{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:52:22Z","timestamp":1787925142420,"version":"build-2784847793"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Comput Soc Sc"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Covert or dark networks, such as those formed by organized crime or illicit alliances, pose unique challenges for link prediction research due to their inherent secrecy and data incompleteness. In this study, we compare a suite of advanced methods for inferring missing links in covert networks, including classical node similarity indices, graph embedding approaches, and GNN-based methods. We evaluate them on two real-world datasets: the Lantia dataset (a 2021 network of alliances between criminal organizations) and the 2020 Bacrim dataset (an open dataset on alliances among Mexican criminal groups in 2020). Our experiments focus on how these algorithms handle missing or partially observed links, a common reality in covert networks. Performance is measured using Area Under the ROC Curve (AUC) and F1 scores. Although classical similarity measures and embedding algorithms offer meaningful predictions, GNN-based models, particularly the Graph Convolutional Network, consistently achieve near-perfect AUC and F1 scores. These results highlight that learning from the broader graph topology via GNNs can effectively uncover hidden ties in incomplete and inherently noisy covert network data. Our findings provide practical guidance for researchers, analysts, and policymakers looking to identify future or missing alliances in large, fragmented, and illicit networks.<\/jats:p>","DOI":"10.1007\/s42001-025-00429-0","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T08:53:43Z","timestamp":1758099223000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Uncovering hidden alliances in organized crime networks with machine learning: from node similarity to graph neural networks"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0566-4060","authenticated-orcid":false,"given":"Oscar","family":"Contreras-Velasco","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan P.","family":"Jones","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel Weisz","family":"Argomedo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John P.","family":"Sullivan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Callaghan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"issue":"3","key":"429_CR1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s12117-017-9301-z","volume":"21","author":"LH Atuesta","year":"2018","unstructured":"Atuesta, L. H., & P\u00e9rez-D\u00e1vila, Y. S. (2018). Fragmentation and cooperation: The evolution of organized crime in Mexico. Trends in Organized Crime, 21(3), 235\u2013261.","journal-title":"Trends in Organized Crime"},{"key":"429_CR2","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1126\/science.1173299","volume":"325","author":"A-L Barab\u00e1si","year":"2009","unstructured":"Barab\u00e1si, A.-L. (2009). Scale-free networks: A decade and beyond. Science, 325, 412.","journal-title":"Science"},{"issue":"5","key":"429_CR3","first-page":"1277","volume":"98","author":"E Berman","year":"2018","unstructured":"Berman, E. (2018). A government of laws and not of machines. Boston University Law Review, 98(5), 1277\u20131356.","journal-title":"Boston University Law Review"},{"key":"429_CR4","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.socnet.2021.01.006","volume":"66","author":"D Bright","year":"2021","unstructured":"Bright, D., Brewer, R., & Morselli, C. (2021). Using social network analysis to study crime: Navigating the challenges of criminal justice records. Social Networks, 66, 50\u201364.","journal-title":"Social Networks"},{"issue":"2","key":"429_CR5","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10611-011-9336-z","volume":"57","author":"DA Bright","year":"2012","unstructured":"Bright, D. A., Hughes, C. E., & Chalmers, J. (2012). Illuminating dark networks: A social network analysis of an Australian drug trafficking syndicate. Crime, Law and Social Change, 57(2), 151\u2013176.","journal-title":"Crime, Law and Social Change"},{"key":"429_CR6","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1038\/s41467-019-08746-5","volume":"10","author":"AD Broido","year":"2019","unstructured":"Broido, A. D., & Clauset, A. (2019). Scale-free networks are rare. Nature Communications, 10, 1017.","journal-title":"Nature Communications"},{"key":"429_CR7","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/S0191-3085(00)22009-1","volume":"22","author":"RS Burt","year":"2000","unstructured":"Burt, R. S. (2000). The network structure of social capital. Research in Organizational Behavior, 22, 345\u2013423.","journal-title":"Research in Organizational Behavior"},{"issue":"1","key":"429_CR8","first-page":"11","volume":"66","author":"P Campana","year":"2016","unstructured":"Campana, P. (2016). Explaining criminal networks: Strategies and models in non-state actors research. Crime, Law and Social Change, 66(1), 11\u201332.","journal-title":"Crime, Law and Social Change"},{"key":"429_CR9","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.socnet.2020.03.002","volume":"69","author":"P