function formulas for the model
√
Pointwise
L = positive_loss+negative_loss
positive_loss = 1 - sigmoid(pos_pred)
negative_loss=sigmoid(neg_pred)
√
Hinge
L = max{0, (neg_pred − pos_pred) +1}
√
Adaptive Hinge
L = max{0, (neg_pred − hightest_pos_pred) +1}
√
Bayesian Personalized Ranking (BPR)
L = 1−sigmoid(pos_pred − neg_pred)
neg_pred: negative_prediction;
pos_pred: positive_prediction
Figure 4: Loss function performance on the model
loss can minimize the loss better than others can. Es-
pecially BPR, which can run the loss well as the be-
ginning and it looks more stable than Hinge in reg-
ularization, as the comparison in training and test-
the model instead of Hinge, Pointwise and Adaptive
Hinge.
Table 2: Sorted loss results for several
hyperparameters test
Batch
size
EmbeddinLearning L2
loss
dimen-
sion
rate
128
64
8
64
0.001
0.01
0.01
0.1
0.0001
0.0001
1e-6
1e-5
0.001
0
0.1962
0.2491
0.2537
0.2701
0.271
64
Evaluation results
8
e evaluation results between LSTM, RNN and the
According to the experiment results, both LSTM
and RNN can perform better than the baseline
method (Item-KNN). Moreover, LTSM performs well
in building a RS with specific relevant movies. LSTM
can forget what it thinks to be not necessary for the
long-term. erefore, the learning results of LSTM
are more updatable by time and frequency of interac-
tions. Overall, LSTM is a better model for building
the session-based RS.
16
16
16
16
32
16
8
256
32
0.05
0.01
0.001
0.05
0.1
128
64
0.276
1e-6
1e-5
0.001
0
0.281
32
0.2944
0.3566
0.4204
128
128
0.05
SI6
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
Figure 5: Good fit on training and testing by BPR loss function
Table 3: RNN on the testing set
DL Model
Precision
@20
Recall
@20
F1-Score@20
MRR
(test/validation)
LSTM
0.705
0.598
0.707
0.614
0.706
0.606
0.239/0.235
0.224/0.204
RNN (dropout
=0.2)
Item-KNN
0.506
0.507
0.506
0.201/0.206
the long-term computation. Adam optimizer plays a
great role in modifying the hyperparameter. More-
over, LSTM has been proved as the better model than
RNN during evaluation. Despite the results of both
are not good enough, but this study has presented
some solutions to improve the accuracy of the learn-
ing model.
DISCUSSION
In our approach, the modern model of recurrent neu-
ral networks, i.e., LSTM, is applied to do the movie RS
with the task of session-based recommendations. Be-
sides, the modification of LSTM in order to fit it better
is performed by using session-parallel mini-batches
and ranking losses. e evaluation results have shown
the outstanding improvement in comparison with the
popular baseline approach. e movie dataset pro-
vided by GroupLens is excellent for researching on
some principal features. us, this approach can be
applied not only for movie data, but also for some
other practical fields.
ACKNOWLEDGMENTS
is research is funded by Vietnam National Foun-
dation for Science and Technology Development
(NAFOSTED) under grant number: 06/2018/TN.
ABBREVIATIONS
RS: Recommender Systems
CONCLUSIONS
LSTM: Long Short-Term Memory
RNN: Recurrent Neural Networks
DL: Deep Learning
KNN: K-Nearest Neighbors
BPR-MF: Bayesian Personalized Ranking – Matrix
In conclusions, the LSTM-based movie RS has been
proposed and can achieve higher recommendation
performance when optimizing the hyperparameters
of LSTM, using loss function and optimization func-
tion. e loss is calculated to keep decreasing af-
ter each epoch and keep as minimum as possible for Factorization
SI7
Science & Technology Development Journal – Engineering and Technology, 3(S1):SI1-SI9
SGD: Stochastic Gradient Descent
MRR: Mean Reciprocal Rank
4. Vieira A. Predicting online user behaviour using deep learning
algorithms. arXiv:151106247v3. 2016;.
5. Devooght R, Bersini H. Collaborative Filtering with Recurrent
Neural Networks. arXiv:160807400. 2016;.
COMPETING INTERESTS
6. Hidasi B, Karatzoglou A, Baltrunas L, Tikk D. Session-based
Recommendations with Recurrent Neural Networks. 2015;.
7. GravesA. SupervisedSequenceLabellingwith RecurrentNeu-
ral Networks. Springer-Verlag Berlin Heidelberg. 2012;Avail-
8. Patterson J, Gibson A. Deep Learning-A Practitioner’s Ap-
proach. O’Reilly Media, Inc. 2017;.
9. Rendle S, Freudenthaler C, Gantner Z, Schmidt-Thieme L. BPR:
Bayesian personalized ranking from implicit feedback. Pro-
ceedings of the Twenty-Fifth Conference on Uncertainty in Ar-
tificial Intelligence, Montreal, Quebec, Canada,. 2009;p. 452–
461.
