Content uploaded by Tomislav Hlupic
Author content
All content in this area was uploaded by Tomislav Hlupic on Apr 12, 2022
Content may be subject to copyright.
IEEE BROADCAST TECHNOLOGY SOCIETY SECTION
Received March 1, 2022, accepted March 20, 2022, date of publication April 4, 2022, date of current version April 11, 2022.
Digital Object Identifier 10.1109/ACCESS.2022.3164409
A Novel Method for IPTV Customer Behavior
Analysis Using Time Series
TOMISLAV HLUPIĆ 1,2, DRAŽEN OREŠČANIN 1,2,
AND MIRTA BARANOVIĆ 2, (Member, IEEE)
1Poslovna Inteligencija d. o. o., 10000 Zagreb, Croatia
2Faculty of Electrical Engineering and Computing, University of Zagreb, 10000 Zagreb, Croatia
Corresponding author: Tomislav Hlupić (tomislav.hlupic@inteligencija.com)
This work was supported by the European Regional Development Fund under Grant KK.01.1.1.01.0009 (DATACROSS).
ABSTRACT Internet Protocol Television (IPTV) has had a significant impact on live TV content consump-
tion in the past decade, as improvements in the broadband speed have allowed more data volume to be
delivered. In addition to existing infrastructure, which is mostly based on the set top boxes, new content
providers have emerged, utilizing newly developed proprietary streaming platforms. As the number of IPTV
users grew, more volume and variety of data became available for analysis. By analyzing stored user actions,
it is possible to create a multivariate time series that represents user behavior over time. The approach
presented in the paper is based on multivariate time series generation from user data and determining the
similarity between them. Time series are created for each user based on the proposed quantified action sets,
grouped in the feature groups and summarized over time. The action sets and feature groups can be adjusted to
a certain IPTV platform. The end result of the analysis is the similarity score matrix, generated by calculating
the similarities of all users’ time series, where the similarity measure calculation can be chosen arbitrarily.
INDEX TERMS IPTV, time series analysis, data analysis, user behavior analysis, time series similarity, user
profiling.
I. INTRODUCTION
Time series of user-generated data are partially unpredictable
for several reasons. One of them is user behavior, which might
follow same patterns, but partly depends on various environ-
mental impacts. Next to it, the circumstances in which the
data are created are unknown, but still impact the behavior.
Therefore, a conclusion can be drawn that the entire users’
environment is dynamic. In the time series decomposition,
the unrepeatable dynamic falls into the residual data which
have a different impact on the time series analysis.
Time series analysis of the digital broadcasted content
includes analyzing the customer related data (e. g. the stored
actions of a certain user or a group of users), analysis of the
channels on which the content was shown, analysis of the
content level etc. The analysis’ is done, among other usages,
for content recommendation, personalization of the content
for a certain customer, and churn predictions.
This paper presents a novel method for Internet Protocol
Television (IPTV) user behavior analysis based on time series
pattern detection. Time series are created from the discretized
The associate editor coordinating the review of this manuscript and
approving it for publication was Dost Muhammad Khan .
user actions (e.g., channel change, content search etc.) and
their respective timestamps, forming an uninterrupted stream.
The analysis focuses on detecting similarities in time series
that can subsequently lead to the clustering of users with the
same detected behavior.
The motivation behind this method is based on the observa-
tion of different IPTV users’ behavior. While some users tend
to focus on a certain content or type of content, others show
a behavior called ‘‘channel zapping’’. Several approaches
have been taken to identify user behavior, some of which are
described in the Section II. Identification and quantification
of user behavior is the foundation for user clustering, based
on the calculated similarity of their behavior.
The user clusters later create the possibility of refining
recommendations provided by the recommendation engine.
Although some recommender systems have already been
established in this domain, they mostly focus on compar-
ing the users based on their watched content, rather than
their behavior. Using clusters based on user behavior, the
recommended content obtains a refined input of the con-
tent that users with similar behavior consume. This brings
the possibility of, for instance, providing recommenda-
tions of different content types depending on users’ activity
VOLUME 10, 2022 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ 37003
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
periods – which is significant for on-the-fly IPTV broadcast-
ing. Another possibility of using the clusters is to deploy a
different recommendation model for a single cluster. As the
recommender systems rely on these data, their overview is
included in related work.
While the proposed model exists as a standalone system,
its usage is devised as a supplement for existing recommender
systems. The model produces a similarity matrix of quantified
users’ behavior that acts as an input for the recommendation
model, but also as a basis for additional analysis.
The main contributions of this paper can be summarized as
follows:
•The digital broadcast content data are classified on a
high level
•The approach of using the time series in the IPTV data
analysis is considered and described
•A novel method for IPTV customer behavior analysis
using time series is proposed and demonstrated
The remainder of this paper is organized as follow-
ing: In Section II, an overview of prior related work in
the field is presented. The Section III covers the topic of
time series usage in the digitally broadcasted content anal-
ysis. It begins with an introduction to digital broadcast
content data classification, and in the rest of the section,
a novel method for IPTV customer behavior analysis using
time series similarities is presented. In the section IV,
the experimental work on the IPTV data set using pro-
posed method is evaluated. Finally, in the Section V, the
paper is concluded, along with a description of future
work.
II. RELATED WORK
The research in the field of IPTV systems varies from intro-
ducing different recommender system models, by analyzing
the user behavior up to analyzing the entire IPTV systems
based on the user-generated data.
Recommender systems are well-known and widely used
approaches for adjusting the content to the users’ preferences.
There are numerous models for generating recommendations
based on previous content consumption data, such as collab-
orative filtering [1] [2], that mostly have to tackle the cold-
start challenge [3]. Their implementation varies, depending
on the distribution platform. A different approach has to be
taken for digital terrestrial television models [4] compared to
the video-on-demand models [5]. Several other approaches
for IPTV recommendation model have been proposed, such
as using transformed-based fusion [6] and time-context aware
model based on Tensor learning [7]. Consumer feedback can
also be explicit [5], which relies on the user providing explicit
rating to the system.
Next to the collaborative filtering based recommender
systems, content-based recommender systems [8] are also
widely used. Content-based recommender systems typically
use profile information filtering to create recommendations.
In such systems, information from the consumer profile
(age, gender, education, interests) and its content ratings are
correlated with information about the content item itself and
its various attributes. If the item has attributes similar to
other items this consumer has rated highly, the system will
recommend it to the user.
Another approach for building recommender systems are
hybrid recommender systems, which combine both profile
and interaction information [4], [9]. Hybrid recommender
systems can have broader usage than recommending content,
such as broadband data recommendations.
