Mobile Gift Recommendation Framework
A COREL Framework Approach
Ca
´
ıque de Paula Pereira
1
, Ruyther Parente da Costa
2
and Edna Dias Canedo
2
1
Faculty of Gama (FGA), University of Bras
´
ılia (UnB), Bras
´
ılia-DF,
´
Area Especial de Ind
´
ustria, Projec¸
˜
ao A – P.O. Box
8114 – CEP 72.444-240, Brazil
2
Department of Computer Science – Edif
´
ıcio CIC/EST – Campus Darcy Ribeiro, Asa Norte - University of Bras
´
ılia (UnB),
Keywords:
E-commerce, Recommendation Algorithms, Mobile Software Development, iOS, Giftr.
Abstract:
This paper proposes a recommendation algorithm for mobile devices based on the COREL framework. In this
context, the mobile application market and m-commerce sales have grown steadily, along with the growth of
studies and product recommendation solutions implemented in e-commerce systems. The proposed recom-
mendation algorithm is a customization of the COREL framework, based on the complexity of the implemen-
tation associated with iOS mobile applications. Therefore, this work aims to customize a gift recommendation
algorithm in the context of mobile devices using as main input the user preferences for the gifts recommen-
dation in the Giftr application. This algorithm has been tested through three cycles of tests and improved
during it, the results suggest that the algorithm presents a good performance and gifts results based on the user
preferences.
1 INTRODUCTION
In order to improve the user experience and increase
their sales, e-commerce companies use product rec-
ommendation algorithms according to the characteris-
tics of their consumers. There are many types of algo-
rithms, and despite the success of some of them, most
of them have problems. Therefore, it is important that
companies have a consistent and relevant algorithm to
recommend products to their costumers (Gama et al.,
2011).
In recent years, the online sales have seen an in-
tense growth in sales in Brazil and the rest of the
World. Festive dates of the year like Mother’s Day,
Valentine’s Day, Children’s Day, Christmas Day and
others are the time of year in which the demand
for this type of trade intensifies e-commerce(Mendes,
2016). This scenario has provided a business opportu-
nity for software applications that offer the consumer
the opportunity to gift someone on those festive dates
by cross-referencing user profile data to offer the best
related gifts.
Initially, one of the problems encountered in cre-
ating recommendation algorithms is that, the system
has not much user information. That hinders the
learning and performance of the algorithms. Thus,
mechanisms that reduce the learning time of the al-
gorithms and prediction based on the little available
information are necessary (Gama et al., 2011).
In the 90s, the e-commerce began when the first
sales websites were created. Initially, the volume
of transactions was very low. But the change in
the world market made it become the largest and
most voluminous way to market products (do Nasci-
mento et al., 2009). According to a survey released
by Buscap
´
e in 2015, billions of Brazilian reais are
collected on commemorative dates for e-commerce
sales. The revenue for Christmas in 2015 was 7.40
billion Brazilian reais through purchases made on the
Internet(de Souza, 2013).
Studies have been done in the area of e-commerce,
especially about algorithms of recommendations,
widely used in web systems. A good example of a
study that proposes an improvement of recommenda-
tion systems using techniques that aim to predict the
behavior of the user is the article Predicting Customer
Purchase Behavior in the E-Commerce Context, later
to use it as input for the recommendation of Products
itself (Qiu et al., 2015).
The Giftr application is the study object of an ini-
tiative in this context. This application was designed
and developed by Ruyther Costa, Ca
´
ıque Pereira,
Caio Sanchez and Victor Bruno, during the BEPiD
project in the period of February 2 and December 11,
de Paula Pereira, C., Parente da Costa, R. and Dias Canedo, E.
Mobile Gift Recommendation Framework.
DOI: 10.5220/0006792806570663
In Proceedings of the 20th International Conference on Enterprise Information Systems (ICEIS 2018), pages 657-663
ISBN: 978-989-758-298-1
Copyright
c
 2019 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved
657

2015.
Based on information of the user profile and per-
sonal preferences in the Giftr application, this re-
search seeks to recommend gifts that best suit the
user. The Buscap
´
e engine has been chosen because
of its popularity and available API in the context of
brazilian e-commerce, which will support the Giftr
application and the gift recommendation algorithm.
A common issue found in e-commerce stores and
sales applications is the creation of good products by
means of recommendation algorithms for their users.
These algorithms help both the user experience and
the increased sales of the companies.
