Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Inferring Lifetime Status of Point-of-Interest

Inferring Lifetime Status of Point-of-Interest A Point-of-Interest (POI) refers to a specific location that people may find useful or interesting. In modern cities, a large number of POIs emerge, grow, stabilize for a period, then finally disappear. The stages (e.g., emerge and grow) in this process are called lifetime statuses of a POI. While a large body of research has been devoted to identifying and recommending POIs, there are few studies on inferring the lifetime status of POIs. Indeed, the predictive analytics of POI lifetime status can be valuable for various tasks, such as urban planning, business site selection, and real estate appraisal. In this article, we propose a multitask learning approach, named inferring POI lifetime status, to inferring the POI lifetime status with multifaceted data sources. Specifically, we first define three types of POI lifetime status, i.e., booming, decaying, and stable. Then, we formulate a serial classification problem to predict the sequential/successive lifetime statuses of POIs over time. Leveraging geographical data and human mobility data, we examine and integrate three aspects of features related to the prosperity of POIs, i.e., region popularity, region demands, and peer competitiveness. Next, as the booming/decaying POIs are relatively rare in our data, we perform stable class decomposition to alleviate the imbalance between stable POIs and booming/decaying POIs. Finally, we develop a POI lifetime status classifier by exploiting the multitask learning framework as well as the multiclass kernel-based vector machines. We perform extensive experiments using large-scale and real-world datasets of New York City. The experimental results validate the effectiveness of our approach to automatically inferring POI lifetime status. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Knowledge Discovery from Data (TKDD) Association for Computing Machinery

Inferring Lifetime Status of Point-of-Interest

Download PDF
27 pages

Loading next page...
 
/lp/association-for-computing-machinery/inferring-lifetime-status-of-point-of-interest-6wYT85U1Fj

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2020 ACM
ISSN
1556-4681
eISSN
1556-472X
DOI
10.1145/3369799
Publisher site
See Article on Publisher Site

Abstract

A Point-of-Interest (POI) refers to a specific location that people may find useful or interesting. In modern cities, a large number of POIs emerge, grow, stabilize for a period, then finally disappear. The stages (e.g., emerge and grow) in this process are called lifetime statuses of a POI. While a large body of research has been devoted to identifying and recommending POIs, there are few studies on inferring the lifetime status of POIs. Indeed, the predictive analytics of POI lifetime status can be valuable for various tasks, such as urban planning, business site selection, and real estate appraisal. In this article, we propose a multitask learning approach, named inferring POI lifetime status, to inferring the POI lifetime status with multifaceted data sources. Specifically, we first define three types of POI lifetime status, i.e., booming, decaying, and stable. Then, we formulate a serial classification problem to predict the sequential/successive lifetime statuses of POIs over time. Leveraging geographical data and human mobility data, we examine and integrate three aspects of features related to the prosperity of POIs, i.e., region popularity, region demands, and peer competitiveness. Next, as the booming/decaying POIs are relatively rare in our data, we perform stable class decomposition to alleviate the imbalance between stable POIs and booming/decaying POIs. Finally, we develop a POI lifetime status classifier by exploiting the multitask learning framework as well as the multiclass kernel-based vector machines. We perform extensive experiments using large-scale and real-world datasets of New York City. The experimental results validate the effectiveness of our approach to automatically inferring POI lifetime status.

Journal

ACM Transactions on Knowledge Discovery from Data (TKDD) – Association for Computing Machinery

