IRJET - Venue Recommender for Events based on User Preferences

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 03 | Mar 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 2976
Venue Recommender for Events based on User Preferences
M. Maheshwari1, N. DevaDarshini2, S. Khanishkha3
1Professor, Department of CSE, Panimalar Engineering college, Tamil Nadu, India
2,3Student, Department of CSE, Panimalar Engineering college, Tamil Nadu, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract-Venue recommendation for hosting popular
Meet up events is a perfect example of a
recommendation problem where multiple entities
interact and influence each other. In this paper, we
present a deep learning based venue recommendation
system deep venue which provides context driven venue
recommendations for the Meet up event-hosts to host
their events. While recommending suitable events and
groups to Meet up users, we have taken into account the
users preference of visiting venues extensively,
Motivated by these endeavors, in this paper, we propose
a venue recommendation methodology for Meet up hosts
to organize popular events. The Recommended venue
should be suitable for all the members in a group.
Keywords-Deep Learning, Venue Recommender,
Collaborative Filtering, Group Recommendation.
1. INTRODUCTION
There is a tremendous growth of internet and its related
services each year. A huge amount of data is generated
by the users of internet (social networks, e-commerce
applications etc.). This data when analysed and studied
properly can provide huge benefits to the users as well
as the systems that provide services to these users .One
such system is the recommendation system which is an
integral part of almost all the applications we use today
such as Amazon, Facebook, Twitter etc.
Recommendation system which are used to recommend
venues are known as Venue Recommendation System.
Different approaches such as deep learning, neural
networks can be used for this system. One important
challenge in these systems is the large amount of data
that is generated. Moreover data sparsity is another
problem. All these setbacks should be considered and
overcome in these systems. It also involves multiple
entities such as venues, events, groups and individual
user. We propose a content and collaborative filtering
based approach. Collaborative filtering takes into
account the similarities among user, venue, event.
Content based filtering is used to overcome the data
sparsity problem. Recommendation of venues can be of
two types: single user, group. For a single user, the
recommendation is based on their interests which is
collected from the user. For group recommendation the
venue recommended is based on the location of all the
users i.e locations closer to all the users are displayed
from which the user selects the best one.
2. LITERATURE SURVEY
2.1. Event Based Social Networks
Newly emerged event-based online social services, such
as Meetup and Plancast, have experienced increased
popularity rapid growth. From these services, we
observed a new type of social network {event-based
social network (EBSN). An EBSN does not only contain
online social interactions as in other conventional online
social networks, but also includes valuable online social
interactions captured in online activities.
2.2 Recommendation based on Content
Recommender systems have the effect of guiding users
in a personalized way to interesting objects in a large
space of possible options. Content-based
recommendation systems try to recommend items
similar to those a given user has liked in the past. Indeed,
the basic process performed by a content-based
recommender consists in matching up the attributes of a
user profile in which preferences and interests are
stored, with the attributes of a content object (item), in
order to provide the user with new interesting items.
2.3 Combining Heterogenous Social and Geographical
Information for Event Recommendation
With the rapid growth of event-based social networks
(EBSNs) like Meetup, the demand for event
recommendation becomes increasingly urgent. In EBSNs,
event recommendation plays a central role in
recommending the most relevant events to users who
are likely to participate in. Different from traditional
recommendation problems, event recommendation
encounters three new types of information, i.e.,
heterogenous online+offline social relationships,
geographical features of events and implicit rating data
from users. Yet combining the three types of data for
offline event recommendation has not been considered.
2.4 Context-Aware Event Recommendation
The Web has grown into one of the most important
channels communicate social events nowadays.
However, the sheer volume of events available in event-
based social networks (EBSNs) often undermines the
users' ability to choose the events that matches their
interests. Recommender systems appear as a natural
solution for this problem, but different from classic
recommendation scenarios (e.g. movies, books), the