This work proposes the following question due to
this difficulty:
Q1. How to create a gift recommendation algo-
rithm that fits the demand of a mobile App?
This work aims to contribute improving recom-
mendation algorithms answering this question. The
data collected through it can be used for future work
related to the algorithms of recommendations focused
on the e-commerce for gifts. This work general objec-
tive is to develop a gift suggestion algorithm that rec-
ommends the best products to the user based on their
profile.
Investigating possible gift recommendation solu-
tions that consider the user profile, substantiating the
adopted solution with other algorithms solutions are
the secondary objectives of this work.
1.1 Related Work
Some remarkable studies have been developed in the
field of e-commerce recommendation algorithms, and
this in particular proposes a framework that aims to
predict user behavior in the context of e-commerce
(Qiu et al., 2015). The big idea presented in this ar-
ticle is that it aims to predict consumer behavior, in
other words, the consumer’s preferences to buy some
product in an e-commerce system. The article points
out that through traditional algorithms there is no sat-
isfactory execution of predictive tasks, so the article
proposes a framework, COREL, a solution capable of
solving this very common challenge in the traditional
business context.
COREL, the framework proposed in this study is
consists of two stages. The first stage is making an
association between products by raising what is com-
mon among them and from these data to predict the
motivations that lead the consumer to buy a particular
product, and then build a list of products candidates
for purchase by this consumer. The second stage is
to predict the main characteristics that the consumer
will be interested in a particular type of product and
through these data define the products in which the
consumer will be interested, based on the list of can-
didate products generated at the end of the first stage.
2 DEVELOPMENT
The Giftr application was created in the BEPiD
(de Braslia, 2016) project with the idea of helping
people give gifts to each other. The solution found
by the team was to develop a social network where
each user registers their favorite products, tastes and
sizes (shoes, t-shirts, etc), and with this data the user
has the possibility to give another through the appli-
cation.
The functionality of the search application, both
user and product has a fundamental role in the ap-
plication, because through them users can find other
users and thus invite them to be your friends. The
search for products allows the user to find products
in general, based on the products available from the
API of the Lomadee (Lomadee, 2016b), enabling the
user to make the purchase of products and evaluate
the products, with a variation of zero to five points,
to show in the system how much the user wants to be
presented with that product.
The data control functionality of the profile allows
the user to change and add personal information of
the user, this being the means that the same has to
register their tastes, fundamental for the operation of
the algorithm of recommendation, and the measures,
the size of footwear used by him. The registration
of the tastes occurs through the entry by the user of
a string that represents a taste of yours, for example,
”iPhone”, and later inform which category of the Bus-
cap
´
e is associated with preference, for example ”cel-
lular and smartphone”.
2.1 Lomadee Platform
Buscap
´
e (Company, 2016) offers some very ro-
bust platforms, among which is Lomadee (Lomadee,
2016c), which provides several APIs for data access
available in the Buscap
´
e system. Lomadee offers sev-
eral APIs (Lomadee, 2016a), they are:
• Offers API: it allows to retrieve data of cate-
gories, products, offers and evaluations of users
and stores of Buscap
´
e;
• Coupon API: enables you to query for active
coupons on the Lomadee platform;
• Reporting API: Enables the retrieval of transac-
tion or commission data in detail.
ICEIS 2018 - 20th International Conference on Enterprise Information Systems
658

The API used in the Giftr application is that of the
Offers on the Lomadee platform, because through it
there is the possibility to retrieve data from categories,
products, offers and evaluations of Buscap
´
e users and
stores, which are fundamental to the Giftr application
and for the recommendation algorithm of gifts opera-
tion presented in this paper. This API provides several
types of query for data recovery and among them the
ones that are used are:
• Find Category List: returns detailed information
of existing product categories in Buscap
´
e and Lo-
madee;
• Top Products: returns the best products from Bus-
cap
´
e and Lomadee, processed and filtered by a ex-
clusive technology of the platform;
• Find Products List: lists with detailed product in-
formation on Buscap
´
e and Lomadee;
• View User Ratings: returns general user rating
data about a specific product;
• Top Offers: returns the most searched products in
Buscap
´
e/Lomadee;
• Find Offer List: returns a list of the sites that are
offering the product.
In addition to the outputs that each type of query
returns, it is necessary to have a well-structured input
so that the results are correct, the complete descrip-
tion of the inputs and outputs of each query available
on the website of the Lomadee platform (Lomadee,
2016b).