Published: Jan 27, 2020

Keywords: Point-of-Interest

References

  • Modeling urban dynamics through GIS-based cellular automata
    Batty, Michael; Xie, Yichun; Sun, Zhanli
  • LIBSVM: A library for support vector machines
    Chang, Chih-Chung; Lin, Chih-Jen
  • Business Site Selection, Location Analysis, and GIS
    Church, Richard L.; Murray, Alan T.
  • On the algorithmic implementation of multiclass kernel-based vector machines
    Crammer, Koby; Singer, Yoram
  • Modeling urban growth with GIS based cellular automata and least squares SVM rules: a case study in Qingpu--Songjiang area of Shanghai, China
    Feng, Yongjiu; Liu, Yan; Batty, Michael
  • Real estate ranking via mixed land-use latent models
    Fu, Yanjie; Liu, Guannan; Papadimitriou, Spiros; Xiong, Hui; Ge, Yong; Zhu, Hengshu; Zhu, Chen
  • Exploiting geographic dependencies for real estate appraisal: A mutual perspective of ranking and clustering
    Fu, Yanjie; Xiong, Hui; Ge, Yong; Yao, Zijun; Zheng, Yu; Zhou, Zhi-Hua
  • Where businesses thrive: Predicting the impact of the olympic games on local retailers through location-based services data
    Georgiev, Petko Ivanov; Noulas, Anastasios; Mascolo, Cecilia
  • A comparison of methods for multiclass support vector machines
    Hsu, Chih-Wei; Lin, Chih-Jen
  • Modeling urban growth in Atlanta using logistic regression
    Hu, Zhiyong; Lo, C. P.
  • Network-based predictions of retail store commercial categories and optimal locations
    Jensen, Pablo
  • Multitask multiclass support vector machines
    Ji, You; Sun, Shiliang
  • Geo-spotting: Mining online location-based services for optimal retail store placement
    Karamshuk, Dmytro; Noulas, Anastasios; Scellato, Salvatore; Nicosia, Vincenzo; Mascolo, Cecilia
  • Generating diverse and representative image search results for landmarks
    Kennedy, Lyndon S.; Naaman, Mor
  • P-DBSCAN: A density based clustering algorithm for exploration and analysis of attractive areas using collections of geo-tagged photos
    Kisilevich, Slava; Mansmann, Florian; Keim, Daniel
  • Learning location naming from user check-in histories
    Lian, Defu; Xie, Xing
  • Restaurant survival analysis with heterogeneous information
    Lian, Jianxun; Zhang, Fuzheng; Xie, Xing; Sun, Guangzhong
  • Learning geographical preferences for point-of-interest recommendation
    Liu, Bin; Fu, Yanjie; Yao, Zijun; Xiong, Hui
  • Point-of-interest recommendation in location based social networks with topic and location awareness
    Liu, Bin; Xiong, Hui
  • A cocktail approach for travel package recommendation
    Liu, Qi; Chen, Enhong; Xiong, Hui; Ge, Yong; Li, Zhongmou; Wu, Xiang
  • Personalized point-of-interest recommendation by mining users’ preference transition
    Liu, Xin; Liu, Yong; Aberer, Karl; Miao, Chunyan
  • Unified point-of-interest recommendation with temporal interval assessment
    Liu, Yanchi; Liu, Chuanren; Liu, Bin; Qu, Meng; Xiong, Hui
  • Point-of-interest demand modeling with human mobility patterns
    Liu, Yanchi; Liu, Chuanren; Lu, Xinjiang; Teng, Mingfei; Zhu, Hengshu; Xiong, Hui
  • Characterizing the life cycle of point of interests using human mobility patterns
    Lu, Xinjiang; Yu, Zhiwen; Sun, Leilei; Liu, Chuanren; Xiong, Hui; Guan, Chu
  • Modelling urban growth
    Makse, Hernén A.; Havlin, Shlomo; Stanley, H. E.
  • Portfolio selection
    Markowitz, Harry
  • Probabilistic identification of visited point-of-interest for personalized automatic check-in
    Nishida, Kyosuke; Toda, Hiroyuki; Kurashima, Takeshi; Suhara, Yoshihiko
  • Link graph analysis for business site selection
    Quan, Xiaojun; Wenyin, Liu; Dou, Wenyu; Xiong, Hui; Ge, Yong
  • Support vector machines are universally consistent
    Steinwart, Ingo
  • A pure theory of local expenditures
    Tiebout, Charles M.
  • Understanding human movement semantics: A point of interest based approach
    Trestian, Ionut; Huguenin, Kévin; Su, Ling; Kuzmanovic, Aleksandar
  • Operational urban models state of the art
    Wegener, Michael
  • Local decomposition for rare class analysis
    Wu, Junjie; Xiong, Hui; Wu, Peng; Chen, Jian
  • Identifying points of interest using heterogeneous features
    Yang, Yiyang; Gong, Zhiguo; U., Leong Hou
  • Exploiting geographical influence for collaborative point-of-interest recommendation
    Ye, Mao; Yin, Peifeng; Lee, Wang-Chien; Lee, Dik-Lun
  • Predicting human activities using spatio-temporal structure of interest points
    Yu, Gang; Yuan, Junsong; Liu, Zicheng
  • Personalized travel package with multi-point-of-interest recommendation based on crowdsourced user footprints
    Yu, Zhiwen; Xu, Huang; Yang, Zhe; Guo, Bin
  • Where to find my next passenger
    Yuan, Jing; Zheng, Yu; Zhang, Liuhang; Xie, XIng; Sun, Guangzhong
  • Discovering urban functional zones using latent activity trajectories
    Yuan, Nicholas Jing; Zheng, Yu; Xie, Xing; Wang, Yingzi; Zheng, Kai; Xiong, Hui
  • Time-aware point-of-interest recommendation
    Yuan, Quan; Cong, Gao; Ma, Zongyang; Sun, Aixin; Thalmann, Nadia Magnenat
  • Graph-based point-of-interest recommendation with geographical and temporal influences
    Yuan, Quan; Cong, Gao; Sun, Aixin
  • U-Air: When urban air quality inference meets big data
    Zheng, Yu; Liu, Furui; Hsieh, Hsun-Ping
  • Diagnosing New York city’s noises with ubiquitous data
    Zheng, Yu; Liu, Tong; Wang, Yilun; Zhu, Yanmin; Liu, Yanchi; Chang, Eric
  • A collaborative learning framework to tag refinement for points of interest
    Zhou, Jingbo; Gou, Shan; Hu, Renjun; Zhang, Dongxiang; Xu, Jin; Jiang, Airong; Li, Ying; Xiong, Hui