[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119494-en":3,"doc-seo-119494-105":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},119494,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",6,"Technology","Graph Machine Learning for fast product development from formulation trials","Product development aims to create new or improved products, and formulation trials are a critical step requiring extensive exploration of variables and product properties. Traditional trial-and-error experimentation is slow and resource intensive. Machine learning can speed up development, but many models remain difficult to interpret, limiting trust, regulatory compliance, and understanding of decision logic. The work proposes a fast product development methodology using graph machine learning, explainability, and visualization, learning latent item graphs from tabular trials and predicting consumer-appealing properties. Results on two datasets show accurate prediction, reduced lab experiments, and lower material waste, while supporting R&D recipe discovery through perturbation and sensitivity analysis.","Graph Machine Learning for fast product development from formulation trials  \nManuel Dileo(􀀀) 1[0000−0002−4861−455X], Raffaele Olmeda2[0000−0001−9258−7416], Margherita Pindaro2[0009−0008−6250−9650], and Matteo Zignani 1[0000−0002−4808−4106]  \n1 Department of Computer Science, University of Milan, Milan, Italy  \n{manuel.dileo, [matteo.zignani}@unimi.it](matteo.zignani}@unimi.it)[ ](matteo.zignani}@unimi.it)2 Intellico s.r.l. , Milan, Italy  \n{raffaele.olmeda, [margherita.pindaro}@intellico.ai](margherita.pindaro}@intellico.ai)  \nAbstract. Product development is the process of creating and bringing a new or improved product to market. Formulation trials constitute a crucial stage in product development, often involving the exploration of numerous variables and product properties. Traditional methods of formulation trials involve time-consuming experimentation, trial and error, and iterative processes. In recent years, machine learning (ML) has emerged as a promising avenue to streamline this complex journey by enhancing efficiency, innovation, and customization. One of the paramount challenges in ML for product development is the models’ lack of interpretability and explainability. This challenge poses significant limitations in gaining user trust, meeting regulatory requirements, and understanding the rationale behind ML-driven decisions. Moreover, formulation trials involve the exploration of relationships and similarities among previous preparations; however, data related to formulation are typically stored in tables and not in a network-like manner. To cope with the above challenges, we propose a general methodology for fast product development leveraging graph ML models, explainability techniques, and powerful data visualization tools. Starting from tabular formulation trials, our model simultaneously learns a latent graph between items anda downstream task, i.e. predicting consumer-appealing properties of a formulation. Subsequently, explainability techniques based on graphs, perturbation, and sensitivity analysis effectively support the R&D department in identifying new recipes for reaching a desired property. We evaluate our model on two datasets derived from a case study based on food design plus a standard benchmark from the healthcare domain.  \nResults show the effectiveness of our model in predicting the outcome of new formulations. Thanks to our solution, the company has drastically reduced the labor-intensive experiments in real laboratories and the waste of materials.  \nKeywords: Product Development · Structure Learning · XAI for tabular data  \n2 M. Dileo et al.  \n1 Introduction  \nProduct development refers to the systematic process of designing, creating, and introducing new or improved products into the market. A fundamental step of this process is represented by the formulation trials, in which the research and development (R&D) department of industrial companies experiments with various ingredients, proportions, physical properties, and other factors to determine the optimal combination that meets the desired specifications and performance criteria. Conventional approaches to formulation trials typically utilize laborintensive experimentation, trial and error, and iterative procedures, which can take several weeks to meet a desired formulation.  \nOver the past few years, machine learning (ML) has emerged as a promising solution for simplifying this process and enhancing efficiency, innovation, and customization. A main challenge in ML for product development is the models’ lack of interpretability and explainability. This limitation poses significant burdens in gaining user trust, fulfilling regulatory standards, and understanding the logic behind ML-driven decisions. Moreover, formulation trials involve the exploration of relationships and similarities among previous preparations or solutions; but, data related to these formulations are typically stored in tables without explicit relationships between trials.","cbCailtD2d5WlMkB","https://ap.wps.com/l/cbCailtD2d5WlMkB","pdf",938839,1,16,"English","en",105,"# Abstract\n# Introduction\n## Formulation trials and their challenges\n## Machine learning for faster development\n## Proposed graph ML methodology and explainability\n## Case study in food design and evaluation","[{\"question\":\"Why are formulation trials important in product development?\",\"answer\":\"Formulation trials determine optimal combinations of ingredients, proportions, and physical properties to meet desired specifications, making them a fundamental step before a product reaches the market.\"},{\"question\":\"What key limitation exists for machine learning in product development?\",\"answer\":\"Many ML models lack interpretability and explainability, which constrains user trust, regulatory acceptance, and understanding the rationale behind ML-driven decisions.\"},{\"question\":\"How does the proposed approach use graph machine learning with tabular trials?\",\"answer\":\"Starting from tabular formulation trials, the model jointly learns a latent graph among items and a downstream prediction task, such as forecasting consumer-appealing properties.\"}]","Graph Machine Learning for fast product development from formulation trials | PDF",1785724611,40,{"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},"graph-machine-learning-for-fast-product-development-from-formulation-trials","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/graph-machine-learning-for-fast-product-development-from-formulation-trials/119494/",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","2026-08-03",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 are formulation trials important in product development?","Question",{"text":75,"@type":76},"Formulation trials determine optimal combinations of ingredients, proportions, and physical properties to meet desired specifications, making them a fundamental step before a product reaches the market.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What key limitation exists for machine learning in product development?",{"text":80,"@type":76},"Many ML models lack interpretability and explainability, which constrains user trust, regulatory acceptance, and understanding the rationale behind ML-driven decisions.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed approach use graph machine learning with tabular trials?",{"text":84,"@type":76},"Starting from tabular formulation trials, the model jointly learns a latent graph among items and a downstream prediction task, such as forecasting consumer-appealing properties.","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},[93,97,101,105,110,113,117,122,127,130,134],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":29,"slug":116},7,"Healthcare","healthcare",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",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"]