[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121775-en":3,"doc-seo-121775-105":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},121775,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Predicting Stock Prices with Investor Trading Behaviour - A Machine Learning Approach","Stock market prediction remains a challenging problem due to complex market dynamics and unclear drivers of asset prices. This thesis investigates how investor trading behaviour relates to stock returns using machine learning. Data from the Finnish stock market covers 2000–2009 and is provided by Euroclear Finland Oy. The study asks how strong the contemporaneous relation is, how behaviour affects future returns, and how effects change across time horizons (1-day, 5-day, 21-day) in both contemporaneous and lead-lag settings. Logistic regression and a previous-period naive model serve as benchmarks, and ensemble methods are evaluated for nonlinear interactions.","Joona Viitanen  \nPREDICTING STOCK PRICES WITH INVESTOR TRADING BEHAVIOUR: A MACHINE LEARNING APPROACH  \nMaster of Science Thesis  \nFaculty of Management and Business Examiners: Professor Juho Kanniainen Dr. Anubha Goel  \ni  \nABSTRACT  \nJoona Viitanen: Predicting Stock Prices with Investor Trading Behaviour: A Machine Learning Approach  \nMaster of Science Thesis Tampere University  \nMaster’s Degree Programme in Industrial Engineering and Management June 2023  \nStock market prediction has always been considered a difficult task in both academia and industry. Markets have complex dynamics by nature and it is not always clear what drives asset prices. However, the rise of machine learning models has enabled the potential to capture patterns in data that were difficult to uncover using traditional methods. Recently, there has been lots of research about using machine learning methods for different applications in stock markets. However, in behavioural finance and specifically in microstructure literature, machine learning methods remain largely unexplored.  \nThis thesis studies the relationship between investor trading behaviour and stock returns using machine learning methods. The data is from the Finnish stock market between 2000-2009 and the unique dataset was provided by Euroclear Finland Oy. The key questions are 1 . How significant is the contemporaneous relation between trading behaviour and stock returns? 2 . How significant is the effect of trading behaviour on future returns? and 3 . How does the relationship change over different time horizons? The thesis studies 1-day, 5-day and 21-day horizons in both contemporaneous and lead-lag settings using different machine learning models. Logistic regression acted as a benchmark model and a previous period model as a naive model.  \nThe results showed some degree of predictability in stock returns in both contemporary and lead-lag settings. The contemporaneous relationship was stronger as the models were able to beat the naive model by a wide margin. Lead-lag relationship was able to produce results above the naive model, but not by a significant margin. Furthermore, the predictability decreased when the time horizon increased in both settings. Finally, the predictability dropped in the 21-day leadlag setting, as no model was able to beat the naive model. When it comes to the machine learning models, most of the models were able to beat benchmark logistic regression and a naive model in most configurations, suggesting nonlinear interactions in the system. From Ensemble-based methods, LightGBM, Random Forest and XGBoost performed the best, while AdaBoost struggled to beat logistic regression in other than 1-day horizons.  \nKeywords: stock market, behavioural finance, investor behaviour, machine learning, return predictability  \nThe originality of this thesis has been checked using the Turnitin OriginalityCheck service. ChatGPT models have been used to help in structuring the thesis, rephrasing text and the creation of LaTex tables.  \nii  \nTIIVISTELMÄ  \nJoona Viitanen: Osakkeiden hintojen ennustaminen sijoittajakäyttäytymisen avulla käyttäen ko  \nneoppimismalleja Diplomityö Tampereen yliopisto  \nTuotantotalouden diplomi-insinöörin tutkinto-ohjelma Kesäkuu 2023  \nOsakemarkkinoiden ennustamista on aina pidetty vaikeana tehtävänä sekä tiedemaailmassa että teollisuudessa. Markkinoiden dynamiikka on luonteeltaan monimutkainen, eikä aina ole selvää, mikä ohjaa arvopapereiden hintoja. Koneoppimismallien nousu on kuitenkin mahdollistanut potentiaalin löytää datasta kaavoja, joita oli vaikea paljastaa perinteisillä menetelmillä . Viime aikoina on tehty paljon tutkimusta koneoppimismenetelmien käytöstä osakemarkkinoilla erilaisiinkäyttötarkoitukseen. Behavioraalisessa rahoituksessa ja erityisesti mikrorakennekirjallisuudessakoneoppimismenetelmiä ei kuitenkaan ole käytetty merkittävästi.  \nTämä opinnäytetyö tutkii sijoittajien kaupankäyntikäyttäytymisen ja osakkeiden tuottojen välistä suhdett","cbCaidtF1wFQQPrP","https://ap.wps.com/l/cbCaidtF1wFQQPrP","pdf",357028,1,57,"English","en",105,"# Abstract\n# Preface\n# Research Questions and Data\n# Methodology and Models\n# Results and Findings\n# Keywords","[{\"question\":\"What is the main goal of this thesis?\",\"answer\":\"To study the relationship between investor trading behaviour and stock returns using machine learning models and to evaluate its predictive power across different horizons.\"},{\"question\":\"What data and time period are used in the study?\",\"answer\":\"The thesis uses data from the Finnish stock market between 2000 and 2009, provided by Euroclear Finland Oy.\"},{\"question\":\"How are the prediction horizons and settings defined?\",\"answer\":\"It evaluates 1-day, 5-day, and 21-day horizons in both contemporaneous and lead-lag configurations.\"}]","Predicting Stock Prices with Investor Trading Behaviour - A Machine Learning Approach | PDF",1785806778,144,{"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},"predicting-stock-prices-with-investor-trading-behaviour-a-machine-learning-approach","",{"@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/predicting-stock-prices-with-investor-trading-behaviour-a-machine-learning-approach/121775/",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","2026-08-04",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},"What is the main goal of this thesis?","Question",{"text":75,"@type":76},"To study the relationship between investor trading behaviour and stock returns using machine learning models and to evaluate its predictive power across different horizons.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data and time period are used in the study?",{"text":80,"@type":76},"The thesis uses data from the Finnish stock market between 2000 and 2009, provided by Euroclear Finland Oy.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the prediction horizons and settings defined?",{"text":84,"@type":76},"It evaluates 1-day, 5-day, and 21-day horizons in both contemporaneous and lead-lag configurations.","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"]