Campana","year":"2022","unstructured":"Campana, P., & Varese, F. (2022). Studying organized crime networks: Data sources, boundaries and the limits of structural measures. Social Networks, 69, 149\u2013159.","journal-title":"Social Networks"},{"issue":"4","key":"429_CR10","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1137\/070710111","volume":"51","author":"A Clauset","year":"2009","unstructured":"Clauset, A., Shalizi, C. R., & Newman, M. E. J. (2009). Power-law distributions in empirical data. SIAM Review, 51(4), 661\u2013703.","journal-title":"SIAM Review"},{"key":"429_CR11","doi-asserted-by":"publisher","first-page":"S95","DOI":"10.1086\/228943","volume":"94","author":"JS Coleman","year":"1988","unstructured":"Coleman, J. S. (1988). Social capital in the creation of human capital. The American Journal of Sociology, 94, S95\u2013S120.","journal-title":"The American Journal of Sociology"},{"key":"429_CR12","unstructured":"Contreras,\u00a0V. O. (2023). Unintended consequences of state action: How the kingpin strategy transformed the structure of violence in Mexico\u2019s organized crime. Trends in Organized Crime."},{"key":"429_CR13","unstructured":"Contreras\u00a0V. O., Jones, N. P., Weisz\u00a0Argomedo, D., Sullivan, J.\u00a0P., & Callaghan, C. (2023). The use of similarity-based algorithms to predict links in Mexican criminal networks. Research paper, Rice University\u2019s Baker Institute."},{"issue":"5","key":"429_CR14","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1109\/TKDE.2018.2849727","volume":"31","author":"P Cui","year":"2018","unstructured":"Cui, P., Wang, X., Pei, J., & Zhu, W. (2018). A survey on network embedding. IEEE Transactions on Knowledge and Data Engineering, 31(5), 833\u2013852.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"429_CR15","unstructured":"Cunningham, D., Everton, S., & Murphy, P. (2016). Understanding Dark Networks: A Strategic Framework for the Use of Social Network Analysis. Rowman and Littlefield."},{"issue":"32","key":"429_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3310\/hsdr02320","volume":"2","author":"G Currie","year":"2014","unstructured":"Currie, G., Burgess, N., White, L., Lockett, A., Gladman, J., & Waring, J. (2014). A qualitative study of the knowledge-brokering role of middle-level managers in service innovation: Managing the translation gap in patient safety for older persons\u2019 care. Health Services and Delivery Research, 2(32), 1.","journal-title":"Health Services and Delivery Research"},{"key":"429_CR17","doi-asserted-by":"crossref","unstructured":"Duijn, P. A. C., & Klerks, P.\u00a0P. H.\u00a0M. (2014). Social network analysis applied to criminal networks: Recent developments in dutch law enforcement. In Networks and Network Analysis for Defence and Security, pages 121\u2013159. Springer.","DOI":"10.1007\/978-3-319-04147-6_6"},{"key":"429_CR18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139136877","volume-title":"Disrupting Dark Networks","author":"SF Everton","year":"2012","unstructured":"Everton, S. F. (2012). Disrupting Dark Networks. Cambridge University Press."},{"issue":"3","key":"429_CR19","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/0378-8733(78)90021-7","volume":"1","author":"L Freeman","year":"1979","unstructured":"Freeman, L. (1979). Centrality in social networks conceptual clarification. Social Networks, 1(3), 215\u2013329.","journal-title":"Social Networks"},{"key":"429_CR20","unstructured":"Gambetta, D. (1993). The Sicilian Mafia: The Business of Private Protection. Harvard University Press."},{"key":"429_CR21","volume-title":"Analyzing the Social Web","author":"J Golbeck","year":"2013","unstructured":"Golbeck, J. (2013). Analyzing the Social Web. Elsevier."},{"key":"429_CR22","doi-asserted-by":"crossref","unstructured":"Grover, A., & Leskovec, J. (2016). node2vec: Scalable feature learning for networks. In KDD \u201916.","DOI":"10.1145\/2939672.2939754"},{"key":"429_CR23","unstructured":"Hamilton, W. L., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. In NIPS \u201917."},{"key":"429_CR24","unstructured":"Jones, N. P., Chindea, I., Weisz\u00a0Argomedo, D., & Sullivan, J.\u00a0P. (2022). Mexico\u2019s 2021 dark network alliance structure: An exploratory social network analysis of lantia consultores\u2019 illicit network alliance and subgroup data. Working paper, Rice University\u2019s Baker Institute."},{"key":"429_CR25","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s12117-018-9352-9","volume":"23","author":"NP Jones","year":"2018","unstructured":"Jones, N. P., Dittmann, W. L., Wu, J., & Reese, T. (2018). A mixed-methods social network analysis of a cross-border drug network: The Fernando Sanchez organization. Trends in Organized Crime, 23, 154\u2013182.","journal-title":"Trends in Organized Crime"},{"issue":"2","key":"429_CR26","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1080\/10485252.2015.1010532","volume":"27","author":"Y Jung","year":"2015","unstructured":"Jung, Y., & Hu, J. (2015). A k-fold averaging cross-validation procedure. Journal of Nonparametric Statistics, 27(2), 167\u2013179. Epub 2015 Feb 26.","journal-title":"Journal of Nonparametric Statistics"},{"key":"429_CR27","unstructured":"Kipf, T.