[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123277-en":3,"doc-seo-123277-105":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},123277,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning to Predict Risk Management Applications Performance - Research","Machine Learning is used to predict application performance through a black-box approach that avoids detailed knowledge of internal implementation. The study models and forecasts execution time for an industrial risk calculation application tied to Solvency II regulations in insurance. Multiple models are compared, with XGBoost achieving the best accuracy (Mean Absolute Percentage Error of 23%). Results show robust performance for intermediate durations, while shorter and very long runs degrade due to limited data, supporting better prediction for resource allocation and performance management.","Machine Learning to Predict Risk Management Applications Performance  \nLaura De Giorgi  \nDepartment of Electronics Information and Bioengineering Politecnico Di Milano Tinvention s.r.l.  \nEmail: [laura.degiorgi@polimi.it](laura.degiorgi@polimi.it)  \nDanilo Ardagna  \nDepartment of Electronics Information and Bioengineering Politecnico Di Milano Email: [danilo.ardagna@polimi.it](danilo.ardagna@polimi.it)  \nAbstract—Machine Learning is increasingly crucial for predicting application performance, offering a black-box approach that does not require a deep understanding of the application internal workings. This method enables accurate predictions without delving into complex system models. Our study utilized ML to forecast the execution time of an industrial application dealing with risk measures as part of the Solvency II regulations for insurance companies. By conducting a comparative analysis of multiple models, XGBoost was identified as the most effective, achieving a Mean Absolute Percentage Error of 23%. The results demonstrated robust accuracy for intermediate durations, though limitations were observed for shorter and significantly longer times due to data scarcity. Overall, this study highlights the significant potential of ML in improving prediction accuracy for complex industrial applications, offering valuable insights for resource allocation and performance management.  \nIndex Terms—Performance, Machine Learning, XGBoost  \nI. INTRODUCTION  \nPredicting software execution time and performance metricsis essential in software-related endeavors, particularly with established Service Level Agreements (SLAs) . Accurate resource allocation based on expected workloads is crucial for job scheduling and data center management. The complexity of modern software, including big data and High-Performance Computing (HPC) applications, challenges traditional analytical methods. These applications involve multiple software layers and operate across cluster nodes, making performance analysis intricate. In such scenarios, black-box techniques like Machine Learning (ML) are preferred due to their ability to map input/output relationships to performance indicators without requiring internal system knowledge. This study compares several ML models developed to predict the execution time of an industrial risk calculation application. Starting from simpler cases and progressively addressing more complex scenarios, our approach was incremental. The application processes various financial reports, requiring a predictive model capable of handling variability in the report numbers processed by individual requests. Our dataset spans from September 2022 to February 2024, containing 43,480 runs. Initial analyses considered executions requiring only one report, extending to runs requiring up to 100 reports. This methodology yielded an average percent error of 11% for one-report cases and 23% for 100-report cases. This paper is organized as follows. Section II reviews current Machine Learning (ML) approaches for forecasting ICT system performance. Section III provides  \n979-8-3503-6104-9/24/$31.00 ©2024 IEEE  \na brief overview of the application functionality. In Section IV, statistical analysis reports the distribution of run times and the number of reports in our historical dataset. Section V details the methodology and experimental results, explaining how the variable demands associated with each execution were addressed. Finally, conclusions are drawn in Section VI.  \nII. RELATED WORK  \nML is integral in forecasting ICT system performance, with applications ranging from video streaming platforms, where it evaluates service quality through QoD (Quality of Delivery) metrics [4], to cloud systems, AI models, communication networks, and FaaS systems. Maros et al. [3] used ML to predict Apache Spark job performance, outperforming native Spark models for various workloads. In cloud-based IoT management, Nawrocki and Osypanka [15] combined multiple ML mode","cbCaikxBqpucR3s6","https://ap.wps.com/l/cbCaikxBqpucR3s6","pdf",1429233,1,6,"English","en",105,"# Introduction\n## Related Work\n# Application\n## Application Architecture","[{\"question\":\"Why is machine learning suitable for predicting application performance in this study?\",\"answer\":\"The study uses a black-box ML method that maps input-output behavior to performance indicators without requiring deep knowledge of the application’s internal workings.\"},{\"question\":\"Which model performed best for execution time prediction, and what accuracy was achieved?\",\"answer\":\"XGBoost delivered the strongest results, with a Mean Absolute Percentage Error of 23% across the evaluated runs.\"},{\"question\":\"What limitations were observed in the prediction results?\",\"answer\":\"Prediction accuracy is robust for intermediate execution durations, but performance drops for shorter and significantly longer times because of data scarcity.\"}]","Machine Learning to Predict Risk Management Applications Performance - Research | PDF",1785815679,15,{"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-to-predict-risk-management-applications-performance-research","",{"@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-to-predict-risk-management-applications-performance-research/123277/",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 machine learning suitable for predicting application performance in this study?","Question",{"text":75,"@type":76},"The study uses a black-box ML method that maps input-output behavior to performance indicators without requiring deep knowledge of the application’s internal workings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which model performed best for execution time prediction, and what accuracy was achieved?",{"text":80,"@type":76},"XGBoost delivered the strongest results, with a Mean Absolute Percentage Error of 23% across the evaluated runs.",{"name":82,"@type":73,"acceptedAnswer":83},"What limitations were observed in the prediction results?",{"text":84,"@type":76},"Prediction accuracy is robust for intermediate execution durations, but performance drops for shorter and significantly longer times because of data scarcity.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]