[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123248-en":3,"doc-seo-123248-105":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},123248,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Machine learning in weekly movement prediction - Research benchmark for objective weekly stock direction forecasting","Machine learning research on stock market forecasting often relies on daily data and benchmarks that differ across studies, limiting comparability and standardization. The work shifts focus to weekly movement prediction and proposes a novel random-trader benchmark that is independent of any ML model for more objective evaluation. Training incorporates technical indicators, scaling laws, directional changes, and weighted samples. Backtesting shows stable and robust results, with MLP performing reliably across upward, downward, and cyclic trends.","Machine learning in weekly movement prediction  \nHAN GUI  \nDepartment of Informatics  \nKing ’s College London  \nBush House, Strand Campus, 30, Aldwych, London WC2B 4BG [han.gui@kcl.ac. uk](han.gui@kcl.ac. uk)  \nAbstract  \nTo predict the future movements of stock markets, numerous studies concentrate on daily data and employ various machine learning (ML) models as benchmarks that often vary and lack standardization across different research works. This paper tries to solve the problem from a fresh standpoint by aiming to predict the weekly movements, and introducing a novel benchmark of random traders. This benchmark is independent of any ML model , thus making it more objective and potentially serving as a commonly recognized standard. During training process , apart from the basic features such as technical indicators, scaling laws and directional changes are introduced as additional features , furthermore, the training datasets are also adjusted by assigning varying weights to different samples , the weighting approach allows the models to emphasize specific samples. On backtesting, several trained models show good performance , with the multi-layer perception (MLP) demonstrating stability and robustness across extensive and comprehensive data that include upward, downward and cyclic trends. The unique perspective of this work that focuses on weekly movements, incorporates new features and creates an objective benchmark , contributes to the existing literature on stock market prediction.  \nKeywords: machine learning, computational finance  \n1. Introduction  \nAccurate predictions of stock markets movements are crucial for investors and traders, trading strategies can be designed on the predictions to mitigate potential risks and make consistent profits. With the development of information technology, researchers and investors are increasingly utilizing machine learning techniques to forecast the future trends of financial markets, as machine learning algorithms have the potentials to analyze vast amounts of data, identify complex patterns, and make predictions based on those patterns. However, the prediction tasks are still very challenging, as financial markets are dynamic, noisy and volatile.  \nEMH & RWH  \nEfficient market hypothesis (EMH) and random walk hypothesis (RWH) state that prices of financial instruments already reflect all available information, and financial markets follow a random and unpredictable pattern, it is not possible to consistently beat the market with more than 50% accuracy or above-average profits [1] . While the two hypotheses are theoretical frameworks and not universally accepted. A considerable amount of research suggests that certain markets, particularly emerging markets, may not be fully efficient or well-organized. As a result, there is a possibility that predicting future stock prices and returns could yield better outcomes than random selection. Moreover, when examining the stock market through the viewpoint of behavioral economics and the socioeconomic theory, the market is predictable to some degree [3] . Namely, it is possible to forecast the market to a certain extent.  \nFundamental & technical analysis  \nGenerally, there are two primary methods of analyzing financial markets: fundamental analysis and technical analysis. Fundamental analysis involves the evaluations of various factors such as the intrinsic value of stocks, the performance of the industry and the economy, and the political climate, etc. Technical analysis use indicators and models derived from historical data to identify patterns and trends, and assumes the patterns and trends can provide insights into future price movements. The most commonly used technical indicators for stock market prediction include SMA (Simple Moving Average), EMA (Exponential Moving Average), MACD (Moving Average Convergence Divergence), and RSI (Relative Strength Index) [3] . Traditional methods like ARIMA (Auto-Regressive Integrated Moving Aver","cbCailDqhRco7iH9","https://ap.wps.com/l/cbCailDqhRco7iH9","pdf",1636417,1,29,"English","en",105,"# Introduction\n## EMH & RWH\n## Fundamental & technical analysis\n## Classification & regression\n## Data & market\n## Feature engineering & model selection\n## Weekly prediction benchmark","[{\"question\":\"Why does the paper move from daily to weekly movement prediction?\",\"answer\":\"Most prior studies focus on daily data, making benchmarks inconsistent. Weekly prediction aims to provide a clearer, more comparable evaluation target.\"},{\"question\":\"What is the purpose of the random traders benchmark?\",\"answer\":\"The benchmark is independent of any ML model, improving objectivity and enabling a commonly recognized standard for evaluation.\"},{\"question\":\"What additional inputs and training changes are introduced in the proposed approach?\",\"answer\":\"Besides basic features like technical indicators, the approach adds scaling laws and directional changes, and adjusts training datasets by assigning varying weights to samples.\"}]","Machine learning in weekly movement prediction - Research benchmark for objective weekly stock direction forecasting | PDF",1785815465,73,{"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},"machine-learning-in-weekly-movement-prediction-research-benchmark-for-objective-weekly-stock-direction-forecasting","",{"@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/machine-learning-in-weekly-movement-prediction-research-benchmark-for-objective-weekly-stock-direction-forecasting/123248/",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},"Why does the paper move from daily to weekly movement prediction?","Question",{"text":75,"@type":76},"Most prior studies focus on daily data, making benchmarks inconsistent. Weekly prediction aims to provide a clearer, more comparable evaluation target.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the purpose of the random traders benchmark?",{"text":80,"@type":76},"The benchmark is independent of any ML model, improving objectivity and enabling a commonly recognized standard for evaluation.",{"name":82,"@type":73,"acceptedAnswer":83},"What additional inputs and training changes are introduced in the proposed approach?",{"text":84,"@type":76},"Besides basic features like technical indicators, the approach adds scaling laws and directional changes, and adjusts training datasets by assigning varying weights to samples.","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"]