event recommendation problem is intrinsically cold-
start. Indeed, events published in EBSNs are typically
short-lived and, by definition, are always in the future,
having little or no trace of historical attendance. To
overcome this limitation, we propose to exploit several
contextual signals available from EBSNs.
2.5 Deep learning driven venue recommendation
Deep learning based venue recommendation system
DeepVenue which provides context driven venue
recommendations for the Meetup event-hosts to host
their events. The crux of the proposed model relies on
the notion of similarity between multiple Meetup entities
such as events, venues, groups etc. We develop deep
learning techniques to compute a compact descriptor for
each entity, such that two entities (say, venues) can be
compared numerically. Notably, to mitigate the scarcity
of venue related information in Meetup, we leverage on
the cross domain knowledge transfer from popular LBSN
service Yelp to extract rich venue related content. For
hosting an event, the proposed DeepVenue model
computes a success score for each candidate venue and
ranks those venues according to the scores and finally
recommend the top k venues.
3. PROPOSED SYSTEM
Our proposed system focuses on recommending venue
for a group of users or single user. In this system users
can add their past and future events successfully hosted
in their venue and also the users who attended the
events can also add the event details. By doing this we
can avoid data scarcity. While searching for a venue
based on event the end user has to select type of
recommendation i.e. whether it is a single or a group
recommendation.
For single user recommendation, the user can select
their preference which maybe the events the user wishes
to attend. Based on the preference various events in the
nearby venue will be recommended to the user.
In group recommendation end user can select list of
people going to participate in an event, location of all the
selected members will be collected and center point of
location gathered calculated and based on user
preference venue will be recommended. User can select
the venue and send place details to the group along with
the route map for the location .It will be displayed for all
the users in the group.
The various modules in our system are user
authentication, group creation, adding events and
viewing nearby events, single user recommendation,
group recommendation.
3.1 USER AUTHENTICATION
User has an initial level Registration Process. The users
provide their own personal information for this process
i.e. the user id and password are collected and stored
along with the mail id. The server in turn stores the
information in its database. The user can also create a
group of members. They can add people from their
contact list and invite them to attend the events. The
events can be anything such as a birthday party, blood
camp etc. After successful registration the user can login
using their own details.
3.2 ADD EVENTS AND VIEW NEARBY EVENTS
Proprietor can add the events hosted in their venues.
The venue and the type of event is also submitted by the
proprietor. The location of the venue is also stored in
database. The guests who attended the event can add the
event in database. User hosting events in their house can
also select and add event details in the system. Users can
see the list of events hosted within 2km radius from their
location. They can also search for the other events they
might be interested in. For more convenience 2km
distanced venues are shown automatically to the users.
3.3 SINGLE USER RECOMMENDATION
User can select their preference on which type of place
they wish to attend an event. All the nearby events which
suits the user preference will be displayed in Google
map. User can select and view the location and event
hosted in that venue based on the user preference.
Collaborative filtering is used to recommend venues to
the user based on the user’s interest and the past history
of events attended.
Initially the user logs in. If the user provides a correct set
of credentials the user is taken to their profile. After
which the user gives his preference. It can be the type of
events they would like to attend, the venues they like.
After that the user can give an event as input. The system
takes the input and recommends a suitable venue to the
user. Also the system notifies about the events that are
happening around the user within a 2km radius.
3.4 GROUP RECOMMENDATION
people going to participate in an event. Location of all the
selected members will be collected and center point of
location is calculated. Now the particular location is
displayed to the user. User can select the venue and send
place details to the group member’s .The route map for
the location will be displayed for all the users. Initially
the user logs in and creates a group of members they
need to invite. Then they determine the type of event.
The system gets the location of all the users. A center
point of all the locations is determined. The venues in

