[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117624-en":3,"doc-seo-117624-105":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},117624,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Benchmarking Automated Machine Learning Methods for Price Forecasting Applications - Research Report","Price forecasting for used construction equipment faces significant spatial and temporal price fluctuations, making accurate residual value prediction difficult. The work addresses practical constraints for small and medium-sized enterprises that lack sufficient machine learning expertise. It presents an approach that replaces manually built ML pipelines with automated machine learning (AutoML) and combines AutoML outputs with company domain knowledge. Using CRISP-DM, the pipeline is split into ML and non-ML components, and a method evaluation score is introduced to unify technical and nontechnical quality and usability metrics.","arXiv :2304 . 14735v1 [ cs .LG] 28 Apr 2023  \nBenchmarking Automated Machine Learning Methods for Price Forecasting Applications  \nHorst Stühler 1a , Marc-André Zöller2b , Dennis Klau3c , Alexandre Beiderwellen-Bedrikow 1  \nd and Christian Tutschku3e  \n1 Zeppelin GmbH, Graf-Zeppelin-Platz 1, 85766 Garching, Germany  \n2 USU Software AG, Rüppurrer Str. 1, 76137 Karlsruhe, Germany  \n3 Fraunhofer IAO, Nobelstraße 12, 70569 Stuttgart, Germany  \n{horst.stuehler, [alexandre.bedrikow}@zeppelin.com](alexandre.bedrikow}@zeppelin.com), [marc.zoeller@usu.com](marc.zoeller@usu.com),  \n{dennis.klau, [christian.tutschku}@iao.fraunhofer.de](christian.tutschku}@iao.fraunhofer.de)  \nKeywords: Construction Equipment, Price Forecasting, Machine Learning, ML, AutoML, CRISP-DM, Case Study  \nAbstract: Price forecasting for used construction equipment is a challenging task due to spatial and temporal price fluctuations. It is thus of high interest to automate the forecasting process based on current market data. Eventhough applying machine learning (ML) to these data represents a promising approach to predict the residual value of certain tools, it is hard to implement for small and medium-sized enterprises due to their insufficient ML expertise. To this end, we demonstrate the possibility of substituting manually created ML pipelines with automated machine learning (AutoML) solutions, which automatically generate the underlying pipelines. We combine AutoML methods with the domain knowledge of the companies. Based on the CRISP-DM process, we split the manual ML pipeline into a machine learning and non-machine learning part. To take all complex industrial requirements into account and to demonstrate the applicability of our new approach, we designed a novel metric named method evaluation score, which incorporates the most important technical and nontechnical metrics for quality and usability. Based on this metric, we show in a case study for the industrial use case of price forecasting, that domain knowledge combined with AutoML can weaken the dependence on ML experts for innovative small and medium-sized enterprises which are interested in conducting such solutions.  \n1 INTRODUCTION  \nPrice forecasting is crucial for companies dealing with used assets whose price depends on availability and demand varying spatially and over time. Especially the sector of heavy construction equipment dealers and rental companies relies heavily on accurate price predictions. Determining the current and future residual value of their fleet allows construction equipment dealers to identify the optimal time to resell individual pieces of machinery (Lucko et al., 2007; Chiteri, 2018) . Although several data-driven methods have been proposed to forecast the heavy equipment's residual value (Lucko, 2003; Lucko and Vorster, 2004; Fan et al., 2008; Lucko, 2011; Zong,  \na [https://orcid.org/0000-0002-7638-1861](https://orcid.org/0000-0002-7638-1861)  \nb [https://orcid.org/0000-0001-8705-9862](https://orcid.org/0000-0001-8705-9862)  \nc [https://orcid.org/0000-0003-3618-7359](https://orcid.org/0000-0003-3618-7359)  \nd [https://orcid.org/0000-0001-7934-8410](https://orcid.org/0000-0001-7934-8410)  \ne [https://orcid.org/0000-0003-0401-5333](https://orcid.org/0000-0003-0401-5333)  \n2017; Miloševi et al., 2020), price forecasting in practice is still mainly performed manually due to the lack of sufficiently skilled employees. Consequently, it is a time-consuming and inflexible process that highly depends on the domain expertise of the employees. Due to these substantial time, cost, and knowledge factors, the manual process is generally carried out irregularly and infrequently, maybe even fragmentary. This may lead to partially outdated or even obsolete prices, as current market price fluctuations are not taken into account (Ponnaluru et al., 2012) . To reflect current market prices while supporting domain experts and digitalization of price prediction in general, it is desirable to automate","cbCaib8gXaZxJrHE","https://ap.wps.com/l/cbCaib8gXaZxJrHE","pdf",522495,1,10,"English","en",105,"# Introduction\n## Problem: Manual price forecasting\n## Prior work on ML and residual value prediction\n## AutoML as an alternative for SMEs\n## Case study design and CRISP-DM-based pipeline split","[{\"question\":\"Why is price forecasting for used construction equipment challenging?\",\"answer\":\"Prices vary across space and time, creating fluctuations that complicate residual value prediction.\"},{\"question\":\"What makes the manual ML pipeline difficult for small and medium-sized enterprises?\",\"answer\":\"SMEs often lack employees with sufficient machine learning expertise, making the process time-consuming, inflexible, and dependent on domain knowledge.\"},{\"question\":\"How does the proposed approach improve feasibility using AutoML?\",\"answer\":\"AutoML generates underlying pipelines automatically, and the method combines AutoML with domain knowledge while structuring the workflow via CRISP-DM into ML and non-ML parts.\"}]","Benchmarking Automated Machine Learning Methods for Price Forecasting Applications - Research Report | PDF",1785677365,25,{"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},"benchmarking-automated-machine-learning-methods-for-price-forecasting-applications-research-report","",{"@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/benchmarking-automated-machine-learning-methods-for-price-forecasting-applications-research-report/117624/",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","2026-08-02",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 price forecasting for used construction equipment challenging?","Question",{"text":75,"@type":76},"Prices vary across space and time, creating fluctuations that complicate residual value prediction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes the manual ML pipeline difficult for small and medium-sized enterprises?",{"text":80,"@type":76},"SMEs often lack employees with sufficient machine learning expertise, making the process time-consuming, inflexible, and dependent on domain knowledge.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed approach improve feasibility using AutoML?",{"text":84,"@type":76},"AutoML generates underlying pipelines automatically, and the method combines AutoML with domain knowledge while structuring the workflow via CRISP-DM into ML and non-ML parts.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]