In order to support the recommender system in terms of
adapting the system towards group-based recommendation,
rather than the user-based ones, it is necessary to model
the characteristics of the users, such as in [10]. The IPTV
user behavior is a challenge addressed in research for over
a decade, where the initial research [10], [11] was aimed
at creating marketing strategies and detecting user activity
peaks and channel zapping, which had an impact on the
IPTV service performance. Moreover, an important aspect,
especially for IPTV, is the channel popularity dynamics [13].
User feedback, mostly obtained as the implicit data based
on user actions, provides valuable insight and the possibility
of determining the user opinion of the broadcasted content
[14], [15]. In [15], a framework for assessing the implicit
feedback was proposed, based on tracking the change channel
events [14], [16]. Based on this framework, the same group
of authors built a model that utilizes implicit feedback and
content metadata to classify viewers’ opinions [17]. Another
interesting approach, based on the hybrid trust metric was
recently introduced in [18].
To some extent, [19] deals with streaming strategy classifi-
cation which affects the user experience of content consump-
tion. In the proposed framework, the authors classified the
content into:
•time-shifted streaming (TSS), where users can access
the content stored after it is created
•on-the-fly streaming (OFS), usually related to the
retransmission of live programs
In addition, the broader classification given in [20] con-
siders the type of services, which also includes the Video on
Demand (VoD). From the perspective of the user behavior, the
VoD platform follows different models with different inputs
and is not a part of this research. Another study [21] focused
on the IPTV platform, which had VoD and live TV content,
and concluded that VoD holds the user activity longer, while
live TV users tend to search for content by surfing through
the channels.
Recently, a new approach to user behavior detection was
addressed in [22] and [23]. In [22], the authors dealt with
the channel zapping behavior of IPTV users, a feature that
is present in the on-the-fly IPTV content broadcasting. The
authors have split the user behavior into the
•watching session (period between turning on the TV,
followed by active channel watching and turning off
the TV)
•channel zapping type (three types of channel switching
depending on the previous action)
37004 VOLUME 10, 2022
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
•interesting channel watching (channel being watched
longer than the threshold)
•transition between interesting channels (two or more
sequential sessions of interesting channel watching)
Although this analysis focuses on the granularity of a
channel, the zapping behavior is clearly detectable and useful
for recommending purposes. The collected data were used to
generate recommendations through six different recommen-
dation systems, each of them focused on one particular type of
information. Recommender scores are later combined using
fusion functions. Finally, the authors presented the channel
recommendation approach using an attention mechanism,
which is used to improve the recommendation accuracy. This
approach to observing an IPTV user behavior is similar to one
proposed in this paper, although based on a finer granularity
level of the user-related data.
Another approach to IPTV user behavior detection was
described in [23], in which the authors have proposed a multi-
item-sets fingerprinting to identify IPTV users. The proposed
fingerprinting method is based on identifying both frequent
individual activity items (FIA) and the frequent consecutive
item sequences. As the user accounts can be shared by multi-
ple actual users or even by unknown users, the authors dealt
with the accuracy of the user identification. It was suggested
that the statistical features of behavioral traces would be
a more accurate approach. Moreover, a new algorithm was
introduced to generate the feature vector, together with a new
similarity distance.
All proposed approaches are embedded in a MISFUB [23]
computing framework, which:
•uses the SURE algorithm [23] to construct the user
digital behavior fingerprints from the sequence of items
•introduces the similarity distance using the Jaccard dis-
tance and a variant of the Kullback-Liebler divergence
function
•introduces a fusion decision scheme to improve the per-
formance of the algorithm and the similarity distance
The effectiveness of the new framework was demonstrated
on a large IPTV subscriber dataset, with an average matching
precision of 93.8% on the 1000 user dataset. Similar to the
work presented in [22], the analyzed data granularity level
was the selected channel.
An insight into the similarity measures at a high level is
presented in [24] without any specific data context, presented
for univariate time series. By using similarity measures, it is
possible to classify the time series [25], which is a step toward
creating time series clusters. In [26], a review of deep learning
algorithms for time series classification was presented, which
is a novel approach for using deep neural networks for time
series classification. However, the multivariate time series
present a significantly higher complexity when determin-
ing the similarity owing to their high dimensionality. Most
approaches typically involve a variant of principal component
analysis (PCA) [27]–[29]. One of recent approaches to clus-
tering multivariate time series using common PCA was pre-
sented and evaluated in [28]. The aforementioned approach
is an extension of a previous study [29] and can be evaluated
for IPTV multivariate time series clustering. In [30], the
authors focused their research on the correlation between
simultaneous movement patterns of variables over time, with
the multivariate pattern being a union of all univariate ordinal
patterns. The recent work in [31] focused even more on the
multivariate time series, as they emphasized human activity
as a typical case with multiple observed dimensions. The
main focus of this study was to evaluate the multivariate
time series and state-of-the-art classifiers in a comprehensive
overview.
In addition to similarity metrics, pattern recognition is
another approach that can result in user behavior clustering
[32], [33]. Pattern matching can be achieved by the moving-
window approach, as described in [34], through template-
based or rule-based approaches [35], or a combination of
rule-based approaches and neural networks [36]. Time series
motifs can also be used to create time series clusters using dif-
ferent approaches to similarity measures. A novel approach,
which uses dynamic time warping (DTW) to measure the
similarity between time series, was recently proven to have
significant performance benefits over other methods, as pre-
sented in [37]. Dynamic time warping [38] is a well-known
method that has a wide application on time series, such as
finding patterns [39] and classification [40]. Pattern recogni-
tion in the scope of the IPTV user behavior analysis is planned
as the next step in the research.
III. THE METHOD FOR IPTV CUSTOMER BEHAVIOR
ANALYSIS USING TIME SERIES
A. CLASSIFICATION OF THE DIGITAL BROADCASTED
CONTENT DATA
For analytical purposes, it is of utmost importance to classify
the data according to their source, sort or usage. The IPTV
data originate from various sources: they can be sourced on
the provider’s side, on the content creator’s side or created
by the service users.
The data created on the provider’s side consist mostly of
automatically generated technical data that act as a support
for the broadcasted content. An example of technical data
are extended metadata, which are bound to a certain content.
Although usually smallest, volume-wise, their significance in
analytics is rather important, as they are usually related to the
data created on the user’s side. Thus, a unique footprint of
the link between user actions and the environment is gener-
ated, forming an insight into user behavior, thus forming the
basis for recommender systems. Examples of these data are
the current broadband speed, user package data (when they
exist) etc.
Data created on the content generator side combine
content-related metadata and the distribution-related meta-
data. Content-related metadata are rarely updated and are
mostly focused on content, such as the name, content length,
content type, genre etc., while content-specific data vary
according to distribution type.
