{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:52:33Z","timestamp":1781725953642,"version":"3.54.5"},"reference-count":50,"publisher":"Emerald","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,2]]},"abstract":"\n Purpose<\/jats:title>\n Identifying potential risks is important in project risk management, especially in complex R&D projects that are commonly implemented as project portfolio (PP). However, most of the existing data-driven risk prediction and identification methods focus on individual projects and specific risks, and there is limited research on risk prediction and identification methods that also consider the similarity between risk propagation and projects. This study aims to provide a data-driven approach for risk identification in complex R&D projects, expanding the tools used for risk prediction.<\/jats:p>\n <\/jats:sec>\n \n Design\/methodology\/approach<\/jats:title>\n This study proposes a similarity measurement framework for R&D projects. A relational graph conventional network based on Node2vec, referred to as Node2vec-RGCN, is then utilized for data augmentation in the project risk association network, facilitating risk identification. Finally, the model is validated on real data.<\/jats:p>\n <\/jats:sec>\n \n Findings<\/jats:title>\n The test results indicate that the average accuracy of our model is 70.2%, the call rate is 73.4% and the AUC indicator is 71.9%, which enables better identification of potential risks and analysis of their possible sources.<\/jats:p>\n <\/jats:sec>\n \n Research limitations\/implications<\/jats:title>\n In this study, for the first time, link prediction based on graph neural networks is used in project risk networks to replace guesswork in risk identification by data-driven approach. However, there are still some limitations. The first limitation is that projects have a long life cycle, and risks may occur in different project phases. Therefore, to consider the dynamics of risks and project phases, the concept of time can be added to graph neural networks. The second limitation is that there can be complex interactions between different risks, and one risk can trigger the occurrence of other risks. However, in our study, risks were treated as independent and interactions between risks were not considered. In the future, risk identification can incorporate risk interactions to make the risk identification model more comprehensive.<\/jats:p>\n <\/jats:sec>\n \n Practical implications<\/jats:title>\n Specifically, it assists program managers in making decisions across three components: (1) During the project initiation phase, subsequent to the acquisition of data from the enterprise\u2019s risk register and the project\u2019s historical case base, it may, to a certain degree, supplant risk identification that relies on expert opinion, thereby facilitating the project in identifying potential risks and their fundamental characteristics. (2) During the project planning phase, it is also possible to conduct a risk assessment based on the risk scores generated through deep learning. This process enables the prioritization of risks and the allocation of risk response resources to address those of higher significance. (3) During the project execution phase, an updated list of potential risks and their prioritization may be generated by revising the model data according to newly generated dynamic risks. Finally, although our model is for R&D projects for risk prediction, except for the calculation of project similarity, which is mainly for R&D projects, all other data are standard features common to PP, so as long as the similarity calculation is done for projects in different industries for model adjustment, it can be applied to PP in various industries for risk identification and prediction, and it has strong transfer ability.<\/jats:p>\n <\/jats:sec>\n \n Social implications<\/jats:title>\n The contribution of this study is mainly in three aspects. First, our proposed model considers the risk propagation caused by the PIs. Most existing prediction studies for project risk identification and analysis ignore the impact of complex relationships between projects on risk prediction. Therefore, our model results make the decision-making more reliable and objective. Second, the model is an effective risk management tool based on ML that can assist managers in decision-making. This study uses a real data set from a company that can help project managers identify potential risks by using data-driven instead of guesswork with records of risks that have occurred in the past and project similarities.<\/jats:p>\n <\/jats:sec>\n \n Originality\/value<\/jats:title>\n This study develops a hybrid risk identification model that integrates project similarity, Node2vec and RGCN, applying graph neural networks to capture risk impacts from other projects in the risk propagation of project portfolios. The results of the study replace project decision-makers\u2019 guesses about potential risks with a data-driven approach.