[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124258-en":3,"doc-seo-124258-105":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},124258,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Small-Scale Demand Forecasting - Exploring the Potential of Machine Learning and Hierarchical Reconciliation - Master’s Thesis","Demand forecasting supports data-driven decisions in areas such as inventory planning and resource allocation. While traditional time-series methods like exponential smoothing and autoregressive models remain common, recent work emphasizes machine learning approaches that can be highly flexible but often need large datasets. This thesis develops forecasting strategies for a young industrial-production company with limited data, comparing Temporal Fusion Transformer (TFT) and LightGBM to an exponential smoothing state-space model. Results show higher average accuracy from both ML models, while forecast reconciliation corrects hierarchical inconsistencies without improving accuracy.","Small-Scale Demand Forecasting:  \nExploring the Potential of Machine Learning and Hierarchical Reconciliation  \nMaster’s thesis in Complex Adaptive Systems  \nViking Zandhoff Westerlund  \nDEPARTMENT OF PHYSICS  \nCHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2023  \n[www.chalmers.se](www.chalmers.se)  \nMaster’s thesis 2023  \nSmall-Scale Demand Forecasting: Exploring the Potential of Machine Learning and Hierarchical Reconciliation  \nVIKING ZANDHOFF WESTERLUND  \nDepartment of Physics Chalmers University of Technology Gothenburg, Sweden 2023  \nSmall-Scale Demand Forecasting:  \nExploring the Potential of Machine Learning and Hierarchical Reconciliation  \nVIKING ZANDHOFF WESTERLUND  \n© VIKING ZANDHOFF WESTERLUND , 2023 .  \nExaminer: Mats Granath, Department of Physics  \nMaster’s Thesis 2023 Department of Physics  \nChalmers University of Technology SE-412 96 Gothenburg Telephone +46 31 772 1000  \nCover: Illustration of hierarchical time series forecasting. Designed with Python and PowerPoint.  \nTypeset in LATEX  \nPrinted by Chalmers Reproservice Gothenburg, Sweden 2023  \nSmall-Scale Demand Forecasting: Exploring the Potential of Machine Learning and Hierarchical Reconciliation  \nVIKING ZANDHOFF WESTERLUND Department of Physics  \nChalmers University of Technology  \nAbstract  \nDemand forecasting plays an important role in facilitating data-driven decisionmaking for businesses, particularly in domains such as inventory planning and resource allocation. While traditional forecasting models such as exponential smoothing and autoregressive models have long been prevalent in the time series forecasting domain, recent research has been increasingly focused on more complex machine learning-based models. These complex models offer great potential and flexibility, but they require large amounts of data to achieve optimal performance. In this thesis, I explored viable approaches for constructing accurate forecasting models fora young company in the industrial production industry who wants to predict their future demand, while facing the challenge of limited data availability. The analysis in this thesis involved comparing the predictive performance of state-of-the-art machine learning models, such as the Temporal Fusion Transformer (TFT) and the LightGBM to an exponential smoothing state-space model. Furthermore, I investigated whether the hierarchical structure of the time series data could be exploited through forecast reconciliation to further increase forecasting accuracy. My findings indicate that both the TFT and LightGBM demonstrate superior forecasting accuracy, improving the average forecast accuracy with 43.1 % and 33.2 % respectively, compared to the exponential smoothing model. However, the TFT displayed inconsistent performance results, suggesting its unreliability. Moreover, the results show that while hierarchical forecast reconciliation does not enhance forecast accuracy, it corrects incoherency between forecasts without compromising accuracy, which is of great value.  \nKeywords: Time series forecasting, Demand forecasting, Hierarchical time series, Temporal Fusion Transformer, LightGBM, Minimum trace reconciliation  \nAcknowledgements  \nI would like to extend my sincere gratitude to the examiner of this thesis, Mats Granath, for his valuable feedback. I would also like to thank Adam Söderholm, the opponent of this thesis, for challenging me to improve my work by providing insightful thoughts and comments.  \nViking Zandhoff Westerlund, Gothenburg, June 2023  \nList of Acronyms  \nBelow is the list of acronyms that have been used throughout this thesis listed in alphabetical order:  \nBU  \nES  \nGBM  \nMinT  \nOLS  \nPSEL  \nTFT  \nWLSs WMASE  \nBottom-Up Reconciliation Exponential Smoothing  \nGradient Boosting Machine Minimum Trace  \nOrdinary-Least-Squares Percentage Sum of Errors per Level Temporal Fusion Transformer  \nWeighted-Least-Squares applying structural scaling Weighted Mean Absolute Scaled Error","cbCaimpDC50C55E4","https://ap.wps.com/l/cbCaimpDC50C55E4","pdf",1864276,1,75,"English","en",105,"# Abstract\n## Keywords\n## Acknowledgements\n## List of Acronyms","[{\"question\":\"What problem does this thesis address?\",\"answer\":\"It addresses demand forecasting for a young industrial production company facing limited historical data.\"},{\"question\":\"Which forecasting models are compared in the thesis?\",\"answer\":\"The thesis compares Temporal Fusion Transformer (TFT) and LightGBM against an exponential smoothing state-space model.\"},{\"question\":\"What is the impact of hierarchical forecast reconciliation?\",\"answer\":\"Hierarchical forecast reconciliation does not increase forecast accuracy, but it corrects incoherence between hierarchical forecasts without compromising accuracy.\"}]","Small-Scale Demand Forecasting - Exploring the Potential of Machine Learning and Hierarchical Reconciliation - Master’s Thesis | PDF",1785821255,189,{"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},"small-scale-demand-forecasting-exploring-the-potential-of-machine-learning-and-hierarchical-reconciliation-masters-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/small-scale-demand-forecasting-exploring-the-potential-of-machine-learning-and-hierarchical-reconciliation-masters-thesis/124258/",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 problem does this thesis address?","Question",{"text":75,"@type":76},"It addresses demand forecasting for a young industrial production company facing limited historical data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which forecasting models are compared in the thesis?",{"text":80,"@type":76},"The thesis compares Temporal Fusion Transformer (TFT) and LightGBM against an exponential smoothing state-space model.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the impact of hierarchical forecast reconciliation?",{"text":84,"@type":76},"Hierarchical forecast reconciliation does not increase forecast accuracy, but it corrects incoherence between hierarchical forecasts without compromising accuracy.","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"]