VOLUME 10, 2022 37005
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
The highest volume data with the most variety are gen-
erated by the users, whose actions are stored as valuable
data, providing insight not only on the users but also on the
content. By combining the user action data with the content
metadata, the data can be segmented over certain features
or transformed into a time series. The time series enhance
the static data, providing the possibility of additional time-
variant data analysis. By creating time series from the features
over time, it is possible to detect certain patterns in the user
behavior or to predict how the users might react to content
introduction in a given time slot.
TABLE 1. Digital broadcasted content data features.
Moreover, when considering digitally broadcasted content,
it should be considered that content availability also has an
impact on user behavior. The user’s behavior is affected by
the preference for the content availability, which has impli-
cations for further user classification. In addition, each of the
content categories uses different prediction models in general,
as the impact of live broadcasted content on user behavior
and further recommendations has to have a different analytics
approach than on-demand content.
Time series are defined as the sequence of discrete data
in time and can be either univariate or multivariate. The
multivariate time series is a sequence of pairs
X=[(p1,t1),...,(pi,ti),...,(pn,tn)]
×(t1< . . . ti< . . . < tn)(1)
where each piis a data point in a d-dimensional space, and
each tiis the time stamp at which pioccurs [41].
In the context of classification, a time series is a list of
vectors over ddimensions and mobservations [31], denoted
as
X= hx1,...,xi,where x1,k,x2,k,...,xm,k(2)
We denote the jth observation of the ith case of dimension
kas scalar Xi,j,k.
Although time series analysis is mostly focused on future
data forecasting, they can provide valuable insight into the
data change over the time.
Time series used for digitally broadcasted content analysis
can also be univariate or multivariate. Feature selection for
the analysis is important for data granularity, as the data vary
significantly in that segment. The most volume, velocity and
variety-intense data with the greatest impact on the analysis
are user-generated through certain user actions. These data
must be tracked on the time granularity of a single sec-
ond. The automatically generated data mostly lay in coarser
granularity levels (sometimes on the daily level). Because
these data are interdependent, first the data on the coarser
granularity level must be multiplexed over the analyzed time
frame in order to match the data on the common granularity.
An example of the analysis is the correlation between the
user action, such as the content change or content search, and
the recommendation shown during the live broadcast. If the
recommended content is selected, the action is highly cor-
related with the previous recommendation. Another general
example of the analysis is the time difference between the
two content changes. The longer the difference, the higher the
chance of the user’s affinity towards a newly shown content.
The time series based on tracking the frequency of user
actions (such as the channel change, defined in the next
chapter) provides information on the users’ behavior models.
Users of similar behavior are later clustered, giving the con-
tent provider the possibility of generating various personally
adjusted recommendations or recommendation groups.
As this work deals with the time series as a basis for
user behavior detection, the other possible usages of the time
series in IPTV will be mentioned as a part of future research.
Forecasting, as the most common time series usage, will be
particularly emphasized in it.
B. THE PROPOSE D METHOD FOR IPTV CUSTOMER
BEHAVIOR ANALYSIS
In this chapter, the proposed novel IPTV data analysis method
is presented. The analysis method is based on developing the
time series analysis, which serves as the framework for the
similarity calculation. The algorithms for similarity, pattern
matching and clustering are not a subject of this model and
will be discussed in Section V.
The method is based on tracking user actions in a certain
time frame, from which the multivariate time series represent-
ing the footprint of the user behavior is generated. The user
actions, combined together, provide implicit feedback on the
user’s content interest that can be used for content recommen-
dation purposes [2], [15]. All user actions are performed in
the content consumption environment, which can be an STB,
a dedicated application, a browser page, or any other available
platform on which the content can be shown and consumed.
Definition 1: An action ais defined as a tuple consisting of
the description and the related quantifier a=(δ, θ ), where
the δrepresents the action description, and θrepresents the
action quantifier in the time series. Action set A holds all the
available actions a1,...,an.
An action is a time-independent event that can happen at
an arbitrary point in time.
The actions typically come in pairs hai,ajiwhich have
opposite quantifier values, thus creating opposite results
when performed. It should be noted that a single action can
only belong to one action set.
37006 VOLUME 10, 2022
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
A feature of the IPTV is a subset of the action set that holds
the actions that move a certain IPTV platform component to a
different state. Features are somehow dependent – some fea-
tures can be prerequisites for others to occur (e.g. a channel
change cannot be performed until the environment is turned
on). However, each feature can be independently analyzed.
A data point pin time series Xis a vector of a size d, where
ddenotes the number of observed dimensions [31]. A single
feature is represented as a dimension of the analyzed time
series.
Definition 2: An IPTV feature fis defined as a set of action
pairs, f=hai1,aj1i,...,hain,ajn i.
As the piis a vector, it can be represented as
p=hf1,q1i,...,hfd,qdi(3)
where each feature holds a certain quantifier value q.
Although it is mentioned in [30] that the features in the
multivariate time series might be simultaneously dimension-
dependent, it should be noted that in the proposed analysis
method the features in pare collectively independent (with
the exception of f1, as the environment needs to be turned on
before any other actions can be performed).
The actions, on which the method is based, are enumer-
ated as shown in Table 2. It should be emphasized that the
proposed action set is not the final action set and might be
adapted depending on the IPTV platform or the available
action set.
As the features are independent, their quantifiers can have
different values. This is due to the impact each feature has on
the analysis. For some features, it makes sense to decrease the
value and efficiently set the time series value to the previous
state. Features f1· · · f4are the example of this representa-
tion, where the feature consists of actions that usually are of
browsing type (except f1in the proposed feature set). Feature
f1represents the state of the user’s content consumption
environment (STB, application etc.).
On the other hand, the feature f5represents a differ-
ent action that, through direct search (channel selection
through the channel number, content search through the name
or other keyword etc.) sets the environment to the search
state followed by either another search, content consumption
or environment shutting down. Therefore, the consumption
environment is either in the search state or in the consumption
state, and feature f5represents those states.
An IPTV platform is a content delivery system that pro-
vides digitally broadcasted content over the Internet protocol
to users. In theory, the platform can provide the access to a
finite number of users n, which is limited by the hardware,
software and broadband constraints. Each user uirepresents
an independent subscriber to the IPTV platform who accesses
the content through a hardware client (STB) or a dedicated
application. Through user interaction with either a client or
an application, a log of the interaction data is generated. Inter-
action data can contain, for example, user action, previously
consumed channel, or a chosen consumed content.
TABLE 2. Action sets and Quantifier Values.
By joining the action result (e.g., chosen channel/content)
to the action, a valuable data on the user affinity are created.
