[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128544-en":3,"doc-seo-128544-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128544,549768064622,"Anda","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine and Deep Learning Applications for Inventory Replenishment Optimization - Master Thesis","Inventory replenishment ensures items, components, and raw materials are acquired and delivered efficiently and on time. Mismanaged replenishment negatively affects customers and business performance, leading to stock-outs, delays, overstocking, lost revenue, reduced profits, and damaged reputation. Forecasting accuracy is central to retailer profitability, especially in fashion where intermittent demand complicates sales prediction. This thesis implements advanced models for intermittent time series and develops a replenishment algorithm based on a modified Periodic Review Policy (Order-Up-To).","University of Padova  \nDEPARTMENT OF MATHEMATICS TULLIO LEVI-CIVITA  \nMASTER THESIS IN DATA SCIENCE  \nMachine and Deep Learning Applications for Inventory Replenishment Optimization  \nSUPERVISOR MASTER CANDIDATE  \nPROF. MARIANGELA GUIDOLIN MASSIMO ANDREETTA  \nUNIVERSITY OF PADOVA 2038499  \nACCADEMIC YEAR  \n2022-2023  \nii  \nAbstract  \nInventory replenishment is the process of obtaining the items, components, and raw materials required to make and sell products. It guarantees that items and resources are acquired and delivered in an eΜcient and timely manner. Poorly managed inventory replenishment can have a severe inΟuence on customers and the overall health of a business, which may result in lost revenue, reduced proΞts and damaged reputation. Implementing the correct inventory replenishment helps manufacturers and sellers in avoiding major issues such as stock-outs, delayed deliveries andoverstocking. Accuracy of forecasting is therefore crucial to retailers' proΞtability. Fashion businesses need precise and accurate sales forecasting tools to prevent stock-outs and maintain a high inventory Ξll rate. This thesis navigates the complex landscape of fashion retail forecasting, addressing the challenges posed by intermittent time series data and stock management. Advanced forecasting models have been implemented to account for the intermittent nature of fashion product demand, resulting in predictions more accurate and reliable.The study extends also tostock replenishment strategies, emphasizing the importance of the reorder point, the Cycle Service Level and the safety stock. Lastly, it culminates in the development of a replenishment algorithm aimed at reducing stock-outs, which is a modiΞed version of the Periodic Review Policy:  \nOrder-Up-To-Level, now tailored to the sporadic nature of intermittent demand.  \niv  \nContents  \nABSTRACT iii  \nLIST OF FIGURES viii  \nLIST OF TABLES x  \nLISTING OF ACRONYMS xii  \n1 INTRODUCTION 1  \n1.1 Operative Context 2  \n1.2 Thesis Outline 5  \n2 DEMAND FORECASTING 6  \n2.1 Intermittent Demand Forecasting 6  \n2.2 Forecasting Methodologies 7  \n2.2.1 Statistical Models 7  \n2.2.2 Machine Learning Models 8  \n3 DATA EXPLORATION AND PRE-PROCESSING 11  \n3.1 Data Selection 11  \n3.2 Data Exploration 12  \n3.2.1 Distribution 15  \n3.2.2 Target and Covariates 16  \n3.3 Pre-processing 17  \n4 FORECASTING 19  \n4.1 Naïve 19  \n4.2 Croston’s method 20  \n4.3 LGBM 21  \n4.4. LSTM 22  \n4.5 NBEATS 25  \n4.6 Implementation 26  \n4.6.1 Training 28  \n4.7 Evaluation 31  \n4.7.1 Evaluation Metrics 31  \n5 REPLENISHMENT 33  \n5.1 Reorder Point 34  \n5.2 Cycle Service Level 35  \n5.3 Implementation 37  \n5.3.1 Simulations 38  \n6 RESULTS 40  \n6.1 Forecasting Models 40  \n6.2 Replenishment Simulations 45  \n7 CONCLUSION 51  \nREFERENCES 53  \nvii  \nListing of Ξgures  \n2.1 Examples of intermittent time series........................................................................... 6  \n2.2 Architecture of a deep (multi-layer) neural network................................................. 9  \n3.1 Examples of extremely intermittent time series........................................................ 11  \n3.2 Distribution of the ratio of weeks with non-null sales............................................. 12  \n3.3 Distribution of the weekly sales................................................................................ 13  \n3.4 Types of covariates .................................................................................................... 17  \n4.1 Internal structure and processes of an LSTM cell.................................................... 24  \n4.2 Internal architecture of NBEATS…………………..……................................................ 26  \n4.3 Training process with one time series……………........................................................ 28  \n4.4 Training process with two time series……………........................................................ 28  \n5.1 Relationship between the service level and the inventory level...","cbCaiklaVMBAkXZh","https://ap.wps.com/l/cbCaiklaVMBAkXZh","pdf",1728680,3,1,72,"English","en",105,"# Abstract\n# Introduction\n## Operative Context\n## Thesis Outline\n# Demand Forecasting\n## Intermittent Demand Forecasting\n## Forecasting Methodologies\n### Statistical Models\n### Machine Learning Models\n# Data Exploration and Pre-processing\n## Data Selection\n## Data Exploration\n### Distribution\n### Target and Covariates\n## Pre-processing\n# Forecasting\n## Naïve\n## Croston’s method\n## LGBM\n## LSTM\n## NBEATS\n## Implementation\n### Training\n## Evaluation\n### Evaluation Metrics\n# Replenishment\n## Reorder Point\n## Cycle Service Level\n## Implementation\n### Simulations\n# Results\n## Forecasting Models\n## Replenishment Simulations\n# Conclusion","[{\"question\":\"Why is forecasting accuracy critical for inventory replenishment in retail?\",\"answer\":\"Accurate forecasting helps retailers avoid stock-outs and overstocking, supporting timely deliveries and healthier inventory levels. Poor forecasting can reduce profits and harm reputation.\"},{\"question\":\"What makes the demand in fashion retail challenging for forecasting?\",\"answer\":\"Fashion demand often follows intermittent time series behavior, where many weeks show non-null sales irregularly. This sparsity requires models tailored to sporadic demand patterns.\"},{\"question\":\"How does the thesis connect demand forecasting to replenishment decisions?\",\"answer\":\"After forecasting intermittent demand using advanced models, the study evaluates replenishment by key parameters such as reorder point, cycle service level, and safety stock. It then develops an Order-Up-To based algorithm adapted to intermittent demand.\"}]","Machine and Deep Learning Applications for Inventory Replenishment Optimization - Master Thesis | PDF",1786001646,181,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"machine-and-deep-learning-applications-for-inventory-replenishment-optimization-master-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/machine-and-deep-learning-applications-for-inventory-replenishment-optimization-master-thesis/128544/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",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},"Why is forecasting accuracy critical for inventory replenishment in retail?","Question",{"text":76,"@type":77},"Accurate forecasting helps retailers avoid stock-outs and overstocking, supporting timely deliveries and healthier inventory levels. Poor forecasting can reduce profits and harm reputation.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What makes the demand in fashion retail challenging for forecasting?",{"text":81,"@type":77},"Fashion demand often follows intermittent time series behavior, where many weeks show non-null sales irregularly. This sparsity requires models tailored to sporadic demand patterns.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the thesis connect demand forecasting to replenishment decisions?",{"text":85,"@type":77},"After forecasting intermittent demand using advanced models, the study evaluates replenishment by key parameters such as reorder point, cycle service level, and safety stock. It then develops an Order-Up-To based algorithm adapted to intermittent demand.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]