Point-of-Interest Recommender Systems by HosseinAli Rahmani Dashti - - PowerPoint PPT Presentation

▶

Jan 13, 2023 183 likes •502 views

Point-of-Interest Recommender Systems by HosseinAli Rahmani Dashti Supervisors: Dr. Mitra Baratchi Advisor: Dr. Sajad Ahmadian Dr. Mohsen Afsharchi Outline Data Social Networks Location-Based Social Networks Information

SLIDE 1

Point-of-Interest Recommender Systems

by HosseinAli Rahmani Dashti Supervisors:

Dr. Mitra Baratchi
Dr. Mohsen Afsharchi

Advisor:

Dr. Sajad Ahmadian

SLIDE 2

Outline

 Data  Social Networks  Location-Based Social Networks  Information Overload Problem  Recommender Systems  Point-of-Interest Recommender Systems  Challenges  References

2/29

SLIDE 3

Data

3/29

SLIDE 4

Social Networks

 Social Networks impact on Data Generation

4/29

SLIDE 5

Location-Based Social Networks

5/29

SLIDE 6

Information Overload Problem

 Which items are better for costumer?  Effective decision making

6/29

SLIDE 7

Recommender Systems

Recommender System User Feedbacks User or Object Profiles Context Information

ratings, check-ins, buys, like attributes location, time, friends, category, content,

Recommended List

7/29

SLIDE 8

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

8/29

SLIDE 9

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

SLIDE 10

Content Based

Checked-in by User Recommended to User Similar Location User’s Profile

10/29

SLIDE 11

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

11/29

SLIDE 12

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

12/29

SLIDE 13

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

13/29

SLIDE 14

User-Based Collaborative Filtering

High Similarity

User 1 User 2 User 3 Location 1 Location 2 Location 3 Location 4

14/29

SLIDE 15

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

15/29

SLIDE 16

Item-Based Collaborative Filtering

High Correlation

User 1 User 2 User 3 Location 1 Location 2 Location 3 Location 4

16/29

SLIDE 17

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

17/29

SLIDE 18

Matrix Factorization

𝑉𝑡𝑓𝑠𝑡 (𝑛) 𝑀𝑝𝑑𝑏𝑢𝑗𝑝𝑜 (𝑜)

≈ ×

𝑛 𝑜 𝑙 𝑙

 Latent Features (𝑙)

18/29

SLIDE 19

Recommendation Methods

Recommender System Content Based Collaborative Filtering Hybrid Model Memory Based Model Based User-Based Item-Based

19/29

SLIDE 20

Hybrid Model

20/29

SLIDE 21

Check-ins

21/29

 Check-in becomes a Life Style

SLIDE 22

Point-of-Interest Recommendation

22/29

SLIDE 23

Challenges

23/29

 Data Sparsity

Low percentage of rated (checked-in) items (locations)
Foursquare: 50 million user, 105 million venues, 12 billion check-ins

 Scalability

The number of users and items

 Cold-Start

New user or item
Little information

SLIDE 24

Challenges (Cont.)

 User Feedback

Explicit Feedback Data
Rating or like and dislike
Implicit Feedback Data
User visited or bought object

24/29

SLIDE 25

Check-in Information

25/29

Location Time Comments Friends

SLIDE 26

Contextual Information

26/29

Social Information Geographical Information Temporal Information Categorical Information Content Information Periodic Continues Power-Law Distribution Multi-Center Gaussian Model Category Tree Tags Photos Comments Time Slot Contextual Information in POI recommendation

SLIDE 27

Contextual Information in Related Works

27/29

Table 1. Summary of contextual information in related works

SLIDE 28

References

1. Y. Zheng, "Trajectory Data Mining: An Overview," ACM Transactions on Intelligent Systems

and Technology (TIST), vol. 6, no. 3, p. 29, 2015.

2. J. D. Mazimpaka and S. Timpf, "Trajectory Data Mining: A Review of Methods and

Applications," Journal of Spatial Information Science, no. 13, pp. 61-99, 2016.

3. J. Bao, Y. Zheng, D. Wilkie and . M. Mokbel, "Recommendations in Location-Based Social

Networks: A Survey," GeoInformatica, vol. 19, no. 3, pp. 525-565, 2015.

4. Z. Ding, X. Li, C. Jiang and M. Zhou, "Objectives and State-of-the-Art of Location-Based

Social Network Recommender Systems," ACM Computing Surveys (CSUR), vol. 51, no. 1, p. 18, 2018.

5. Y. Yu and X. Chen, A Survey of Point-of-Interest Recommendation in Location-Based Social

Networks, Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.

6. J.-B. Griesner, T. Abdessalem and H. Naacke, "POI Recommendation: Towards Fused Matrix

Factorization with Geographical and Temporal Influences," in Proceedings of the 9th ACM Conference on Recommender Systems, 2015.

SLIDE 29

References

7. S. Zhao, I. King and M. R. Lyu, "A Survey of Point-of-Interest Recommendation in Location-

Based Social Networks," arXiv preprint arXiv:1607.00647, 2016.

8. X. Li, G. Cong, X. Li, T.-A. Nguyen Pham and S. Krishnaswamy, "Rank-GeoFM: A Ranking

based Geographical Factorization Method for Point of Interest Recommendation," in Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, Santiago, 2015.

9. C. Cheng, H. Yang, I. King and M. R. Lyu, "A Unified Point-of-Interest Recommendation

Framework in Location-Based Social Networks," ACM Transactions on Intelligent Systems and Technology (TIST, vol. 8, no. 1, p. 10, 2016. 10.Y. Liu, T.-A. N. Pham, G. Cong and Q. Yuan, "An Experimental Evaluation of Point-of-Interest Recommendation in Location-Based Social Networks," VLDB, vol. 10, no. 10, pp. 1010-1021, 2017.

SLIDE 30

Thanks!

Questions or Comments?