[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127027-en":3,"doc-seo-127027-105":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},127027,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Deep Learning and Machine Learning Models for High-Frequency Stock Price Prediction and Inference","Deep learning and machine learning models are developed for high-frequency stock price prediction and inference. The work compares Long Short-Term Memory (LSTM), Convolutional LSTMs (CLSTM), and Transformer architectures across single-step and multi-step forecasting tasks. Training leverages datasets enriched with technical indicators, sentiment analysis, and the US Dollar Index, plus Fourier-transformed features to strengthen feature engineering. Results show Transformer variants with convolutional layers better capture long-term dependencies and yield more accurate extended-horizon predictions. Fourier-transformed representations reveal underlying periodic patterns to further improve performance, supporting more effective financial forecasting.","UCLA  \nUCLA Electronic Theses and Dissertations  \nTitle  \nDeep Learning and Machine Learning Models for High-Frequency Stock Price Prediction and Inference  \nPermalink  \n[https://escholarship.org/uc/item/2pz9p0dc](https://escholarship.org/uc/item/2pz9p0dc)  \nAuthor  \nZhang, Yuelong  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA Los Angeles  \nDeep Learning and Machine Learning Models for High-Frequency Stock Price Prediction and Inference  \nA thesis submitted in partial satisfaction of the requirements for the degree Master of Science in Statistics  \nby  \nYuelong Zhang  \n2024  \n© Copyright by Yuelong Zhang 2024  \nABSTRACT OF THE THESIS  \nDeep Learning and Machine Learning Models for High-Frequency Stock Price Prediction and Inference  \nby  \nYuelong Zhang  \nMaster of Science in Statistics  \nUniversity of California, Los Angeles, 2024  \nProfessor George Michailidis, Chair  \nThis thesis investigates the use of deep learning and machine learning models for highfrequency stock price prediction and inference. By using models such as Long Short-Term Memory (LSTM) networks, Convolutional LSTMs (CLSTM), and Transformer architectures, this work evaluates the predictive performance of these models in both single-step and multi-step stock price prediction tasks. The models are trained on various datasets, including those with technical indicators, sentiment analysis, and the US Dollar Index, along with Fourier-transformed features for improved feature engineering. The results demonstrate that Transformer-based models, particularly those added with convolutional layers, outperform LSTM-based models in capturing long-term dependencies and making accurate predictions over extended time periods. Additionally, the Fourier-transformed features enhances overall models performance by revealing underlying periodic patterns in stock prices. This research contributes to the growing literature on stock price prediction and inference by offering insights into model architectures and feature engineering techniques that improve the accuracy of financial forecasting.  \nThe thesis of Yuelong Zhang is approved.  \nFrederic R. Paik Schoenberg Yingnian Wu  \nGeorge Michailidis, Committee Chair  \nUniversity of California, Los Angeles 2024  \nTo my family, whose unwavering support and encouragement have guided me throughout  \nmy life.  \nTABLE OF CONTENTS  \n1 Introduction ...................................... 1  \n2 Literature Review .................................. 2  \n2.1 Prediction Task and Inference Task ....................... 2  \n2.2 Optimization ................................... 2  \n2.2.1 Gradient-Based Optimization Methods ................. 3  \n2.2.2 Advanced Optimization algorithm .................... 5  \n2.3 Deep Learning Models .............................. 8  \n2.3.1 Common Layers in Neural Network ................... 8  \n2.3.2 Convolutional Neural Networks ..................... 10  \n2.3.3 Recurrent Neural Networks ....................... 11  \n2.3.4 Transformer ................................ 12  \n2.4 Machine learning model ............................. 14  \n2.4.1 Extreme Gradient Boosting Tree .................... 14  \n3 Dataset Introduction ................................ 17  \n3.1 Lookback Timestamp ............................... 17  \n3.2 Time interval ................................... 17  \n3.3 Single-step prediction ............................... 17  \n3.3.1 Basic Data (D1 ) .............................. 18  \n3.3.2 Data with Technical Indicator (D2 ) ................... 18  \n3.3.3 Dataset with sentiment analysis and Dollar Index (D3 ) ........ 19  \n3.4 Sequence Prediction ............................... 20  \n3.4.1 Sequence Data (D4 ) ........................... 20  \n3.4.2 Sequence Data with Fourier Transformation (D5 ) ........... 20  \n3.5 Data Preprocessing ................................ 21","cbCaihlttc0RglwU","https://ap.wps.com/l/cbCaihlttc0RglwU","pdf",1266109,1,62,"English","en",105,"# Introduction\n# Literature Review\n## Prediction Task and Inference Task\n## Optimization\n## Deep Learning Models\n## Machine learning model\n# Dataset Introduction\n## Lookback Timestamp\n## Time interval\n## Single-step prediction\n## Sequence Prediction\n## Data Preprocessing\n## Dataset Summary\n# Single-Step SPY Prediction\n## Problem Formantion\n## Model Introduction\n## Training Setup\n## Experiment Results\n## Discussion\n# Multiple Steps Prediction\n## Problem Formation\n## Model Introduction\n## Training Setup\n## Half Year Experiment\n## Full Year Experiment\n## Discussion\n# Inference\n## Feature Importance","[{\"question\":\"Which model architectures are compared for high-frequency stock price prediction?\",\"answer\":\"The thesis compares LSTM networks, convolutional LSTMs (CLSTM), and Transformer-based architectures, including convolutional variants.\"},{\"question\":\"How does the research handle both single-step and multi-step prediction tasks?\",\"answer\":\"It evaluates predictive performance for single-step and multi-step stock price forecasting, using different model structures such as encoder-only Transformers and encoder-decoder Transformers.\"},{\"question\":\"What role do Fourier-transformed features play in model performance?\",\"answer\":\"Fourier-transformed features improve overall performance by revealing underlying periodic patterns in stock prices, which helps the models capture longer-term structure.\"}]","Deep Learning and Machine Learning Models for High-Frequency Stock Price Prediction and Inference | PDF",1785936411,156,{"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},"deep-learning-and-machine-learning-models-for-high-frequency-stock-price-prediction-and-inference","",{"@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/deep-learning-and-machine-learning-models-for-high-frequency-stock-price-prediction-and-inference/127027/",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","2026-08-22","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},"Which model architectures are compared for high-frequency stock price prediction?","Question",{"text":76,"@type":77},"The thesis compares LSTM networks, convolutional LSTMs (CLSTM), and Transformer-based architectures, including convolutional variants.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the research handle both single-step and multi-step prediction tasks?",{"text":81,"@type":77},"It evaluates predictive performance for single-step and multi-step stock price forecasting, using different model structures such as encoder-only Transformers and encoder-decoder Transformers.",{"name":83,"@type":74,"acceptedAnswer":84},"What role do Fourier-transformed features play in model performance?",{"text":85,"@type":77},"Fourier-transformed features improve overall performance by revealing underlying periodic patterns in stock prices, which helps the models capture longer-term structure.","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"]