Therefore, a single action ai, with the accompanying result
vector riand quantified state vector ωi, exists for user ui
at a certain moment of time t. The quantified state vector
ωiholds the sum of all quantifiers for each of the actions
that have occurred by the moment t. Together, they represent
a state of user uion the IPTV platform in a moment t,
defined as
Pi(t)=(ai,ri, ωi(t)),i=1,...,nwhere n
denotes the number of users of the IPTV platform (4)
VOLUME 10, 2022 37007
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
The beginning of the time series tsis set arbitrarily; it
can either the active user’s time using the platform or can
use the longer time frame where the platform inactive time
is quantified as 0. When they are used, the service state set
feature explicitly sets the active timeframe boundaries based
on the defined user actions. The end of the time series te,
either defined explicitly or implicitly, effectively ends the
observed period.
Even though the time series are theoretically unbounded,
in order to achieve the possibility of comparing different
users’ behavior, the starting timestamp and the ending times-
tamp of the compared period must be aligned. Usually, the
behavior is tracked on a daily level, so the typical boundaries
would be ts=00 :00 :00 and te=23 :59 :59. However, for
the prediction applications of the time series, the boundaries
[ts,te]may stretch over a longer time period.
Therefore, the dataset from which the time series is created
can be represented as:
P={Pi(t),i=1,...,n;t=ts,...,te}(5)
In each time stamp tof the time series, each Pihas to have
the current quantified state vector ωi(t) stored. The ωi(t) is
calculated as the sum of all the previous action quantifiers
that occurred by tfor a certain action aiand can be denoted
as
ωi(t)=[(a1, ϕ1),...,(an, ϕn)],a1· · · an∈A(6)
where ϕrepresents the quantified state for each action a. For
action a, at a moment of time t, the quantified state ϕholds
the sum of all quantifiers of occurrences of the given action.
Algorithm 1 Calculating the quantified state vector ωi(t)
1: Input: ai,A,t,ωi(t−1)
2: Output: ωi(t)
3: Function ωi(t)=value (a,A,t, ωi(t−1))
4: For each a∈A
5: If a=ai
6: Get index jof aiin ω(t)
7: Get ϕjfor ajfrom ω(t−1)
8: ϕj=ϕj+θj
9: End if
10: End for
In a single moment of time t, as the algorithm points out,
only one update of ωi(t)will occur.
The algorithm can be summed as following:
For each user, the quantified state vector ωichanges over
time. A single action per user might occur in a single moment
in time. If action aiis detected, the algorithm searches for the
action’s index jinside vector ωi, in order to update the state ϕj
related to the detected action. Only a single value is updated at
each moment, by adding the quantifier value to the previous
state for the detected action. The other values in the vector
are skipped.
A multivariate time series can be seen as a multiple uni-
variate time series in a d-dimensional space, in which a single
dimension corresponds to a certain feature f. The feature data
are generated from aggregated quantified state data of all the
action pairs hai1,aj1i,...,hain,ajn i, to which they belong.
A multivariate time series Xidenotes the time series repre-
senting the discretized behavior of user ui.
Algorithm 2 Building the multivariate time series Xifrom P
1: Input: P,A,ts,te,i
2: Output: Xi
3: Function Xi=MVTS(P,A,ts,te,i)
4: For each tbetween tsand te
5: For each fin p
6: Set q=0
7: If a∈f
8: Then extract ϕfor afrom ω(t)
9: q=q+ϕ
10: End If
11: End for
12: End for
The described algorithm generates a multivariate time
series Xiconsisting of ddimensions, where each dimension
represents a single tracked feature f. The time series is built
with the boundaries of tsand te. In each timestamp t, the
state Pi(t)is observed. For each feature, the state of adjoined
action pairs is summed to determine the value of the feature
in an observed timestamp t.
The set of all the time series for the nusers is denoted as
TS ={X1,X2,...,Xn}(7)
Using the common intervals proposed in [24], the simi-
larity score sbetween two time series is represented using
a value in the interval [0, 1], where 1 is the value that repre-
sents the maximum similarity of two time series. Each Xiis
compared to the members of the set TS \Xi, resulting in the
n−1 pairs of values si
jwhere jrepresents the time series of
user uj.
The final result of the analysis is the matrix of the simi-
larities between users, generally represented as a matrix of
similarity scores.
S=
1s1
2. . . s1
j. . . s1
n
s2
11. . . s2
j. . . s2
n
.
.
..
.
. . . . .
.
. . . . .
.
.
si
1si
2. . . 1. . . si
n
.
.
..
.
. . . . .
.
. . . . .
.
.
sm
1sm
2. . . sm
j. . . 1
(8)
IV. EXPERIMENT
In this chapter, the results of applying the algorithm to the
test dataset are presented and compared with similar previous
studies. The experiment is divided into two separate tasks.
The first is creating time series from the dataset for a single
user and a single feature. The second is building the similarity
matrices for the subset of users, as a basis for further user
37008 VOLUME 10, 2022
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
clustering based on their behavior footprint. Finally, the pro-
posed method is compared with different IPTV user behavior
analysis approaches.
The data provided are the testing data previously used for
building IPTV recommender systems for a small number of
users. All users are represented with their identifier in the
system, which is conveniently converted into appropriate tags
to further anonymize the data. The actions provided by the
data are limited, so only three features (f2,f3and f4) from the
proposed feature set could have been applied, as the service
state and search group data were omitted.
A. TIME SE RIES CREATION
Initially, the data are represented with tuples consisting of
four values: the user identifier, the channel identifier that
resulted from the action, the applied action identifier and the
timestamp. Out of these values, the channel data does not
have an impact on the algorithm, but holds valuable data that
can be used for additional analysis. Prior to the algorithm
application, the data had to be cleansed and prepared by
adjusting the data for time series analysis. This was done by
indexing the records by their timestamp and calculating the
quantified state vector ωi(t) in the given moment of time t,
as proposed in Algorithm 1.
The final result is a set of four time series for each user:
a time series, built as proposed in the Algorithm 2, represents
the multivariate time series Xi. Of these, three separate time
series, one representing each feature, are extracted as they
can provide focused insight for further analysis. The visual
representations of the time series for the three different users
are shown in the Figures 1, 2 and 3.
FIGURE 1. User u5with low activity.
These three users show a completely separate behavior
footprint: in the first figure (Figure 1), representing the activ-
ity of the user u5, it is visible that the user has some activity
in the morning with quick channel browsing inside a single
hour and some focused activity in the evening hours. Apart
from that, there is no activity throughout the day.
The second figure (Figure 2), representing the user u1,
shows the user with a high rate of channel zapping during the
entire day. This behavior indicates a low focus on the content
and high activity engagement, so this user can be a candidate
FIGURE 2. User u1with high activity.
FIGURE 3. User u6with focused activity.
for a separate recommender system that does not take content
into consideration.