<\/jats:p>\n <\/jats:sec>","DOI":"10.1108\/jeim-01-2025-0041","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T02:13:51Z","timestamp":1751336031000},"page":"63-86","source":"Crossref","is-referenced-by-count":1,"title":["Using the data-augmented heterogeneous graph neural networks to identify risk of complex R&D projects considering project similarity"],"prefix":"10.1108","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9781-6967","authenticated-orcid":true,"given":"Zhongqiu","family":"Peng","sequence":"first","affiliation":[{"name":"Faculty of Management and Economics, Kunming University of Science and Technology , ,","place":["Kunming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingqi","family":"Zou","sequence":"additional","affiliation":[{"name":"Faculty of Management and Economics, Kunming University of Science and Technology , ,","place":["Kunming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Economics and Management, University of Science and Technology Beijing , ,","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2025,7,2]]},"reference":[{"issue":"2","key":"2026013100174197000_ref001","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1108\/ecam-06-2021-0555","article-title":"Project portfolio risk analysis with the consideration of project interdependencies","volume":"30","author":"Bai","year":"2023","journal-title":"Engineering Construction and Architectural Management"},{"issue":"2","key":"2026013100174197000_ref002","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1108\/ecam-01-2022-0010","article-title":"Modeling for external stakeholder risk assessment of project portfolios","volume":"31","author":"Bai","year":"2024","journal-title":"Engineering Construction and Architectural Management"},{"issue":"3","key":"2026013100174197000_ref003","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1108\/jeim-07-2022-0247","article-title":"GA-BP neural network modeling for project portfolio risk prediction","volume":"37","author":"Bai","year":"2024","journal-title":"Journal of Enterprise Information Management"},{"issue":"6","key":"2026013100174197000_ref004","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1016\/j.ipm.2011.11.001","article-title":"A three-phase method for patent classification","volume":"48","author":"Chen","year":"2012","journal-title":"Information Processing and Management"},{"issue":"4","key":"2026013100174197000_ref005","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.ijproman.2008.04.001","article-title":"A comprehensive model for selecting information system project under fuzzy environment","volume":"27","author":"Chen","year":"2009","journal-title":"International Journal of Project Management"},{"issue":"2","key":"2026013100174197000_ref006","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.ijpe.2005.03.009","article-title":"A fuzzy approach for supplier evaluation and selection in supply chain management","volume":"102","author":"Chen","year":"2006","journal-title":"International Journal of Production Economics"},{"issue":"8","key":"2026013100174197000_ref007","doi-asserted-by":"publisher","DOI":"10.1061\/jcemd4.coeng-13101","article-title":"Using machine learning to improve cost and duration prediction accuracy in green building projects","volume":"149","author":"Darko","year":"2023","journal-title":"Journal of Construction Engineering and Management"},{"issue":"8","key":"2026013100174197000_ref008","doi-asserted-by":"publisher","DOI":"10.1061\/jcemd4.coeng-13023","article-title":"Cost-weighted TF-IDF: a novel approach for measuring highway project similarity based on pay items\u2019 cost composition and term frequency","volume":"149","author":"Do","year":"2023","journal-title":"Journal of Construction Engineering and Management"},{"issue":"6","key":"2026013100174197000_ref009","doi-asserted-by":"publisher","first-page":"2870","DOI":"10.1016\/j.eswa.2014.11.034","article-title":"Generating project risk response strategies based on CBR: a case study","volume":"42","author":"Fan","year":"2015","journal-title":"Expert Systems with Applications"},{"key":"2026013100174197000_ref010","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2020.106497","article-title":"A risk prediction model for software project management based on similarity analysis of context histories","volume":"131","author":"Filippetto","year":"2021","journal-title":"Information and Software Technology"},{"issue":"11","key":"2026013100174197000_ref011","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1080\/01446190802468487","article-title":"Tools for selecting appropriate risk management techniques in the built environment","volume":"26","author":"Forbes","year":"2008","journal-title":"Construction Management and Economics"},{"key":"2026013100174197000_ref012","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1145\/2939672.2939754","article-title":"node2vec: scalable feature learning for networks","author":"Grover","year":"2016"},{"key":"2026013100174197000_ref013","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10479-023-05653-3","article-title":"A novel framework for risk management of software projects by integrating a new COPRAS method under cloud model and machine learning algorithms","volume":"338","author":"Haghighi","year":"2023","journal-title":"Annals of Operations Research"},{"issue":"8","key":"2026013100174197000_ref014","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)co.1943-7862.0002327","article-title":"A coupled genetic programming Monte Carlo simulation\u2013based model for cost overrun prediction of thermal power plant projects","volume":"148","author":"Islam","year":"2022","journal-title":"Journal of Construction Engineering and Management"},{"issue":"1","key":"2026013100174197000_ref015","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1061\/(asce)co.1943-7862.0000393","article-title":"Revised case-based reasoning model development based on multiple regression analysis for railroad bridge construction","volume":"138","author":"Kim","year":"2012","journal-title":"Journal of Construction Engineering and Management"},{"key":"2026013100174197000_ref016","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv preprint arXiv:1609.02907"},{"issue":"15","key":"2026013100174197000_ref017","doi-asserted-by":"publisher","first-page":"5596","DOI":"10.1080\/00207543.2022.2100841","article-title":"Towards knowledge graph reasoning for supply chain risk management using graph neural networks","volume":"62","author":"Kosasih","year":"2024","journal-title":"International Journal of Production Research"},{"key":"2026013100174197000_ref018","doi-asserted-by":"crossref","DOI":"10.1145\/3394486.3403179","article-title":"Competitive analysis for points of interest","author":"Li","year":"2020"},{"issue":"10","key":"2026013100174197000_ref019","doi-asserted-by":"publisher","DOI":"10.1061\/jcemd4.coeng-13168","article-title":"Construction duration estimation for airport terminals in China: case-based reasoning model considering case retrieval methods and case retention strategies","volume":"149","author":"Li","year":"2023","journal-title":"Journal of Construction Engineering and Management"},{"key":"2026013100174197000_ref020","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1016\/j.asoc.2016.09.022","article-title":"Distributionally robust fuzzy project portfolio optimization problem with interactive returns","volume":"56","author":"Liu","year":"2017","journal-title":"Applied Soft Computing"},{"key":"2026013100174197000_ref021","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"issue":"12","key":"2026013100174197000_ref022","doi-asserted-by":"publisher","DOI":"10.1061\/jcemd4.coeng-13437","article-title":"A data-driven recommendation system for construction safety risk assessment","volume":"149","author":"Mostofi","year":"2023","journal-title":"Journal of Construction Engineering and Management"},{"key":"2026013100174197000_ref023","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101752","article-title":"Identification of accident-injury type and bodypart factors from construction accident reports: a graph-based deep learning framework","volume":"54","author":"Pan","year":"2022","journal-title":"Advanced Engineering Informatics"},{"key":"2026013100174197000_ref024","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1016\/j.asoc.2014.11.042","article-title":"Fuzzy risk analysis using area and height based similarity measure on generalized trapezoidal fuzzy numbers and its application","volume":"28","author":"Patra","year":"2015","journal-title":"Applied Soft Computing"},{"key":"2026013100174197000_ref025","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1145\/2623330.2623732","article-title":"Deepwalk: online learning of social representations","author":"Perozzi","year":"2014"},{"issue":"9","key":"2026013100174197000_ref026","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)co.1943-7862.0001689","article-title":"Quantifying the similarity between different project types based on their pay item compositions: application to bundling","volume":"145","author":"Qiao","year":"2019","journal-title":"Journal of Construction Engineering and Management"},{"issue":"5","key":"2026013100174197000_ref027","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1108\/jkm-05-2017-0184","article-title":"Knowledge transfer between projects within project-based organizations: the project nature perspective","volume":"22","author":"Ren","year":"2018","journal-title":"Journal of Knowledge Management"},{"key":"2026013100174197000_ref028","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/978-3-319-93417-4_38","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018"},{"issue":"3","key":"2026013100174197000_ref029","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1016\/j.ejor.2021.03.063","article-title":"Practical application of reference class forecasting for cost and time estimations: identifying the properties of similarity","volume":"295","author":"Servranckx","year":"2021","journal-title":"European Journal of Operational Research"},{"issue":"4","key":"2026013100174197000_ref030","doi-asserted-by":"publisher","DOI":"10.1061\/jcemd4.coeng-12367","article-title":"Deep multilayer perceptron neural network for the prediction of Iranian dam project delay risks","volume":"149","author":"Shirazi","year":"2023","journal-title":"Journal of Construction Engineering and Management"},{"issue":"7","key":"2026013100174197000_ref031","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1177\/03611981221080129","article-title":"Mapping of state transportation agencies\u2019 practices and perceptions in project bundling","volume":"2676","author":"Shrestha","year":"2022","journal-title":"Transportation Research Record"},{"issue":"4","key":"2026013100174197000_ref032","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1109\/tcbb.2021.3070910","article-title":"Graph convolutional auto-encoders for predicting novel lncRNA-disease associations","volume":"19","author":"Silva","year":"2021","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics"},{"issue":"S1","key":"2026013100174197000_ref033","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1111\/jpim.12064","article-title":"Stratifying the development of product platforms: requirements for resources, organization, and management styles","volume":"30","author":"Sk\u00f6ld","year":"2013","journal-title":"Journal of Product Innovation Management"},{"issue":"13","key":"2026013100174197000_ref034","doi-asserted-by":"publisher","DOI":"10.3390\/su12135231","article-title":"Framework for risk identification of renewable energy projects using fuzzy case-based reasoning","volume":"12","author":"Somi","year":"2020","journal-title":"Sustainability"},{"key":"2026013100174197000_ref035","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2021.127572","article-title":"Developing