2.2 Gift Recommendation Algorithm on
Mobile Devices
The algorithm proposed in this article will be based in
another article, the Predicting Customer Purchase Be-
havior in the E-commerce Context (Qiu et al., 2015),
which will be customized to be accordance with mo-
bile applications.
The framework COREL was proposed for a e-
commerce context, which aims predict the customer
behavior and recommend products based on that pre-
diction. The context proposed for this algorithm is a
mobile application that it helps people give a present
to the other, recommending products based on the
user profile.
The figure 1 shows the flow from the proposed
algorithm with a hybrid approach (Section ??), little
similar to the one that COREL uses, and the subsec-
tions below detail each step.
Figure 1: Proposed Algorithm with a hybrid approach.
2.2.1 Categorize the Products Rated by the User
In the first step from COREL, the ”product currently
purchase by customer c
k
, d
i
”, which consists of veri-
fying the product d
i
bought by the purchased by the
consumer c
k
, given to the framework a base product
that will allow the probability calculations to be per-
formed later. This context, however, differs a lot of
the one that the proposed algorithm is, because the
main goal is to recommend gifts based on the user
profile through a mobile application, the Giftr.
Having this in mind, the proposed algorithm, in-
stead verify the product (d
i
) that the consumer (c
k
)
purchased, identify the product (p
i
) that the user rated
in the mobile application, with a range from zero to
five. The product rated (p
i
) is wrote in a user‘s pur-
chased products list (l
p
) for further use in the algo-
rithm.
The Lomadee API returns many product‘s at-
tributes, usual from all products listed in the platform.
Choose the right attributes to store is important and
determinant as an input to the proposed algorithm, so
the ones selected are: product name (p
n
), product cat-
egory (p
c
), minimum price (Qpmn), maximum price
(Qpmx), user average rating (Qs) and number of com-
ments (Qr).
2.2.2 Categorize the User‘s Preferences
In COREL, the user‘s preferences are predict iden-
tified, in other words, through the interactive steps
(1) Heat Model, (2) A hierarchical Bayesian Discrete
Choice Model and (3) Collaborative Filtering, shown
Mobile Gift Recommendation Framework
659

in the figure 1. The model seeks to predict the tastes
that the consumer will have for a given product from
data of products that the same has already acquired, of
product preferences data (number of comments, user
average rating, etc.) reported by the consumer that
is believed to be of greater relevance and consumers
who have similar tastes, to predict the preferences that
certain user of the system will have at the moment of
purchase of products.
The context of the previous paragraph is not the
same that Giftr has, after all the user will inform his
tastes based in products of different categories, as
smartphone, computer, among others. This prefer-
ences will be use to make this step of the recommen-
dation algorithm, which does not have any method to
predict the tastes of the user as COREL.
As presented in section 2.2.1, the user must in-
sert a string (p
s
) which represents the preferences of
the user and the category (p
c
) associated, based on
the categories from Buscap
´
e (Buscap
´
e, 2016). In this
way, this data will serve as input to the next step of
the recommendation algorithm, and for this motive it
will be saved.
2.2.3 Products Candidates List
In this step will be fulfilled the products listening (p
j
)
that it will be used for the calculations in the next step.
To list the candidates products is need to inform two
important data for the use of the Offers API of Lo-
madee, using the consult API called ”Find Product
List”, the keyword (p
s
) and the category (p
c
) of the
preference informed by the user in the mobile appli-
cation to the API returns the existent products in Bus-
cap
´
e associated with p
s
and p
c
.
In the Lomadee API, the data input is made
through a url and the products that are returned using
the API does not have a defined quantity, therefore it
is necessary define in a empirical way the quantity of
products that will be in the candidates products list,
given that the algorithm will run in a mobile applica-
tion with a limited hardware.
The Giftr user has the possibility to inform many
of his preferences and categories associated it, for this
reason, the scope to the products listing is limited a
one single category (p
c
= 1), nevertheless, having the
possibility of have one or more keywords associated
to this category (s ∈ Z|s > 1), for example, ”iPhone”
and ”Samsung Galaxy” as keywords and the category
being ”cellphone and smartphone”.
In the final of this step, there are ”n” candidates
products listed w.
2.2.4 Probability Calculation
This step consists, briefly, in the calculation of the
user (c
k
) to be interested by the product (p
j
), compar-
ing the characteristics Qpmn and Qpmx of this prod-
uct with the one rated product (p
i
), both in the same
category.