In the third figure (Figure 3), a representation of moderate
activity during most of the day, with a focus on specific
content, is shown. This figure represents user u6, which is a
good candidate for recommender models built around content
recommendations.
B. SIMI LATIRY MATRIX CREATION AN D ANALYSIS
The second part of the experiment involve calculating the user
behavior similarity using dynamic time warping through its
implementation FastDTW [42]. As mentioned in the related
work, dynamic time warping is widely used in the time series
calculations. It is highly applicable in the case of comparing
the time series built with the proposed algorithm as it takes
time shifting into consideration. This is valuable as users
might have similar behavior in the different time slots, so the
dynamic time warping detects their similarity better than
algorithms such as Euclidian distance.
For the experiment purposes, different time series are cre-
ated for a random user sample. The similarity of the time
series is represented as a matrix of n×nsize, where nis the
number of compared users. In this experiment, six users are
compared, so the matrices are 6 ×6 in size. The interdepen-
dence of the values in the matrix is explained in the previous
section. Each matrix is the result of comparing the time series
of the same length using dynamic time warping.
After the calculations and initial matrix creation, the values
in a single matrix are normalized using min/max normaliza-
tion. The main reason for normalization is to represent the
VOLUME 10, 2022 37009
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
similarity as a value that is more suitable for analysis. The
final similarity values fall in the range between 0 and 1, where
1 represents identical user behavior and 0 represents the most
diverse user behavior in the matrix.
The first group of time series represents the user behavior
over a time span of eight days. In this group, a user behavior
is represented by three time series, each representing a certain
feature (f2,f3,f4). For each feature, a separate, independent
similarity matrix is created.
As is visible from the first matrix, user u1has a signifi-
cantly more divergent behavior than the rest of the analyzed
users. By taking into consideration a sample of the user
behavior shown in Figure 1, the result of the matrix related
to the feature f2is expected, as the user has a significantly
higher volume of actions and channel zappings than other
users. Even more disparate behavior is shown for feature f3,
as the user was using EPG browsing more than other analyzed
users. The last feature, f4, representing the EPG service start
and stop actions, shows less, but still significant disparity of
behavior.
FIGURE 4. Similarity matrix for f2for eight-day time span.
FIGURE 5. Similarity matrix for f3for eight-day time span.
FIGURE 6. Similarity matrix for f4for eight-day time span.
The second group of time series consists of user actions
during one weekend. As in the previous group, each feature
for a single user is represented as an independent similarity
matrix.
Compared to the results of the eight-day time span analysis
for the f2(Figure 4), the diversity between user u1and other
FIGURE 7. Similarity matrix for f2for a single weekend time span.
FIGURE 8. Similarity matrix for f3for a single weekend time span.
FIGURE 9. Similarity matrix for f4for a single weekend time span.
FIGURE 10. Similarity matrix for all features for eight-day time span.
FIGURE 11. Similarity matrix for all features for a single weekend time
span.
users is even greater. Simultaneously, the behaviors of users
u2,u3and u5are almost identical, whereas user u4shows
very close similarity. In addition, the difference in weekend
behavior of users u3and u6is significantly greater than that
during the eight-day time span (Figure 7).
By this comparison, it is clear that some users exhibit
different behaviors during the weekends. This, for instance,
provides the possibility of treating the recommendations dif-
ferently during weekdays and weekends for these users.
37010 VOLUME 10, 2022
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
Another valuable insight is the comparison of matrices for
features f3and f4. By having identical values in these matri-
ces, it can be concluded that users show almost no difference
in the behavior during the longer time span (Figures 5 and 6)
and weekends (Figures 8 and 9). In this case, it would be
opportune to omit the time series of the user with the greatest
behavior difference from the analysis so that the other users
can be analyzed closely.
The third group of similarity matrices has a different basis
than the previous two. For this group, the dynamic time
warping algorithm is applied to a multivariate time series with
all three features belonging to a single time series. Two time
series for each user are created: one holding the data of the
eight-day time span (Figure 10), and another holding the data
of a single weekend (Figure 11).
In the case of this user group, the similarity of these two
matrices with the ones representing the feature f2in the same
timespan shows that this feature has the most impact in the
multivariate analysis. Even so, having a separate analysis of
other features can be beneficial as they identify other behavior
characteristics – for example - users that use EPG more tend
to be more content oriented.
C. IPTV TIM E SERIES CLUSTERI NG
The next step in the analysis is the clustering of the created
time series, in order to detect users with similar behavior
on the larger scale. The dataset on which the clustering is
performed contains a week-long data of the users’ actions,
transformed into time series using the proposed algorithm.
The clustering is performed using self-organizing maps
(SOM) [43], a neural network that utilizes unsupervised
learning process to produce classes of patterns. With addition
to existing users and their respective time series, twelve more
users are added to the analysis, with their time series built
for f2, as shown on the Figure 12. The main reason for the
usage of only one feature is to reduce the dimensionality
to the most significant feature, that was previously proven
to be f2.
Although k-means is the usual choice for unsupervised
learning, SOM was proven in [44] to produce the same results
while outperforming k-means and having less variations in
results.
During preprocessing, the calculated time series are nor-
malized using min-max normalization. The normalized val-
ues are used as an input for the SOM, with the number of
clusters being manually set to four. It should be emphasized
that the initial number of clusters is set arbitrarily as a part of
the research, and the number itself depends on the nature of
the analysis.
As a result of first clustering and clusters visualization,
shown on the Figure 13, it can be concluded that the users
with similar weekly behavior are clustered together. Clus-
ter 1 shows that the users with moderate activity during the
working days and higher activity starting on Friday are sep-
arated from the users with only weekend activity (Cluster 3)
and users that are active in the middle of the week (Cluster 4).
FIGURE 12. The analyzed users and their respective time series.
FIGURE 13. Four determined clusters with their respective averages.
FIGURE 14. Cluster distribution for SOM with four clusters.
The highly active users, with one outlier, are grouped in the
Cluster 2. The distribution of the users’ time series is shown
on the Figures 14 and 15.
Typically, users that have a behavior pattern similar to the
one in the Cluster 4 are highly focused on a small number
of content activities that are the main reason for the content
consumption in the first place. In this cluster, it would be
recommendable to analyze the consumed content, e.g. sport
events, and tailor the recommendations accordingly. Unlike
this cluster, for the clusters 1 and 2 the similar approach
VOLUME 10, 2022 37011
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
FIGURE 15. Distribution of users’ time series in four clusters.
cannot be applied, as these users’ activity is less driven by
the content, and more by the consumption regardless of the
content.
Through observing the initial clustering, it is determined
that several time series should fit better in their own cluster
due to calculated similarity being closer to a certain cluster.