that area is suggested to the user. The user select the
venue and updates it in the group.
4. SYSTEM ARCHITECTURE
The working of the system is represented in the above
system architecture. The user performs an initial level
registration process by providing details like name,
email, password, mobile number. The details are stored
in a database. The user may add events to the system
which includes details like nature of the event, host
name, duration of the event, description, fees(if
needed).Users can also form a group when they are
about to attend similar type of events. Each group is
identified by a unique number. Each user enters his/her
own preference. They can be either the location in which
an event occurs or the type of event they want to attend.
Along with the user the preference of the each user as
well as that of the group is stored. Whenever a user logs
in he/she is authenticated. After that based there are two
possibilities. They are:
i. Single user
ii. Group of users
Single User Recommendation: Collaborative filtering is
used to find those events that might match the interest of
the user. Users can select their preference on which type
of place they wish to attend an event. All the nearby
events which suits the user preference will be displayed
in Google map to the user. User can select and view the
location and event hosted in that venue based on the
user preference the venues are recommended
Group Recommendation:
people going to participate in an event, location of all the
selected members will be collected. Then the center
point of all the locations in which the event might be
feasible is selected. Finally, the venue is selected by the
user. Then, the location is sent to all the users in a google
map.
5. CONCLUSION
The major contribution of this system is to propose a
model which takes user preferences as well as their
current locations to recommend venues for the events or
the events that they might be interested in.An event can
be completed successfully in the particular venue if
i. Similar events occurred in the venue in recent
times.
ii. The venue is similar to those venues where
similar types of events that have occurred.
In this model we make use of collaborative filtering
which takes into account the interest of user based on
his past history of events. We also use content based
filtering where we collect datasets of the venues which
are suitable for hosting the event but they are not
popularised yet. This type of event recommendations
uses the algorithm-Content based filtering. Where as
collaborative filtering is based on user preferences and
likeliness. Further, this system can be extended to
recommend movies and used in many other areas which
includes multiple factors similar to our system(here
factors are venue, event, user, group)i.e it can be used in
a multiple entity recommendation problem. For
recommending venues we can also consider multiple
factors other than location such as hobby, professional
details in order to make recommendations more precise.
6. REFERENCES
[1]A. Q. Macedo, L. B. Marinho, and R. L. Santos, “Context-
aware event recommendation in event-based social
networks,” in Proceedings of RecSys ’15. New York, NY,
USA: ACM, 2015, pp. 123–130.
[2] Z. Qiao, P. Zhang, Y. Cao, C. Zhou, L. Guo, and B. Fang,
“Combining heterogenous social and geographical
information for event recommendation,” in Proceedings
of AAAI Conference on Artificial Intelligence, July 27 -31.,
2014, pp. 145–151. [3] Q. Yuan, G. Cong, and C.-Y. Lin,
“COM: A Generative Model for Group Recommendation,”
in Proceedings of KDD ’14. New York, NY, USA: ACM,
2014, pp. 163–172.
[4] X. Liu, Q. He, Y. Tian, W.-C. Lee, J. McPherson, and J.
Han, “Event-based social networks: Linking the online
and offline social worlds,” in Proceedings of KDD ’12.
New York, NY, USA: ACM, 2012, pp. 1032–1040.
[5] S. Purushotham and C.-C. J. Kuo, “Personalized group
recommender systems for location- and event-based
social networks,”ACM Trans. Spatial Algorithms Syst.,
vol. 2, no. 4, pp. 16:1–16:29, Nov. 2016.
[6] P. Lops, M. De Gemmis, and G. Semeraro, “Content-
based recommender systems: State of the art and
trends,” in Recommender systems handbook. Springer,
2011, pp. 73–105.
[7] T.-A. N. Pham, X. Li, G. Cong, and Z. Zhang, “A general
recommendation model for heterogeneous networks,”
IEEE Transactions on Knowledge and Data Engineering,
vol. 28, no. 12, pp. 3140–3153, 2016.
[8] S. Scellato, A. Noulas, R. Lambiotte, and C. Mascolo,
“Socio-spatial properties of online location-based social
networks.” Proceedings of the ICWSM ’11, vol. 11, pp.
329–336, 2011.
[9] S. Gupta, S. Pathak, and B. Mitra, “Complementary
usage of tips and reviews for location recommendation
in yelp,” in Proceedings of PAKDD ’15. Springer, 2015,
pp. 720–731.

IRJET - Venue Recommender for Events based on User Preferences

More Related Content

What's hot

Similar to IRJET - Venue Recommender for Events based on User Preferences

More from IRJET Journal

Recently uploaded

IRJET - Venue Recommender for Events based on User Preferences