[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118321-en":3,"doc-seo-118321-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118321,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Anomaly Detection for Shared Mobility - Master Thesis","Shared mobility systems such as bike-sharing networks have expanded rapidly in urban transportation due to environmental and economic benefits. Identifying anomalies is essential to improve operational efficiency, user satisfaction, and system resilience. Existing anomaly detection methods often prioritize user behavior or system-level metrics, but commonly suffer from limited interpretability and the inability to leverage fast, unsupervised learning when labeled data is scarce. This thesis proposes an unsupervised framework integrating bike-sharing, weather, and mass transit data, using Isolation Forest and DIFFI-based feature importance to pinpoint atypical spatiotemporal usage patterns and relate them to external factors.","Master Thesis in Computer Engineering  \nAnomaly Detection for Shared Mobility  \nMaster Candidate Supervisor  \nElnur Isgandarov Prof. Gian Antonio Susto  \nStudent ID 2014431 University of Padova  \nCo-supervisor  \nProf. Federico Chiariotti University of Padova  \nAcademic Year  \nTo my parents and friends  \nAbstract  \nShared mobility systems, such as bike-sharing networks, have gained significant traction in urban transportation due to their environmental and economic benefits. Understanding anomalies within these systems is critical for improving operational efficiency, user satisfaction, and system resilience. Current state-ofthe-art approaches to anomaly detection in shared mobility often focus on user behavior or system-level metrics. However, these methods frequently lack interpretability and fail to address the need for fast, unsupervised techniques, as labeled data is typically unavailable in this domain.  \nThis thesis addresses these limitations by proposing a comprehensive approach to anomaly detection in shared mobility systems. The approach integrates diverse data sources, including bike-sharing data, weather data, and mass transit data, to provide a richer contextual understanding of anomalies. Machine learning techniques, such as Isolation Forest, are utilized alongside feature selection methods like Depth-based Isolation Forest Feature Importance (DIFFI) to identify atypical patterns in usage that may indicate operational inefficiencies or unusual user behavior.  \nKey contributions of this work include the development of spatiotemporal, environmental, and transit-related features, the application of interpretable anomaly detection models, and an in-depth analysis of the relationships between anomalies and external factors. These findings offer actionable insights for shared mobility operators, enabling enhancements in system performance and user experience.  \nContents  \nList of Figures xi  \n1 Introduction 1  \n2 Related Work (Literature Review) 3  \n2.1 Shared Mobility Systems and Their Challenges ........... 3  \n2.2 Anomaly Detection in Mobility Systems ............... 5  \n2.3 Feature Engineering and Model Interpretability .......... 7  \n2.4 Summary and Research Gaps ..................... 8  \n3 Methodology 11  \n3. 1 Data Sources . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11  \n3.1.1 Bike-Sharing Data . . . . . . . . . . . . . . . . . . . . . . . 12  \n3.1.2 Weather Data . . . . . . . . . . . . . . . . . . . . . . . . . . 12  \n3.1.3 Public Transit Data . . . . . . . . . . . . . . . . . . . . . . . 13  \n3.1.4 Neighborhood Data ...................... 13  \n3.1.5 Holiday Data .......................... 13  \n3.2 Feature Engineering .......................... 14  \n3.2.1 Trip-Level Feature Engineering ................ 14  \n3.2.2 Station-Level Feature Aggregation .............. 17  \n3.3 Anomaly Detection Approach ..................... 18  \n3.3.1 Isolation Forest for Anomaly Detection ........... 18  \n3.3.2 Feature Importance with DIFFI ................ 19  \n4 Preliminary Work: Trip-Focused Analysis 21  \n4.1 Motivation for Trip-Focused Analysis ................ 21  \n4.2 Exploratory Data Analysis (EDA) ................... 22  \n4.3 Initial Anomaly Detection Results ................... 25  \nCONTENTS  \n4.4 Feature Selection and Dimensionality Reduction .......... 28  \n4.5 SHAP vs. DIFFI: Feature Interpretability Comparison ....... 32  \n4.6 Hypothesis on Special Days ...................... 35  \n4.7 Transition to Station-Level Analysis .................. 37  \n5 Final Results: Station-Focused Analysis 39  \n5.1 Exploratory Data Analysis (EDA) ................... 39  \n5.2 Station-Level Anomaly Detection with Isolation Forest ...... 42  \n5.3 Investigating the Anomaly Spikes ................... 44  \n5.4 Neighborhood and Station-Level Spatial Analysis ......... 49  \n5.5 Case Study: Zero-Duration Anomalies ................ 53  \n5.6 General Insights and Final Interpretation .............. 56  \n6 Conclusions and Future Works 59  \nRe","cbCaiawPunNEstSb","https://ap.wps.com/l/cbCaiawPunNEstSb","pdf",6269311,1,77,"English","en",105,"# 1 Introduction\n# 2 Related Work (Literature Review)\n## 2.1 Shared Mobility Systems and Their Challenges\n## 2.2 Anomaly Detection in Mobility Systems\n## 2.3 Feature Engineering and Model Interpretability\n## 2.4 Summary and Research Gaps\n# 3 Methodology\n## 3.1 Data Sources\n## 3.2 Feature Engineering\n## 3.3 Anomaly Detection Approach\n# 4 Preliminary Work: Trip-Focused Analysis\n## 4.1 Motivation for Trip-Focused Analysis\n## 4.2 Exploratory Data Analysis (EDA)\n## 4.3 Initial Anomaly Detection Results\n## 4.4 Feature Selection and Dimensionality Reduction\n## 4.5 SHAP vs. DIFFI: Feature Interpretability Comparison\n## 4.6 Hypothesis on Special Days\n## 4.7 Transition to Station-Level Analysis\n# 5 Final Results: Station-Focused Analysis\n## 5.1 Exploratory Data Analysis (EDA)\n## 5.2 Station-Level Anomaly Detection with Isolation Forest\n## 5.3 Investigating the Anomaly Spikes\n## 5.4 Neighborhood and Station-Level Spatial Analysis\n## 5.5 Case Study: Zero-Duration Anomalies\n## 5.6 General Insights and Final Interpretation\n# 6 Conclusions and Future Works\n# References","[{\"question\":\"Why is anomaly detection important in shared mobility systems?\",\"answer\":\"Anomalies affect operational efficiency, user satisfaction, and overall system resilience. Detecting them helps operators improve performance and reliability.\"},{\"question\":\"What data sources are combined in the proposed approach?\",\"answer\":\"The framework integrates bike-sharing data with weather data and public transit data, plus additional contextual neighborhood and holiday information.\"},{\"question\":\"How does the thesis make unsupervised anomaly detection interpretable?\",\"answer\":\"It uses Isolation Forest for anomaly detection and DIFFI-based feature importance to identify atypical patterns and explain which features drive the detected anomalies.\"}]","Anomaly Detection for Shared Mobility - Master Thesis | PDF",1785683041,194,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"anomaly-detection-for-shared-mobility-master-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/anomaly-detection-for-shared-mobility-master-thesis/118321/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is anomaly detection important in shared mobility systems?","Question",{"text":75,"@type":76},"Anomalies affect operational efficiency, user satisfaction, and overall system resilience. Detecting them helps operators improve performance and reliability.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data sources are combined in the proposed approach?",{"text":80,"@type":76},"The framework integrates bike-sharing data with weather data and public transit data, plus additional contextual neighborhood and holiday information.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis make unsupervised anomaly detection interpretable?",{"text":84,"@type":76},"It uses Isolation Forest for anomaly detection and DIFFI-based feature importance to identify atypical patterns and explain which features drive the detected anomalies.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]