By raising a number of clusters to six, the time series show
more precise cluster fit.
The result of changing the number of clusters to six is
shown on Figures 16, 17 and 18.
FIGURE 16. Six determined clusters with their respective averages.
The difference is especially seen on clusters 2, 3 and
6 where the less active users are clustered together based on
the start of the higher weekly activity. Moreover, a user that
has a pattern of channel change through using channel back-
ward action is detached into its own cluster. The highly active
users with apparent channel zapping behavior are clustered
together in the cluster 5.
By having users clustered together as in the output of
this experiment, an opportunity exists for application of the
recommendation algorithm on a smaller number of users with
FIGURE 17. Cluster distribution for SOM with six clusters.
FIGURE 18. Distribution of users’ time series in four clusters.
a similar behavior. This can lead both to recommendations
that are more precise and execution performance gains, as
fewer comparisons are needed.
D. COMPARISON WITH OTHER APPROACHES
The proposed method differs significantly from the other
approaches that are oriented towards IPTV user behav-
ior. The most similar approach recently was done by [17],
where the authors focused on the implicit user feedback
through their actions (channel zapping etc.) but also on
the explicit actions – that the proposed method did not
take into consideration. The authors’ approach was focused
on building a model between explicit and implicit ratings
and using consumed content as another dimension in the
analysis.
The method proposed in this paper omits the explicit feed-
back and content as a dimension that is consumed in [17] and
focuses only on the detected behavior. This is done to provide
the basis for further user clustering based on their calculated
behavior and the approach presented in [17] could be applied
once the users are already clustered.
Another approach that was focused on a holistic analysis
of the IPTV user behavior was presented in the paper [12],
where the authors focused on detecting certain action patterns
in the system, such as channel zappings and uninterrupted
37012 VOLUME 10, 2022
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
content consuming sessions. This approach proved to be more
oriented towards the analysis of the entire system and all
users together, rather than on the individual user. Several
other papers also focus mostly on a certain pattern detection
in the system, without including other IPTV-related actions
(content time shifting and browsing, etc.) and quantifying
them towards the user behavior description.
E. APPLICATIONS IN IPTV SERVICES AND
RECOMMENDER SYSTEMS
The proposed method is mostly aimed at live TV systems,
where the users have the possibility of faster content
switching. The video-on-demand IPTV systems typically
have less user interaction with more focus on the con-
tent, so the time series would merely show the activity
periods. In the live TV systems, the users show much
more divergent behavior patterns, as more user actions are
available.
By introducing user behavior quantification and its rep-
resentation through time series, the users can be clustered
based on their behavior. The IPTV providers can benefit
from known user clusters as it provides an opportunity for
narrower detection of the cluster’s content and activity affil-
iation. An example would be the indication of clusters with
typical activity on Tuesday to Thursday evening with little
or no activity during other days. These clusters can then be
analyzed from the content perspective and can indicate the
users that consume sports content, such as continental club
football competitions. Moreover, this would omit the users
with potentially less interest in the same content from the
analysis, thus creating smaller data subsets that are analyzed.
By detecting information like this, the IPTV providers can
adjust the subscription packages to match the detected users’
affinities.
Further on, the impact on the recommender system comes
from the time series clustering. The currency recommender
systems rely on algorithms such as collaborative filtering
that require the processing of all the data in the system to
detect similarities in the consumed content. This approach
does not consider user behavior but relies solely on content
consumption. Through introducing user behavior quantifi-
cation, represented through the time series, the clusters of
users with similar quantified behavior are detected. There-
fore, the recommendation algorithm ran over a smaller cluster
of users already has some similarities detected, the detec-
tion of similar content is done faster and potentially more
accurately.
Recommendations in live IPTV have to be time-sensitive,
which is a dimension usually omitted in most of the recom-
mendation systems. The time series, created from the user
actions carrying the timestamp, provides the time data that
can narrow down the user activity periods. Having the defined
periods in which the user consumes the content, the recom-
mendation systems can recommend the live content that falls
in those time slots.
V. CONCLUSION AND FUTURE RESEARCH
In this paper, a method for the IPTV customer behavior deter-
mination and analysis is presented, based on the generation of
multivariate time series. The method is based on quantifiable
actions that are grouped in pairs and tracked as a feature of
the IPTV platform. Each multivariate time series represents
ad-dimensional footprint of user behavior within a certain
time frame. In each timestamp, the IPTV platform is set to
a certain state, presented through a dedicated algorithm, for
each user. Based on the state values for a certain trackable
action, a dimension metric that represents an IPTV platform
feature is calculated using the proposed time series genera-
tion algorithm. Finally, a similarity matrix is generated by
comparing the generated time series for all IPTV platform
users.
The method presented in this paper is the basis for generat-
ing user clusters with similar IPTV platform usage behavior.
By clustering these users, it is possible not only to deter-
mine their behavior similarity, but also to describe it further
through manual or automatic analysis. This can affect the
recommendation system in a certain way, as the recommen-
dations for the different user clusters might have distinc-
tive, more suitable models that can be further refined and
adjusted.
An approach comparable to the use of similarity measures
can be applied to detect patterns in user behavior. In this case,
the generated time series would not be compared to another
user’s time series; the pattern matching algorithms replace the
similarity calculation.
The goal of introducing an analysis approach based on
the actions is not to supplant the existing content-based
recommendation models. The content-based recommen-
dations and actions-based analysis should complement
each other, resulting in content-based and behavior-based
recommendations.
In addition to user clustering, the other possibility of using
the generated time series is user behavior forecasting. As time
series are typically used in forecasting, the recommendation
algorithms can be validated by checking whether the recom-
mended content falls into the timeline of the detected user
behavior. Therefore, the recommended content can be further
refined.
Future research will primarily focus on algorithm result
storage and graph analysis of the results. In addition, the
similarity metrics calculation will be tested with special
consideration of analysis dimensionality using the state-of-
the-art approaches. Next to the similarity metrics, various
approaches of pattern matching will be evaluated, in order
to create the basis for user clustering.
ACKNOWLEDGMENT
The authors would like to thank the Poslovna inteligencija,
especially Goran Gvozden, Ph.D. and Marko Štajcer, who
continuously gave their valuable advice, and also would like
VOLUME 10, 2022 37013
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
to thank the anonymous reviewers for their suggestions that
led to improvements of the paper.
DISCLOSURE
No potential conflict of interest was reported by the author(s).
REFERENCES
[1] D. Orescanin, T. Hlupic, and I. Soric, ‘‘Predictive models for digital broad-
casting recommendation engine,’’ in Proc. 41st Int. Conv. Inf. Commun.
Technol., Electron. Microelectron. (MIPRO), May 2018, pp. 1243–1248.