The probability calculation proposed in this arti-
cle differs a lot of the base article (Qiu et al., 2015),
because in it the calculation is accomplished using a
methodology shown in the figure 1 through the prob-
ability calculation of P(d
j
|c
k
). In the calculations of
the proposed algorithm in this article, it will not be
a specific equation for the probability calculation, in
this case it will be a sequence of steps that will define
the products with the highest probability that the user
will be interested.
To do so, this step will be subdivided into three
sub steps so that the products with the highest proba-
bility are listed, they are:
1. Make a price comparison between the favored
product and the candidate;
2. Filter the candidate products that deviate from
the minimum and maximum price of the favored
product;
3. Elaborate the rank of the candidate products based
on the minimum and maximum prices.
2.2.5 Make a Price Comparison between the
Favored Product and the Candidate
Product
The first step in this sub step is the search of the stored
data of the product favored by the user, output from
the step described in the section 2.2.2, because they
will be the basis for comparisons with the candidate
products, as well as to retrieve the data of all products
from the candidate product list (w), output of the sub
step described in the section 2.2.3.
The parameters that will be used are from the
product evaluated by the user: p
n
, Qpmn and Qpmx.
The first parameter will be necessary for the identi-
fication of the product, the second and third are the
parameters that best show the characteristic of this
product, among other parameters that the API returns
in the query and the parameters that will be used for
pc will be the same as pn.
Given the parameters to be used, the calculations
to be performed for the comparison of p
j
and p
i
are:
PQmn =
Qpmn(p
j
)
Qpmn(p
i
)
(1)
where,
ICEIS 2018 - 20th International Conference on Enterprise Information Systems
660

Qpmn(p
j
) is the minimum price of p
j
, Qpmn(p
i
)
is the minimum price of p
i
, PQmn the proportion of
Qpmn(p
j
) in relation to Qpmn(p
i
), and
PQmx =
Qpmx(p
j
)
Qpmx(p
i
)
(2)
where,
Qpmx(p
j
) is the maximum price of p
j
, Qpmx(p
i
)
is the maximum price of p
i
, PQmx the proportion of
Qpmx(p
j
) in relation to Qpmx(p
i
).
A separate calculation for the minimum (PQmn)
and maximum (PQmx) prices shall be performed,
where the calculations are intended to show how pro-
portionally the maximum and minimum price of p
j
in
relation to p
i
, and thereby identify the p
j
which most
closely resemble the prices of p
i
. This sub step is then
terminated and the generated data is saved for use in
the next substeps of the algorithm, in this way the list
of candidate products (w) is updated with the values
of the proportions calculated from equations 1 and 2.
2.2.6 Filter the Candidate Products that Diverge
of the Minimum and Maximum Price of
the Favored Product
This sub step has as input the updated list w, with the
values of the proportions of the minimum and maxi-
mum prices of the products p
j
. Thus, the objective of
this sub-step is to filter products that diverge from ”x”
percent of the base (minimum and maximum) prices
of p
i
and exclude those that exceed a threshold per-
centage value.
To calculate the proportional percentage that the
parameters Qpmx and Qpmn of p
j
have relative to
the same parameters of p
i
, it is necessary to perform
the following calculations:
PcQmx = PQmx × 100 (3)
PcQmn = PQmn × 100 (4)
The equations 3 and 4 indicate the proportional
percentage of the minimum and maximum price of p
j
in relation to p
i
. In order for filtering of products p
j
to occur, a threshold percentage value (p
l
) is required
both downward and upward of the base value, such
as, for example, ten percent up and down of the one
hundred percent of the minimum and maximum price
of p
i
, and the definition of the value of p
l
is made
empirically.
Then with the percentage values PcQmx and
PcQmn for each product, the classification of those
that comply with the percent limit p
l
is carried out. If
any product has PcQmx and PcQmn outside the per-
cent limit p
l
, it is excluded from the list of candidate
Table 1: Truth Table.
Qpmn Qpmx Qpmn
W
Qpmx Result
1
1 1
It is not excluded
1
0 1
It is not excluded
0
1 1
It is not excluded
0
0 0
It is excluded
products, if only one of the percentage values is not
in the limit p
l
the product Is not excluded from the w
list, as is the case that PcQmx and PcQmn are within
the limit, as shown in Table 1.
