{"id":20110,"name":"DeepMove","description":"Predicting Human Mobility with Attentional Recurrent Networks.","url":"https://github.com/vonfeng/DeepMove","last_synced_at":"2026-04-14T18:00:54.631Z","repository":{"id":47732465,"uuid":"137510067","full_name":"vonfeng/DeepMove","owner":"vonfeng","description":"[WWW 2018] DeepMove: Predicting Human Mobility with Attentional Recurrent Network","archived":false,"fork":false,"pushed_at":"2025-01-23T09:23:50.000Z","size":149574,"stargazers_count":155,"open_issues_count":6,"forks_count":55,"subscribers_count":2,"default_branch":"master","last_synced_at":"2026-03-26T10:42:38.656Z","etag":null,"topics":["attention","mobility-trajectory","prediction","www"],"latest_commit_sha":null,"homepage":"https://vonfeng.github.io/files/WWW2018_DeepMove.pdf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vonfeng.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-06-15T16:31:08.000Z","updated_at":"2025-12-28T04:54:20.000Z","dependencies_parsed_at":"2025-01-31T18:42:43.499Z","dependency_job_id":null,"html_url":"https://github.com/vonfeng/DeepMove","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vonfeng/DeepMove","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vonfeng","download_url":"https://codeload.github.com/vonfeng/DeepMove/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31419548,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T20:09:54.854Z","status":"ssl_error","status_checked_at":"2026-04-04T20:09:44.350Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"owner":{"login":"vonfeng","name":"Jie Feng","uuid":"11694233","kind":"user","description":"I am a researcher in urban science and spatio-temporal data mining.","email":"","website":"https://vonfeng.github.io/","location":"Beijing","twitter":null,"company":"Tsinghua University","icon_url":"https://avatars.githubusercontent.com/u/11694233?v=4","repositories_count":1,"last_synced_at":"2024-06-11T15:44:54.572Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/vonfeng","funding_links":[],"total_stars":136,"followers":82,"following":21,"created_at":"2024-06-11T15:44:55.795Z","updated_at":"2024-06-11T15:44:55.795Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vonfeng","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vonfeng/repositories"},"packages":[],"commits":{"id":1254114,"full_name":"vonfeng/DeepMove","default_branch":"master","total_commits":9,"total_committers":1,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":9.0,"dds":0.0,"past_year_total_commits":0,"past_year_total_committers":0,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":0.0,"past_year_dds":0.0,"last_synced_at":"2026-03-31T19:22:47.554Z","last_synced_commit":"6a969a430e177e87004ca39bea4adba93072bcad","created_at":"2023-03-27T10:58:32.559Z","updated_at":"2026-03-31T19:22:46.885Z","committers":[{"name":"Jie Feng","email":"fengj12ee@hotmail.com","login":"vonfeng","count":9}],"past_year_committers":[],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-14T00:00:07.982Z","repositories_count":6213305,"commits_count":903405131,"contributors_count":34927098,"owners_count":1144355,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"vonfeng/DeepMove","html_url":"https://github.com/vonfeng/DeepMove","last_synced_at":"2025-08-31T09:25:37.944Z","status":null,"issues_count":12,"pull_requests_count":1,"avg_time_to_close_issue":60930343.333333336,"avg_time_to_close_pull_request":null,"issues_closed_count":6,"pull_requests_closed_count":0,"pull_request_authors_count":1,"issue_authors_count":12,"avg_comments_per_issue":1.0833333333333333,"avg_comments_per_pull_request":0.0,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":2,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":957167.0,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":1,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":2,"past_year_avg_comments_per_issue":0.5,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2023-05-09T10:38:27.535Z","updated_at":"2025-08-31T09:25:37.945Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/vonfeng%2FDeepMove/issues","issue_labels_count":{"enhancement":1},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":12},"pull_request_author_associations_count":{"NONE":1},"issue_authors":{"DongZheng0030":1,"pshijie":1,"blldd":1,"1Priyanshu":1,"JerryLife":1,"ikaurrr":1,"Deepsea35":1,"hejl2416":1,"Einstone-edge":1,"jverygood":1,"zhfff4869":1,"vaibhav90":1},"pull_request_authors":{"gunarto90":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-04-14T00:00:07.923Z","repositories_count":14260526,"issues_count":34617559,"pull_requests_count":113192383,"authors_count":11234464,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"ForkEvent":2,"IssuesEvent":5,"WatchEvent":17,"IssueCommentEvent":2,"PushEvent":2},"last_year":{"WatchEvent":2}},"keywords":["attention","mobility-trajectory","prediction","www"],"dependencies":[],"score":5.081404364984463,"created_at":"2023-09-11T14:52:09.777Z","updated_at":"2026-04-14T18:00:54.634Z","avatar_url":"https://github.com/vonfeng.png","language":"Python","category":"Consumption","sub_category":"Mobility