[2] S. Sidana, M. Trofimov, O. Horodnytskyi, C. Laclau, Y. Maximov, and
M.-R. Amini, ‘‘User preference and embedding learning with implicit
feedback for recommender systems,’’ Data Mining Knowl. Discovery,
vol. 35, no. 2, pp. 568–592, Mar. 2021.
[3] P. Cremonesi and R. Turrin, ‘‘Analysis of cold-start recommendations in
IPTV systems,’’ in Proc. 3rd ACM Conf. Recommender Syst. (RecSys),
2009, pp. 233–236.
[4] H. P. Tukuljac, D. Nad, G. Stupar, and M. Z. Bjelica, ‘‘A solution
of a DTV recommendation engine based on broadband and broadcast
data,’’ in Proc. 22nd Telecommun. Forum Telfor (TELFOR), Nov. 2014,
pp. 893–896.
[5] Y.-D. Seo, E. Lee, and Y.-G. Kim, ‘‘Video on demand recom-
mender system for internet protocol television service based on
explicit information fusion,’’ Expert Syst. Appl., vol. 143, Apr. 2020,
Art. no. 113045.
[6] H. Li, H. Lei, M. Yang, J. Zeng, D. Zhu, and S. Fu, ‘‘A transformer-
based fusion recommendation model for IPTV applications,’’ in
Proc. 3rd Int. Conf. Artif. Intell. Big Data (ICAIBD), May 2020,
pp. 177–182.
[7] X. Yin, Y. Chen, X. Mi, H. Wang, Z. Tang, C. He, and D. Fang, ‘‘Time
context-aware IPTV program recommendation based on tensor learning,’’
in Proc. IEEE Global Commun. Conf. (GLOBECOM), Dec. 2018, pp. 1–6.
[8] S. Song, H. Moustafa, and H. Afifi, ‘‘Advanced IPTV services person-
alization through context-aware content recommendation,’’ IEEE Trans.
Multimedia, vol. 14, no. 6, pp. 1528–1537, Dec. 2012.
[9] E. Amolochitis, I. T. Christou, and Z.-H. Tan, ‘‘Implementing a
commercial-strength parallel hybrid movie recommendation engine,’’
IEEE Intell. Syst., vol. 29, no. 2, pp. 92–96, Mar. 2014.
[10] T. Qiu, Z. Ge, S. Lee, J. Wang, J. Xu, and Q. Zhao, ‘‘Modeling user
activities in a large IPTV system,’’ in Proc. 9th ACM SIGCOMM Conf.
Internet Meas. Conf. (IMC), 2009, pp. 430–441.
[11] B. Xiao, J. Yan, X. Guo, and L. Leung, ‘‘IPTV: User behavior analysis,’’
in Proc. Int. Conf. Manage. Service Sci., Sep. 2009, pp. 1–4.
[12] G. Yu, T. Westholm, M. Kihl, I. Sedano, A. Aurelius, C. Lagerstedt, and
P. Odling, ‘‘Analysis and characterization of IPTV user behavior,’’
in Proc. IEEE Int. Symp. Broadband Multimedia Syst. Broadcast.,
May 2009.
[13] T. Qiu, Z. Ge, S. Lee, J. Wang, Q. Zhao, and J. Xu, ‘‘Modeling channel
popularity dynamics in a large IPTV system,’’ ACM SIGMETRICS Per-
form. Eval. Rev., vol. 37, no. 1, pp. 275–286, Jun. 2009.
[14] M. Kren, U. Sedlar, J. Bester, and A. Kos, ‘‘Determination of user opinion
based on IPTV data,’’ in Proc. 18th Int. Conf. Transparent Opt. Netw.
(ICTON), Jul. 2016, pp. 1–5.
[15] M. Kren, A. Kos, Y. Zhang, A. Kos, and U. Sedlar, ‘‘Publicinterest analysis
based on implicit feedback of IPTV users,’’ IEEE Trans. Ind. Informat.,
vol. 13, no. 4, pp. 2077–2086, Aug. 2017.
[16] M. Kren, A. Kos, and U. Sedlar, ‘‘Mining the IPTV channel change event
stream to discover insight and detect ads,’’ Math. Problems Eng., vol. 2016,
p. 5, Mar. 2016, Art. no. 2541814.
[17] M. Kren, A. Kos, and U. Sedlar, ‘‘Modeling opinion of IPTV viewers
based on implicit feedback and content metadata,’’ IEEE Access, vol. 7,
pp. 14455–14462, 2019.
[18] H. Wang, D. Chen, and J. Zhang, ‘‘Group recommendation based
on hybrid trust metric,’’ Automatika, vol. 61, no. 4, pp. 694–703,
Oct. 2020.
[19] M. Masciopinto, P. Comesaña, and and F. Pérez-González, ‘‘IPTV stream-
ing classification,’’ in IPTV Delivery Networks. Hoboken, NJ, USA: Wiley,
2018, pp. 25–63.
[20] A. Punchihewa and A. M. De Silva, ‘‘Tutorial on IPTV and its latest devel-
opments,’’ in Proc. 5th Int. Conf. Inf. Autom. Sustainability, Dec. 2010,
pp. 45–50.
[21] N. Liu, H. Cui, S.-H.-G. Chan, Z. Chen, and Y. Zhuang, ‘‘Dissecting user
behaviors for a simultaneous live and VoD IPTV system,’’ ACM Trans.
Multimedia Comput., Commun., Appl., vol. 10, no. 3, pp. 1–16, Apr. 2014.
[22] G. Li, L. Qiu, C. Yu, H. Cao, Y. Liu, and C. Yang, ‘‘IPTV channel zapping
recommendation with attention mechanism,’’ IEEE Trans. Multimedia,
vol. 23, pp. 538–549, 2021.
[23] C. Yang, L. Wang,H. Cao, Q. Yuan, and Y. Liu, ‘‘User behavior fingerprint-
ing with multi-item-sets and its application in IPTV viewer identification,’’
IEEE Trans. Inf. Forensics Security, vol. 16, pp. 2667–2682, 2021.
[24] C. Cassisi, P. Montalto, M. Aliotta, A. Cannata, and A. Pulvirenti, ‘‘Sim-
ilarity measures and dimensionality reduction techniques for time series
data mining,’’ in Advances in Data Mining Knowledge Discovery and
Applications. London, U.K.: IntechOpen, 2012.
[25] A. Abanda, U. Mori, and J. A. Lozano, ‘‘A review on distance based time
series classification,’’ in Data Mining Knowl. Discovery, vol. 33, no. 2,
pp. 378–412, 2019.
[26] H. I. Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P.-A. Müller, ‘‘Deep
learning for time series classification: A review,’’ Data Mining Knowl.