If there are many candidate products at the end
of this filtering, it may be necessary to define a limit
number so that there are no performance problems in
the algorithm, this number must be defined empiri-
cally.
2.2.7 Elaborate the Rank of the Candidate
Products based on the Minimum and
Maximum Prices
Based on the calculations of the previous sub step of
the price ratio Qpmn and Qpmx of p
j
with respect
to p
i
, the list w contains the p
j
all disordered. The
purpose of this sub step is to sort the list based on the
PcQpmn and PcQpmx data.
Pcm =
PcQmx + PcQmn
2
(5)
Since there are two distinct data, PcQmn and
PcQmx, in order to sort the list in a way that is more
optimized, the arithmetic mean of these two values
(Pcm) will be given so that only one value For the
comparison at the time of the descending ordering of
the products, as shown in the equation 5.
2.3 List of Recommended Products
The purpose of this step is to reorder the list w based
on the comparison of two more parameters of p
j
and
p
i
, Qs and Qr. The motivation of this reordering is to
give more credibility to the ordering of products in the
list, based on the data that Lomadee makes available
in its API.
The parameter Qr informs the amount of com-
ments that a product obtained in Buscap
´
e, and can
be used as a way to give credence to the value given
by Qs, that is, if a product has Qs equal to 9.0 and
another one has 9.0, what has a higher value of com-
ments (Qr) will have a greater relevance in relation to
the other.
Pd =
Qs
Qr
(6)
Mobile Gift Recommendation Framework
661

The parameter Pd then indicates the credibility to
the value of Qs, in case the closer to zero Pd is, the
greater the credibility of Qs, because Qr tends to be
a larger value. Then for the reordering will be used
Pd, plus the list w already found, so that the reorder-
ing is re-done without taking into account the one
performed by the step of the previous algorithm, the
value of pd will be added to Pcm:
Pw = pd + Pcm. (7)
Pw is the base value for descending reordering of
the w list, which takes into account Pcm of the first or-
dering of the third sub step described in Section 2.2.7.
At the end of this step, the w list has the products p
j
in the order of importance to be recommended to the
user.
3 ALGORITHM VALIDATION
AND VERIFICATION
The following results were found using the methodol-
ogy and steps defined, respectively, (de Paula Pereira
et al., 2017) and (da Costa et al., 2017).
The type of tests chosen to validate the algorithm
were gray and black box tests. Each test case has been
defined, refined, executed and documented. They
were executed on the iPhone 5 simulator of Xcode
using iOS 10.3. The Table 2 shows how the results
are represented by color in tables 3 to 5.
Table 3: Results representation.
The Table 3 shows the results from the first cy-
cle of tests. The first cycle contains tests of gray and
black type. The objective of the fist cycle was to test
different numbers of p
l
, interests, rated products with
the same or different categories. The values of p
l
that
were tested were 15, 20 and 25. And the quantities of
interests and rated products were none, 1, 3 or 10.
After the execution of the first cycle, 55% of the
test cases passed. Also, 40% did not pass or had no
results and 5% passed, but had a warning.
In TC-11, a bug was found when you add interests
with the same name more than one time and with dif-
ferent categories. In addition to this, in TC-16 there
was an error on SQLite on the first algorithm execu-
tion. Also, with this cycle, it was possible to observe
Table 4: First cycle of tests.
that when the categories are totally different, there are
no results.
Other bugs not related to the algorithm itself were
found and fixed after this first cycle of tests with the
bugs mentioned above. An important conclusion from
those test cases was that the number of results of the
recommendation for each test were lower than ex-
pected. Most of the results were only one recommen-
dation to the user.
The Table 4 shows the results from the second cy-
cle of tests. The second cycle contains tests of gray
and black type. The objective of the second cycle was
to test higher numbers of p
l
, increase the quantity of
interests and rated products with the same or different
categories. The values of p
l
that were tested were 20,
25 and 30. And the quantities of interests and rated
products were none, 1, 3, 10 or 30.
Table 5: Second cycle of tests.
After the execution of the second cycle, 76,92%
of the test cases passed. Also, 15,38% did not pass or
had no results and 7,7% passed, but had a warning.
In TC-21, for example, using a larger number of
rated products, interests and a higher p
l
, its possible
to see that the larger the p
l
is, the longer it takes to
run the algorithm overall. Another factor that could
be observed was that the results were almost the same
even with some different p
l
values.