a risk breakdown matrix for onshore wind farm projects using fuzzy case-based reasoning","volume":"311","author":"Somi","year":"2021","journal-title":"Journal of Cleaner Production"},{"issue":"20","key":"2026013100174197000_ref036","doi-asserted-by":"publisher","first-page":"23538","DOI":"10.1007\/s10489-023-04739-6","article-title":"Topological enhanced graph neural networks for semi-supervised node classification","volume":"53","author":"Song","year":"2023","journal-title":"Applied Intelligence"},{"key":"2026013100174197000_ref037","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/01969722.2024.2343988","article-title":"An optimal modified bidirectional generative adversarial network for security authentication in cloud environment","author":"Subramanian","year":"2024","journal-title":"Cybernetics and Systems"},{"issue":"1","key":"2026013100174197000_ref038","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1109\/tii.2022.3194659","article-title":"Separated graph neural networks for recommendation systems","volume":"19","author":"Sun","year":"2022","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"1","key":"2026013100174197000_ref039","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/1540-5885.1610003","article-title":"An empirical study of platform and derivative product development projects","volume":"16","author":"Tatikonda","year":"1999","journal-title":"Journal of Product Innovation Management"},{"key":"2026013100174197000_ref040","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv preprint arXiv:1710.10903"},{"key":"2026013100174197000_ref041","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/01969722.2024.2343985","article-title":"Development of modified ECC-based secured FoG-Assisted healthcare data management system in IoT-Enabled WSN","author":"Victoria","year":"2024","journal-title":"Cybernetics and Systems"},{"issue":"8","key":"2026013100174197000_ref042","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)co.1943-7862.0002124","article-title":"Data-driven prediction of contract failure of public-private partnership projects","volume":"147","author":"Wang","year":"2021","journal-title":"Journal of Construction Engineering and Management"},{"issue":"4","key":"2026013100174197000_ref043","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)co.1943-7862.0002253","article-title":"Auditing construction cost from an in-process perspective based on a Bayesian predictive model","volume":"148","author":"Wang","year":"2022","journal-title":"Journal of Construction Engineering and Management"},{"issue":"6","key":"2026013100174197000_ref044","doi-asserted-by":"publisher","first-page":"3353","DOI":"10.1109\/tcbb.2023.3247035","article-title":"Microbe-disease association prediction using RGCN through microbe-drug-disease network","volume":"20","author":"Wang","year":"2023","journal-title":"IEEE\/ACM Transactions on Computational Biology and Bioinformatics"},{"issue":"2","key":"2026013100174197000_ref045","first-page":"70","article-title":"Creating project plans to focus product development","volume":"70","author":"Wheelwright","year":"1992","journal-title":"Harvard Business Review"},{"key":"2026013100174197000_ref046","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114990","article-title":"Information security decisions of firms considering security risk interdependency","volume":"178","author":"Wu","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"2026013100174197000_ref047","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109626","article-title":"Risk assessment of utility tunnels through risk interaction-based deep learning","volume":"241","author":"Xue","year":"2024","journal-title":"Reliability Engineering and System Safety"},{"issue":"6","key":"2026013100174197000_ref048","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3646552","article-title":"Social behavior analysis in exclusive enterprise social networks by FastHAND","volume":"18","author":"Yang","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"issue":"2","key":"2026013100174197000_ref049","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3625101","article-title":"A multisource data fusion-based heterogeneous graph attention network for competitor prediction","volume":"18","author":"Ye","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"2026013100174197000_ref050","doi-asserted-by":"publisher","first-page":"7364","DOI":"10.1109\/tem.2023.3271991","article-title":"Project risk response decision making under uncertain project interdependencies","volume":"71","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Engineering Management"}],"container-title":["Journal of Enterprise Information Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/JEIM-01-2025-0041\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/jeim\/article-pdf\/39\/1\/63\/11211057\/jeim-01-2025-0041en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/jeim\/article-pdf\/39\/1\/63\/11211057\/jeim-01-2025-0041en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T05:17:49Z","timestamp":1769836669000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/jeim\/article\/39\/1\/63\/1268769\/Using-the-data-augmented-heterogeneous-graph"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2,2]]}},"URL":"https:\/\/doi.org\/10.1108\/jeim-01-2025-0041","relation":{},"ISSN":["1741-0398","1758-7409"],"issn-type":[{"value":"1741-0398","type":"print"},{"value":"1758-7409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,2]]}}}