Next point of interest (POI) recommendation

Point-of-interest (POI) recommendation is an imperative benefit to Location-Based Social Systems (LBSNs) that can advantage both users and businesses. POI recommendation can help public to discover new interesting locations. The user and location data are also easily available these days due to the...

Full description

Saved in:
Bibliographic Details
Main Author: Guvvala, Sanjusha
Other Authors: Zhang Jie
Format: Final Year Project
Language:English
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10356/76996
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-76996
record_format dspace
spelling sg-ntu-dr.10356-769962023-03-03T20:50:56Z Next point of interest (POI) recommendation Guvvala, Sanjusha Zhang Jie School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering Point-of-interest (POI) recommendation is an imperative benefit to Location-Based Social Systems (LBSNs) that can advantage both users and businesses. POI recommendation can help public to discover new interesting locations. The user and location data are also easily available these days due to the location-based social networks that enable users to share their check-in information through applications. POI recommendation is upcoming, and many research techniques have been suggested and investigated in this field over time. In this project, some existing next POI recommendation algorithms are explored and developed further on a public dataset obtained from open source applications. This project also involves the evaluation of some common recommender system techniques, applied to POI check-ins. From the evaluation, we get a few important discoveries in order to utilize POI recommendation models in different scenarios. Moreover, we observed the trends in Singapore data. It was discovered that many POIs present in the data have a combined infrastructure location space. This meant that those POIs shared the same address. Certainly, it was true to Singapore city due to its smaller land, many outlets are in the same infrastructure. Thus, we propose a method to group such POIs into combined spaces and carry out POI recommendation techniques on the combined POI data and compare the results accordingly as several new or interesting POIs in the same location point to be recommended for users can be a more meaningful way of recommendation. Bachelor of Engineering (Computer Science) 2019-04-29T14:24:17Z 2019-04-29T14:24:17Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/76996 en Nanyang Technological University 42 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Guvvala, Sanjusha
Next point of interest (POI) recommendation
description Point-of-interest (POI) recommendation is an imperative benefit to Location-Based Social Systems (LBSNs) that can advantage both users and businesses. POI recommendation can help public to discover new interesting locations. The user and location data are also easily available these days due to the location-based social networks that enable users to share their check-in information through applications. POI recommendation is upcoming, and many research techniques have been suggested and investigated in this field over time. In this project, some existing next POI recommendation algorithms are explored and developed further on a public dataset obtained from open source applications. This project also involves the evaluation of some common recommender system techniques, applied to POI check-ins. From the evaluation, we get a few important discoveries in order to utilize POI recommendation models in different scenarios. Moreover, we observed the trends in Singapore data. It was discovered that many POIs present in the data have a combined infrastructure location space. This meant that those POIs shared the same address. Certainly, it was true to Singapore city due to its smaller land, many outlets are in the same infrastructure. Thus, we propose a method to group such POIs into combined spaces and carry out POI recommendation techniques on the combined POI data and compare the results accordingly as several new or interesting POIs in the same location point to be recommended for users can be a more meaningful way of recommendation.
author2 Zhang Jie
author_facet Zhang Jie
Guvvala, Sanjusha
format Final Year Project
author Guvvala, Sanjusha
author_sort Guvvala, Sanjusha
title Next point of interest (POI) recommendation
title_short Next point of interest (POI) recommendation
title_full Next point of interest (POI) recommendation
title_fullStr Next point of interest (POI) recommendation
title_full_unstemmed Next point of interest (POI) recommendation
title_sort next point of interest (poi) recommendation
publishDate 2019
url http://hdl.handle.net/10356/76996
_version_ 1759858044271853568