Besides that, some test cases with different prod-
ICEIS 2018 - 20th International Conference on Enterprise Information Systems
662

uct categories still unsuccessful, but its a smaller
number of test cases than the cycle one due to a
change to the algorithm that was made after the first
cycle. Also, some general bugs from the App were
found and fixed during this phase.
The Table 5 shows the results from the third cy-
cle of tests. The third cycle contains tests of gray
type. The objective of the third cycle was to test a
higher quantity of ”n” candidates products listed (w).
The values of ”n” were 50, 100, 200 or 300. And the
quantities of interests and rated products were 1 or 2.
Table 6: Third cycle of tests.
To make the execution of these tests possible, it
was necessary to adapt the pagination of products re-
sults. However, those tests about the ”n” candidates
products listed (w) were still inconclusive, more tests
are necessary in the future to define.
After these tests, it was possible to define a value
of p
l
equal to 10. In this cycle, it was possible to ob-
serve again that most of the test cases with different
product categories had only one result. That is be-
cause the main keyword is from the rated product that
has no corresponding category with the interests. And
that is much more specific than the case that both have
the same categories. That will be improved in the fu-
ture.
Moreover, the recommendations quality is above
the average. And the time of the algorithm execution
was an acceptable period considering the standards
time of execution in other applications, the hardware
and the complexity of it.
4 CONCLUSIONS
This work allowed to present the results of the pre-
vious paper, (de Paula Pereira et al., 2017), pre-
sented the entire theoretical part of the algorithm im-
plemented in this paper and research review, which
investigated possible gift recommendation solutions
that take into account the user profile and among the
solutions found, the one that best matches the context
of this work is the COREL framework.
The COREL framework was customized to the
Gift application context, which required the recom-
mendation algorithm to run locally in the device and
recommend gifts based in the user preferences. The
proposed algorithm was tested through three cycles
of gray and black box to verify and validate if it was
working as expected and define some constants. A
large number of improvements were made during this
process and the results presented pointed goals were
accomplished, the algorithm presented a good recom-
mendation gifts and process performance.
REFERENCES
Buscap
´
e (2016). http://www.buscape.com.br. Accessed on:
November 26th 2016.
Company, B. (2016). http://developer.buscape.com.br/portal.
Accessed on: November 26th 2016.
da Costa, R. P., de Paula Pereira, C., and Canedo, E. D.
(2017). Algoritmo de recomendac¸
˜
ao de presentes em
dispositivos m
´
oveis. Universidade de Bras
´
ılia - Facul-
dade Gama. https://fga.unb.br/articles/0001/9506/tcc-
gifter-caique-2.pdf.
de Braslia, U. C. (2016). http://www.bepiducb.com.br/. Dis-
trito Federal DF, Brasil. Brazilian Education Pro-
gramm for iOS Development.
de Paula Pereira, C., da Costa, R. P., and Canedo, E. D.
(2017). Mobile Gift Recommendation Algorithm. 12th
Iberian Conference on Information Systems and Tech-
nologies (CISTI).
de Souza, A. E. R. (2013). Um modelo para recomendac¸
˜
ao
de cursos de especializac¸
˜
ao baseado no perfil profis-
sional do candidato. Dissertac¸
˜
ao (Mestrado) - Uni-
versidade Presbiteriana Mackenzie - So Paulo.
do Nascimento, A. R., da Ssilva, B. F., and dos Santos, G. G.
(2009). E-commerce: O Melhor Caminho no Mercado
Atual.
Gama, R., Andr
´
e, N., Pereira, C., Almeida, L., and Pinto,
P. (2011). Algoritmo de Recomendac¸
˜
ao Baseado em
Passeios Aleat
´
orios num Grafo Bipartido.
Lomadee (2016a). http://developer.buscape.com.br/portal/
lomadee/api-de-ofertas/introducao. Accessed on:
November 26th 2016.
Lomadee, O. A. (2016b).
http://developer.buscape.com.br/portal/lomadee/api-
de-ofertas/recursos. Accessed on: November 26th
2016.
Lomadee, P. (2016c). http://developer.buscape.com.br/portal
/lomadee. Accessed on: November 26th 2016.
Mendes, R. (2016). Os n
´
umeros do mercado de e-
commerce. Accessed on: November 26th 2016.
Qiu, J., Lin, Z., and Li, Y. (2015). Predicting customer pur-
chase behavior in the e-commerce context. Springer
Science.
Mobile Gift Recommendation Framework
663