Point-of-interest Recommendation for Location Promotion in Location-based Social Networks

1. Point-of-interest Recommendation for Location Promotion in Location-based
Social Networks
Abstract:
With the wide application of location-based social networks (LBSNs), point-of-interest (POI)
recommendation has become one of the major services in LBSNs. The behaviors of users in
LBSNs are mainly checking in POIs, and these checkingin behaviors are influenced by user’s
behavior habits and his/her friends. In social networks, social influence is often used to help
businesses to attract more users. Each target user has a different influence on different POI in
social networks. This paper selects the list of POIs with the greatest influence for recommending
users. Our goals are to satisfy the target user’s service need, and simultaneously to promote
businesses’ locations (POIs). This paper defines a POI recommendation problem for location
promotion. Additionally, we use submodular properties to solve the optimization problem. At
last, this paper conducted a comprehensive performance evaluation for our method using two
real LBSN datasets. Experimental results show that our proposed method achieves significantly
superior POI recommendations comparing with other state-of-the-art recommendation
approaches in terms of location promotion.
Existing System:
Recently, many researchers have been engaged in location-aware services. In LBSNs, users can
post comments on locations or activities, upload photos, and share check-in locations in which
users are interested with friends. These locations are called points-of-interest (POIs). Currently,
POI recommendation has become one of main location-aware services in LBSNs. POI
recommendation approaches mostly involve recommending users with some locations in which
users may be interested based on users’ characters, preferences, and behavioral habits.Through
the detailed analysis above, we observe traditionalPOI recommendations rarely focus on the
effect of socialrelationships for businesses location promotion through thePOI recommendation
process.
Disadvantages:
 No Concept for on the location promotion in LBSNs.
 Helps only for business people not for users.
Proposed System:

2. In view of POIs, POIs (e.g.restaurants, hotel, markets) haveto explore checking-in records to
attract more users to visit;more users (e.g., friends of users that checked in these POIs)will be
influenced to check in these locations. In this paper, weregard the influence on the business as a
maximization locationpromotion problem. The essential goals of recommendationsystem are to
satisfy users’ service demands and merchants’advertising needs.this paper proposes POI
recommendation method forpromoting POIs. Our proposed method is not only a tool
forbusinesses to use to promote their products and attract morecustomers to visit their stores, but
also recommends users withsome POI’s satisfying users preferences.
Advantages:
 We propose a novel point-of-interest recommendation problem, and its goal is to promote
the businesses’ locations ( POIs ).
 We define the user’s IS under special POI categories in an entire social network, and
model user mobility to describe the geographical influence between user.
Few Points:
In this paper, focus on POI recommendation to social user based on his friends and friends of
friends instead of unknown recommendation.
Main Application collects check in data with geo properties. Like user from his location move to
POI ,PG
u,v(l) tradeoff between geographical influence. And Target user to another user relation,
PT
u,v(l) semantic influence b/w u and v.
POI recommendation approaches mostly involve recommending users with some locations in
which users may be interested based on users’ characters, preferences. Like Facebook no suggest
you some business locations according to your interests.

3. Algorithm for POILP
Input: POI data P
Output: POIre (POI Recommendation)
Initialization:
i. Recommended POI categories RCre
ii. u is target user, v is a influences user .
let RCre ø
let POIuT = {a(1), a(2), · · · , a(K)}; where uT influence scope of social network
Compute POILP (POI recommendation problem for location promotion)
for each POIuT (1 to k)
Pu→v(l) = β × PG
u,v(l) + (1 − β) × PT
u,v(l),
Where -Pu→vThe user u influences user v (u ≠ v)
-β(∈ [0, 1]) avg 0.5
- PG
u,v(l) tradeoff between geographical influence
- PT
u,v(l) semantic influence b/w u and v.
RCreRCre∪ Pu→v(l);
Sort RCre;
Return RCre;

4. SYSTEM REQUIREMENTS
HARDWARE REQUIREMENTS:
Hardware : Pentium
Speed : 1.1 GHz
RAM : 1GB
Hard Disk : 20 GB
SOFTWARE REQUIREMENTS:
Operating System : Windows Family
Technology : Java and J2EE
Web Technologies : Html, JavaScript, CSS
Web Server : Apache Tomcat 7.0/8.0
Database : My SQL 5.5 or Higher
UML's : StarUml
Java Version : JDK 1.7 or 1.8
Implemented by
Development team : Cloud Technologies
Website : http://www.cloudstechnologies.in/
Contact : 8121953811, 040-65511811