10. KingmaDP, Ba J. Adam: A Methodfor StochasticOptimization.
2015;.
11. Duchi J, Hazan E, Singer Y. Adaptive Subgradient Methods for
Online Learning and Stochastic Optimization. J Mach Learn
Res. 2011;12:2121–2159.
e authors hereby declare that there is no conflict of
interest in the publication of the article.
AUTHORS’ CONTRIBUTION
Duy Bao Tran is involved in proposing and imple-
menting solutions, and writing reports.
i anh Sang Nguyen has giving ideas and so-
lutions, assess experimental results and writing the
manuscript.
REFERENCES
1. Aggarwal CC. Recommender Systems. Springer International
Publishing. 2016;Available from: https://doi.org/10.1007/978-
2. Agrawal R, Srikant R. Fast Algorithms for Mining Association
Rules in Large Databases. Proceedings of the 20th Interna-
tional Conference on Very Large Data Bases. 1994;p. 487–499.
3. Nguyen TTS, Lu H, Tran TP, Lu J. Investigation of Sequen-
tial Pattern Mining Techniques for Web Recommendation.
International Journal of Information and Decision Sciences
12. Hinton G, Srivastava N, Swersky K. Lecture 6d- a separate,
adaptive learning rate for each connection. Slides of Lecture
Neural Networks for Machine Learning. 2012;.
13. Grouplens. 2019;Available from:
14. Liu L, Ozsu MT.
Encyclopedia of Database Systems.
Springer. 2009;Available from: https://doi.org/10.1007/978-0-
SI8
Tạp chí Phát triển Khoa học và Công nghệ – Engineering and Technology, 3(S1):SI1-SI9
Bài Nghiên cứu
Open Access Full Text Article
Đề xuất phim dựa trên bộ nhớ ngắn hạn
Trần Duy Bảo, Nguyễn Thị Thanh Sang*
TÓM TẮT
Hiện nay, các hệ thống đề xuất đã trở thành một công cụ cơ bản để giúp người dùng đưa ra quyết
định trong hàng triệu lựa chọn khác nhau - kỷ nguyên của Dữ liệu lớn. Nó mang lại lợi ích rất
lớn cho nhiều mô hình kinh doanh trên toàn thế giới do hiệu quả của chúng đối với khách hàng.
Rất nhiều mô hình và kỹ thuật khuyến nghị đã được đề xuất và có nhiều kết quả đáng kinh ngạc.
Phương pháp lọc cộng tác và phương pháp lọc dựa trên nội dung là phổ biến, nhưng cả hai đều
có một số nhược điểm. Một điều quan trọng là chúng chỉ tập trung vào sở thích tĩnh dài hạn của
một người dùng trong khi bỏ qua các mẫu giao dịch ngắn hạn, dẫn đến bỏ sót sự thay đổi sở thích
của người dùng trong suốt thời gian. Trong trường hợp này, mối quan tâm của người dùng ở một
thời điểm nhất định có thể dễ dàng che mờ bởi các hành vi quyết định trong lịch sử của người đó,
dẫn đến các khuyến nghị không đáng tin cậy. Để giải quyết vấn đề này, một phiên tương tác của
người dùng với các mục có thể được coi là một giải pháp. Trong nghiên cứu này, các mạng Bộ nhớ
ngắn hạn (LSTM) sẽ được phân tích để áp dụng cho các phiên của người dùng trong hệ thống đề
xuất. Bộ dữ liệu MovieLens được dùng trong nghiên cứu hệ thống tư vấn phim. Một số thí nghiệm
được thực hiện để đánh giá hệ thống đề xuất phim dựa trên LSTM.
Use your smartphone to scan this
QR code and download this article
Từ khoá: Học sâu, Bộ nhớ ngắn hạn, Hệ thống đề xuất, Khai thác chuỗi
Khoa Công nghệ ông tin, Trường Đại
học Quốc tế, ĐHQG-HCM, Việt Nam
Liên hệ
Nguyễn Thị Thanh Sang, Khoa Công nghệ
Thông tin, Trường Đại học Quốc tế,
ĐHQG-HCM, Việt Nam
Email: [email protected]u.vn
Lịch sử
• Ngày nhận: 10-8-2019
• Ngày chấp nhận: 22-8-2019
• Ngày đăng: 19-9-2019
DOI : 10.32508/stdjet.v3iSI1.540
Bản quyền
© ĐHQG Tp.HCM. Đây là bài báo công bố
mở được phát hành theo các điều khoản của
the Creative Commons Attribution 4.0
International license.
Trích dẫn bài báo này: Bảo T D, Sang N T T. Đề xuất phim dựa trên bộ nhớ ngắn hạn. Sci. Tech. Dev. J.
-Eng. Tech.; 3(S1):SI1-SI9.
SI9
9 trang
21960
Free
Bạn đang xem tài liệu "Long short-term memory based movie recommendation", để tải tài liệu gốc về máy hãy click vào nút Download ở trên
File đính kèm:
- long_short_term_memory_based_movie_recommendation.pdf
