[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124365-en":3,"doc-seo-124365-105":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},124365,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Economic and Environmental Potential of Machine Learning in Demand Forecasting - Bachelor’s Thesis - Computer Science - January 2025","Demand forecasting accuracy is critical for suppliers of perishable goods to match customer demand while preventing over-stocking and inevitable spoilage. Better predictions enable improved logistics planning that increases sales and reduces waste, strengthening both profitability and environmental sustainability. The thesis investigates how machine learning can outperform traditional approaches using established methods. It implements an LSTM model for regional distribution-center data, emphasizing data quality, cleaning, feature engineering, hyperparameter optimization, and systematic architectural testing under limited computational resources.","MORTEN KNUDSEN  \nDEPARTMENT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE  \nEconomic and Environmental Potential of Machine Learning in Demand Forecasting  \nBachelor's Thesis-Computer Science-January 2025  \nI, Morten Knudsen, declare that this thesis titled,“Economic and Environmental Potential of Machine Learning in Demand Forecasting” and the work presented in it are my own. I confirm that:  \n■ This work was done wholly or mainly while in candidature for a bachelor’s degree at the University of Stavanger.  \n■ Where I have consulted the published work of others, this is always clearly attributed.  \n■ Where I have quoted from the work of others, the source is always given. With the exception of such quotations, this thesis is entirely my own work.  \n■ I have acknowledged all main sources of help.  \n“Torture the data, and it will confess to anything.”  \n– Ronald Coase  \nAbstract  \nDemand forecasting precision is essential for suppliers of perishable items tobe able to meet customer demand and avoid over-stocking goods that will inevitably spoil. Accurately predicting demand enables optimal logistical organization that maximize sales and minimize waste, allowing for increased profitability and decreased environmental impact. Machine learning have the potential to improve demand forecasting accuracy in comparison with traditional methods, with a number of established approaches documented to increase precision. This bachelor thesis will implement an LSTM network to create a demand forecasting model for perishable items supplied from a regional distribution center, detailing the associated challenges and strategies for handling them. Data quality and cleaning is essential for successful model implementation, along with careful feature engineering and optimization of hyperparameters. Access to computational resources is necessary to determine optimal model configuration by testing large numbers of model architectures. Combinations of hyperparameters are systematically tested to create an initial model with selected features. Feature relevancy is tested through a series of experiments on the initial model, forming the foundation for further model optimization. Evaluation of model architecture and performance conclude further dataset and feature improvements are necessary to reach an acceptable level of demand forecasting precision, pointing to features describing the availability and type of items as intriguing avenues of future research.  \nAcknowledgements  \nI would like to thank Coop Norge SA for making this project possible by sharing the necessary data. The functionality of the neural networks created during this bachelor thesis is entirely dependent on the input data and information made available by them.  \nThe advice and encouragement from my supervisor Antorweep Chakravorty has also been greatly appreciated during the writing of this bachelor thesis. I thank him for agreeing to take on the role of supervisor for this thesis without any hesitation, the contribution of which was instrumental to making this project possible. His insights always steered me in the right direction, and his feedback always managed to keep me motivated.  \nI would also like to thank my family forbearing with me through the troubled times of this thesis. Their backing has been invaluable.  \nContents  \nAbstract iii  \nAcknowledgements iv  \n1 Introduction 1  \n1.1 Background and Motivation ..................... 1  \n1.2 Objectives ................................ 3  \n1.3 Approach and Contributions ..................... 4  \n1.4 Outline ................................. 5  \n2 Related Work 7  \n2.1 Demand forecasting and perishable items .............. 7  \n2.2 Potential of artificial intelligence and machine learning in demand forecasting ............................... 8  \n2.3 Basic machine learning and demand forecasting .......... 9  \n2.4 Machine learning challenges for demand forecasting ........ 9  \n2.4.1 Data quality .......................... 10  \n2.4.","cbCaiiaUDFROKSDt","https://ap.wps.com/l/cbCaiiaUDFROKSDt","pdf",3316254,1,214,"English","en",105,"# Abstract\n# Acknowledgements\n# 1 Introduction\n## Background and Motivation\n## Objectives\n## Approach and Contributions\n## Outline\n# 2 Related Work\n## Demand forecasting and perishable items\n## Potential of artificial intelligence and machine learning in demand forecasting\n## Basic machine learning and demand forecasting\n## Machine learning challenges for demand forecasting\n## Evaluation metrics\n## Applicable models for demand forecasting\n# 3 Approach\n## Choice of demand forecasting model\n## Dataset\n## Dataset operationalization\n## Proposed Solution\n# 4 Experimental Evaluation\n## Experimental Setup and Data Set\n## Experimental Results\n# 5 Discussion\n## Complexity of model architecture\n## Model performance\n## Limitations of current dataset and features\n# 6 Conclusions\n# A Instructions to Compile and Run System","[{\"question\":\"Why is demand forecasting important for perishable items?\",\"answer\":\"Accurate demand forecasts help prevent over-stocking that leads to spoilage. This supports better logistics decisions, higher sales, and reduced waste and environmental impact.\"},{\"question\":\"What machine learning model is implemented in the thesis?\",\"answer\":\"The thesis implements an LSTM network to build a demand forecasting model for perishable items supplied from a regional distribution center.\"},{\"question\":\"Which steps are emphasized for successful model implementation?\",\"answer\":\"The thesis emphasizes data quality and cleaning, careful feature engineering, hyperparameter optimization, and systematic testing of model architectures to select relevant features.\"}]","Economic and Environmental Potential of Machine Learning in Demand Forecasting - Bachelor’s Thesis - Computer Science - January 2025 | PDF",1785821832,539,{"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},"economic-and-environmental-potential-of-machine-learning-in-demand-forecasting-bachelors-thesis-computer-science-january-2025","",{"@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/economic-and-environmental-potential-of-machine-learning-in-demand-forecasting-bachelors-thesis-computer-science-january-2025/124365/",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 is demand forecasting important for perishable items?","Question",{"text":75,"@type":76},"Accurate demand forecasts help prevent over-stocking that leads to spoilage. This supports better logistics decisions, higher sales, and reduced waste and environmental impact.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning model is implemented in the thesis?",{"text":80,"@type":76},"The thesis implements an LSTM network to build a demand forecasting model for perishable items supplied from a regional distribution center.",{"name":82,"@type":73,"acceptedAnswer":83},"Which steps are emphasized for successful model implementation?",{"text":84,"@type":76},"The thesis emphasizes data quality and cleaning, careful feature engineering, hyperparameter optimization, and systematic testing of model architectures to select relevant features.","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"]