[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127717-en":3,"doc-seo-127717-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},127717,962084928432,"Emma Wilson","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Challenges in Machine Learning for Predicting Psychological Attributes from Smartphone Data","Predicting psychological attributes through psychometric approaches requires estimating latent constructs that cannot be observed directly. The work leverages smartphone sensor and digital footprint data to extract signals from movement, conversation patterns, activities, and interests, enabling machine-learning models for psychological prediction. The thesis emphasizes meaningful, interpretable, and user-trustworthy predictions by analyzing model behavior, identifying bias, and exposing relied-on variables. With large datasets, multicollinearity complicates feature relevance, so the study groups similar features, quantifies their importance, and visualizes effects to clarify model decision processes.","Challenges in Machine Learning for Predicting Psychological Attributes from Smartphone Data  \nJiew-Quay Au  \nMünchen 2024  \nChallenges in Machine Learning for Predicting Psychological Attributes from Smartphone Data  \nJiew-Quay Au  \nDissertation  \nan der Fakultat für Mathematik, Informatik und Statistik der Ludwig–Maximilians–Universitat München  \neingereicht von Jiew-Quay Au  \nam 04.09.2023  \nErster Berichterstatter: Prof. Dr. Bernd Bischl Zweiter Berichterstatter: Prof. Dr. Markus Bühner Dritter Berichterstatter: Prof. Dr. Achim Zeileis  \nTag der Disputation: 30.01.2024  \nAcknowledgments  \nIam deeply grateful to the many individuals whose help, support, guidance, and advice made this thesis possible. In particular, I would like to express my sincere thanks to thefollowing people: . . .  \n. . . Prof. Dr. BerndBischlfor his unwavering support, encouragement, and valuable guidance throughout the years. Our seamless collaboration and the trust he placed in me have been instrumental in making this thesis a reality.  \n. . . Prof. Dr. Markus Bühner and Prof. Dr. Achim Zeileis for their willingness to serve as the second and third reviewers for my PhD thesis.  \n. . . Prof. Dr. Christian Heumann and Prof. Dr. Helmut Küchenhofffor their willingness tobe part of the examination panel at my PhD defense.  \n. . . Prof. Dr. Clemens Stachl, Dr. Sarah Theres Völkel, and Dr. Ramona Schödelfor their exceptional support, collaborative spirit, and teamwork during our time working together. I would also like to express my sincere appreciation to Dr. Stefan Hummel ofAUDI AGfor his consistent support and guidance. His valuable insights and expertise were instrumental in helping us navigate complex challenges and achieve our goals.  \n. . . all my coauthors for their supportive collaboration.  \n. . . my parents, my brother, and my sisterfor their support and encouragement throughout my life.  \n. . . my partner Vanessa and our children Eliza, Estelle, and Eleanorfor their unwavering love and constant encouragement, which have enriched my life beyond measure. Although their lively and charismatic personalities often poseda challenge to maintainingfocus during my research, they always stood by me with unrivaled dedication to help me achieve my goal of completing my PhD.  \nvi  \nSummary  \nPredicting psychological attributes using psychometric approaches is a complex task that involves estimating latent constructs that cannot be directly measured. Psychometrics focuses on the measurement and assessment of psychological attributes, such as personality traits, behavioral patterns, or psychological disorders. Traditionally, personality assessment relied on self-report questionnaires, but advancements in technology have opened up new possibilities for assessment, particularly through the analysis of digital footprints.  \nSmartphone sensor data has become particularly valuable in this context. By analyzing data related to movement, conversation patterns, activities, and interests, it is possible to gather insights that can contribute to predicting psychological attributes. Machine learning techniques are commonly employed to develop predictive models in this field. However, it is essential to ensure that the predictions are meaningful, accepted, and interpretable to gain trust from users.  \nInterpreting machine learning models is crucial in the context of psychometric prediction. Interpreting the models helps identify biases, understand their operations, and determine the variables they rely on. This process enhances the accuracy of the models, establishes trust in their predictions, and promotes fairness in the prediction process. Given the large datasets involved in using smartphone sensor data, the issue of multicollinearity arises, making it challenging to identify which features are truly essential for predicting psychological attributes. To address this challenge, this thesis focuses on grouping similar features and quantifying their importance, aiming to","cbCaifgqDXtrDo6z","https://ap.wps.com/l/cbCaifgqDXtrDo6z","pdf",12144641,1,254,"English","en",105,"# Summary\n## Psychological attribute prediction via psychometrics\n## Smartphone data and machine learning models\n## Model interpretation, bias, and trust\n## Feature groups, multicollinearity, and importance quantification\n## Visualization of feature-group effects","[{\"question\":\"Why is predicting psychological attributes challenging in this thesis?\",\"answer\":\"Psychometric prediction requires estimating latent constructs that cannot be directly measured, making the modeling task complex and sensitive to measurement quality.\"},{\"question\":\"What role do smartphone sensor data play?\",\"answer\":\"Smartphone data enable extraction of movement, conversation, activity, and interest signals, which can support machine-learning models for psychological prediction.\"},{\"question\":\"How does the thesis address multicollinearity and feature relevance?\",\"answer\":\"It groups similar features, quantifies their importance to reduce complexity, and highlights the most relevant factors for prediction.\"}]","Challenges in Machine Learning for Predicting Psychological Attributes from Smartphone Data | PDF",1785941155,640,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"challenges-in-machine-learning-for-predicting-psychological-attributes-from-smartphone-data","",{"@graph":36,"@context":86},[37,54,69],{"@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/challenges-in-machine-learning-for-predicting-psychological-attributes-from-smartphone-data/127717/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is predicting psychological attributes challenging in this thesis?","Question",{"text":76,"@type":77},"Psychometric prediction requires estimating latent constructs that cannot be directly measured, making the modeling task complex and sensitive to measurement quality.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What role do smartphone sensor data play?",{"text":81,"@type":77},"Smartphone data enable extraction of movement, conversation, activity, and interest signals, which can support machine-learning models for psychological prediction.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the thesis address multicollinearity and feature relevance?",{"text":85,"@type":77},"It groups similar features, quantifies their importance to reduce complexity, and highlights the most relevant factors for prediction.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]