Discovery, vol. 33, no. 4, pp. 917–963, Mar. 2019.
[27] K. Yang and C. Shahabi, ‘‘A PCA-based similarity measure for multivariate
time series,’’ in Proc. 2nd ACM Int. Workshop Multimedia Databases
(MMDB), 2004, pp. 65–74.
[28] H. Li, ‘‘Multivariate time series clustering based on common principal
component analysis,’’ Neurocomputing, vol. 349, pp. 239–247, Jul. 2019.
[29] H. Li, ‘‘Accurate and efficient classification based on common princi-
pal components analysis for multivariate time series,’’ Neurocomputing,
vol. 171, pp. 744–753, Jan. 2016.
[30] M. Mohr, F. Wilhelm, M. Hartwig, R. Möller, and K. Keller, ‘‘New
approaches in ordinal pattern representations for multivariate time series,’’
in Proc. 33rd Int. Florida Artif. Intell. Res. Soc. Conf. (FLAIRS), 2020,
pp. 124–129.
[31] A. P. Ruiz, M. Flynn, J. Large, M. Middlehurst, and A. Bagnall, ‘‘The great
multivariate time series classification bake off: A review and experimental
evaluation of recent algorithmic advances,’’ Data Mining Knowl. Discov-
ery, vol. 35, no. 2, pp. 401–449, Mar. 2021.
[32] S. Spiegel, J. Gaebler, A. Lommatzsch, E. De Luca, and S. Albayrak,
‘‘Pattern recognition and classification for multivariate time series,’’ in
Proc. 5th Int. Workshop Knowl. Discovery Sensor Data (SensorKDD),
2011, pp. 34–42.
[33] J. Lin, S. Williamson, K. Borne, and D. DeBarr, ‘‘Pattern recognition
in time series,’’ in Advances in Machine Learning and Data Mining for
Astronomy. Boca Raton, FL, USA: CRC Press, 2012, pp. 617–645.
[34] A. Singhal and D. E. Seborg, ‘‘Pattern matching in multivariate time
series databases using a moving-window approach,’’ Ind. Eng. Chem. Res.,
vol. 41, no. 16, pp. 3822–3838, 2002.
[35] T.-C. Fu, F.-L. Chung, R. Luk, and C.-M. Ng, ‘‘Stock time series pattern
matching: Template-based vs. rule-based approaches,’’ Eng. Appl. Artif.
Intell., vol. 20, no. 3, pp. 347–364, Apr. 2007.
[36] A. Salekin, M. M. Rahman, and S. H. Chowdhury, ‘‘Pattern matching in
time series using combination of neural network and rule based approach,’’
in Proc. 7th Int. Conf. Electr. Comput. Eng., Dec. 2012, pp. 478–481.
[37] S. Alaee, R. Mercer, K. Kamgar, and E. Keogh, ‘‘Time series motifs dis-
covery under DTW allows more robust discovery of conserved structure,’’
in Data Mining and Knowledge Discovery, vol. 35, no. 3. New York, NY,
USA: Springer, 2021.
[38] P. Senin, ‘‘Dynamic time warping algorithm review,’’ Dept. Inf. Comput.
Sci., Univ. Hawaii Manoa, Honolulu, HI, USA, Tech. Rep., 2008,
pp. 1–23. [Online]. Available: https://csdl.ics.hawaii.edu/techreports/2008/
08-04/08-04.pdf
[39] D. J. Berndt and J. Clifford, ‘‘Using dynamic time warping to find patterns
in time series,’’ in Proc. Workshop Knowl. Discovery Databases, vol. 398,
1994, pp. 359–370.
[40] Y.-S. Jeong, M. K. Jeong, and O. A. Omitaomu, ‘‘Weighted dynamic time
warping for time series classification,’’ Pattern Recognit., vol. 44, no. 9,
pp. 2231–2240, Sep. 2011.
[41] H. Ding, G. Trajcevski, P. Scheuermann, X. Wang, and E. Keogh, ‘‘Query-
ing and mining of time series data,’’ Proc. VLDB Endowment, vol. 1, no. 2,
pp. 1542–1552, 2008.
[42] S. Salvador and P. Chan, ‘‘Toward accurate dynamic time warping in linear
time and space,’’ Intell. Data Anal., vol. 11, no. 5, pp. 561–580, 2007.
[43] T. Kohonen, ‘‘The self-organizing map,’’ Proc. IEEE, vol. 78, no. 9,
pp. 1464–1480, Sep. 1990.
[44] F. Bação, V. Lobo, and M. Painho, ‘‘Self-organizing maps as substitutes
for K-means clustering,’’ in Computational Science—ICCS 2005 (Lecture
Notes in Computer Science), vol. 3516, no. 3. Berlin, Germany: Springer,
2005, pp. 476–483.
37014 VOLUME 10, 2022
T. Hlupić et al.: Novel Method for IPTV Customer Behavior Analysis Using Time Series
TOMISLAV HLUPIĆ was born in Zagreb, Croatia,
in 1986. He received the B.S. degree in com-
puting and the M.S. degree in information and
communication technology from the Faculty of
Electrical Engineering and Computing, University
of Zagreb, in 2012 and 2015, respectively, where
he is currently pursuing the Ph.D. degree.
Since 2016, he has been a business intelligence
consultant in various roles on various international
and domestic projects. Since 2018, he has been a
Teaching Assistant and a Lecturer with Algebra University College, holding
courses in the business intelligence and data engineering domains. He is
the author of several papers presented at international conferences. His
research interests include business intelligence, data lakes, spatio-temporal
data streams, and time series applications in business environment.
DRAŽEN OREŠČANIN received the B.S. and
M.S. degrees from the Faculty of Electrical Engi-
neering and Computing, University of Zagreb,
where he is currently pursuing the Ph.D. degree.
Since 2001, he has been the Founder and the
CEO of Poslovna inteligencija, the leading busi-
ness intelligence and data warehousing vendor in
Adriatic Region. Besides that, he is the author and
coauthor of more than ten papers. He is also an
Active Member of TM forum alliance, contribut-
ing to the ABDR standard and data governance project. His research interests
include the fields of business intelligence, data warehousing, and big data
analytics.
MIRTA BARANOVIĆ (Member, IEEE) is cur-
rently a Full Professor in computer science with
the Faculty of Electrical Engineering and Comput-
ing, University of Zagreb. She worked as the Vice
Dean for students and education with the Faculty
of Electrical Engineering and Computing, Uni-
versity of Zagreb. Her research interests include
databases, information systems, data warehouses,
data lakes, and the semantic web. She is currently
a member of the Croatian Centre of Research
Excellence for Data Science.
VOLUME 10, 2022 37015