and Transportation","monthly_downloads":0,"total_dependent_repos":0,"total_dependent_packages":0,"readme":"# 💡Update\nWe are excited to announce [AgentMove](https://github.com/tsinghua-fib-lab/AgentMove), an LLM-based agentic framework designed for zero-shot mobility prediction. Leveraging the world knowledge and sequential modeling capabilities of LLMs, AgentMove paves the way for a promising new direction in mobility prediction.\n\n# DeepMove\nPyTorch implementation of WWW'18  paper-DeepMove: Predicting Human Mobility with Attentional Recurrent Networks [link](https://dl.acm.org/citation.cfm?id=3178876.3186058)\n\n# Datasets\nThe sample data to evaluate our model can be found in the data folder, which contains 800+ users and ready for directly used. The raw mobility data similar to ours used in the paper can be found in this public [link](https://sites.google.com/site/yangdingqi/home/foursquare-dataset).\n\n# Requirements\n- Python 2.7\n- [Pytorch](https://pytorch.org/previous-versions/) 0.20\n\ncPickle is used in the project to store the preprocessed data and parameters. While appearing some warnings, pytorch 0.3.0 can also be used.\n\n# Project Structure\n- /codes\n    - [main.py](https://github.com/vonfeng/DeepMove/blob/master/codes/main.py)\n    - [model.py](https://github.com/vonfeng/DeepMove/blob/master/codes/model.py) # define models\n    - [sparse_traces.py](https://github.com/vonfeng/DeepMove/blob/master/codes/sparse_traces.py) # foursquare data preprocessing \n    - [train.py](https://github.com/vonfeng/DeepMove/blob/master/codes/train.py) # define tools for train the model\n- /pretrain\n    - /simple\n        - [res.m](https://github.com/vonfeng/DeepMove/blob/master/pretrain/simple/res.m) # pretrained model file\n        - [res.json](https://github.com/vonfeng/DeepMove/blob/master/pretrain/simple/res.json) # detailed evaluation results\n        - [res.txt](https://github.com/vonfeng/DeepMove/blob/master/pretrain/simple/res.txt) # evaluation results\n    - /simple_long\n    - /attn_local_long\n    - /attn_avg_long_user\n- /data # preprocessed foursquare sample data (pickle file)\n- /docs # paper and presentation file\n- /resutls # the default save path when training the model\n\n# Usage\n1. Load a pretrained model:\n\u003e ```python\n\u003e python main.py --model_mode=attn_avg_long_user --pretrain=1\n\u003e ```\n\nThe codes contain four network model (simple, simple_long, attn_avg_long_user, attn_local_long) and a baseline model (Markov). The parameter settings for these model can refer to their [res.txt](https://github.com/vonfeng/DeepMove/blob/master/pretrain/simple/res.txt) file.\n\n|model_in_code | model_in_paper | top-1 accuracy (pre-trained)|\n:---: |:---:|:---:\n|markov | markov | 0.082|\n|simple | RNN-short | 0.096|\n|simple_long | RNN-long | 0.118|\n|attn_avg_long_user | Ours attn-1 | 0.133|\n|attn_local_long | Ours attn-2 | 0.145|\n\n2. Train a new model:\n\u003e ```python\n\u003e python main.py --model_mode=attn_avg_long_user --pretrain=0\n\u003e ```\n\nOther parameters (refer to [main.py](https://github.com/vonfeng/DeepMove/blob/master/codes/main.py)):\n- for training: \n    - learning_rate, lr_step, lr_decay, L2, clip, epoch_max, dropout_p\n- model definition: \n    - loc_emb_size, uid_emb_size, tim_emb_size, hidden_size, rnn_type, attn_type\n    - history_mode: avg, avg, whole\n\n# Citation\nIf you find this work helpful, please cite our paper.\n```latex\n@inproceedings{feng2018deepmove,\n  title={Deepmove: Predicting human mobility with attentional recurrent networks},\n  author={Feng, Jie and Li, Yong and Zhang, Chao and Sun, Funing and Meng, Fanchao and Guo, Ang and Jin, Depeng},\n  booktitle={Proceedings of the 2018 world wide web conference},\n  pages={1459--1468},\n  year={2018}\n}\n```\n","funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://ost.ecosyste.ms/api/v1/projects/20110","html_url":"https://ost.ecosyste.ms/projects/20110"}