\u00a0N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"issue":"2","key":"429_CR28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.73.026120","volume":"73","author":"EA Leicht","year":"2006","unstructured":"Leicht, E. A., Holme, P., & Newman, M. E. J. (2006). Vertex similarity in networks. Physical Review E, 73(2), Article 026120.","journal-title":"Physical Review E"},{"issue":"7","key":"429_CR29","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1002\/asi.20591","volume":"58","author":"D Liben-Nowell","year":"2007","unstructured":"Liben-Nowell, D., & Kleinberg, J. (2007). The link-prediction problem for social networks. Journal of the American Society for Information Science and Technology, 58(7), 1019\u20131031.","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"10","key":"429_CR30","first-page":"1202","volume":"33","author":"M Lim","year":"2021","unstructured":"Lim, M., Abdullah, A., & Jhanjhi, N. Z. (2021). Performance optimization of criminal network hidden link prediction model with deep reinforced learning. Journal of King Saud University, 33(10), 1202\u20131210.","journal-title":"Journal of King Saud University"},{"issue":"2","key":"429_CR31","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.socnet.2008.12.003","volume":"31","author":"R Lindelauf","year":"2009","unstructured":"Lindelauf, R., Borm, P., & Hamers, H. (2009). The influence of secrecy on the communication structure of covert networks. Social Networks, 31(2), 126\u2013137.","journal-title":"Social Networks"},{"issue":"1","key":"429_CR32","doi-asserted-by":"publisher","first-page":"15746","DOI":"10.1038\/s41598-022-20025-w","volume":"12","author":"DD Lopes","year":"2022","unstructured":"Lopes, D. D., da Cunha, B. R., Martins, \u00c1. F., Gon\u00e7alves, S., Lenzi, E. K., Hanley, Q. S., Perc, M., & Ribeiro, H. V. (2022). Machine learning for partners in crime: Uncovering links and predicting criminal associations in networks. Scientific Reports, 12(1), 15746.","journal-title":"Scientific Reports"},{"key":"429_CR33","doi-asserted-by":"publisher","first-page":"2823","DOI":"10.1007\/s13042-018-00906-1","volume":"10","author":"J Mart\u00ednez Torres","year":"2019","unstructured":"Mart\u00ednez Torres, J., Iglesias Comesa\u00f1a, C., & Garc\u00eda-Nieto, P. J. (2019). Machine learning techniques applied to cybersecurity. Review. International Journal of Machine Learning and Cybernetics, 10, 2823\u20132836.","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"87","key":"429_CR34","first-page":"1","volume":"21","author":"X Meng","year":"2020","unstructured":"Meng, X. (2020). Node embedding for link prediction in social networks. Journal of Machine Learning Research, 21(87), 1\u201321.","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"429_CR35","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/10967490600899747","volume":"9","author":"H Brinton Milward","year":"2006","unstructured":"Brinton Milward, H., & Raab, J. (2006). Dark networks as organizational problems: Elements of a theory. International Public Management Journal, 9(3), 333\u2013360.","journal-title":"International Public Management Journal"},{"key":"429_CR36","doi-asserted-by":"crossref","unstructured":"Mohammed, M., Khan, M. B., & Bashier, E. B. M. B. (2016). Machine Learning. CRC Press.","DOI":"10.1201\/9781315371658"},{"issue":"1","key":"429_CR37","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.socnet.2006.05.001","volume":"29","author":"C Morselli","year":"2007","unstructured":"Morselli, C., Gigu\u00e8re, C., & Petit, K. (2007). The efficiency\/security trade-off in criminal networks. Social Networks, 29(1), 143\u2013153.","journal-title":"Social Networks"},{"key":"429_CR38","doi-asserted-by":"crossref","unstructured":"Morselli, C. (2009). Inside Criminal Networks. Springer.","DOI":"10.1007\/978-0-387-09526-4"},{"issue":"2","key":"429_CR39","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1257\/jep.31.2.87","volume":"31","author":"S Mullainathan","year":"2017","unstructured":"Mullainathan, S., & Spiess, J. (2017). Machine learning: An applied econometric approach. Journal of Economic Perspectives, 31(2), 87\u2013106.","journal-title":"Journal of Economic Perspectives"},{"key":"429_CR40","unstructured":"Newman, M.\u00a0E.\u00a0J. (2010). Networks: An Introduction. Oxford University Press."},{"key":"429_CR41","doi-asserted-by":"crossref","unstructured":"Perozzi, B., Al-Rfou, R., & Skiena, S. (2014). Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.","DOI":"10.1145\/2623330.2623732"},{"issue":"2","key":"429_CR42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.67.026112","volume":"67","author":"E Ravasz","year":"2003","unstructured":"Ravasz, E., & Barab\u00e1si, A.-L. (2003). Hierarchical organization in complex networks. Physical Review E, 67(2), Article 026112.","journal-title":"Physical Review E"},{"key":"429_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2023.113579","volume":"172","author":"HV Ribeiro","year":"2023","unstructured":"Ribeiro, H. V., Lopes, D. D., Pessa, A. A. B., Martins, \u00c1. F., da Cunha, B. R., Gon\u00e7alves, S., Lenzi, E. K., Hanley, Q. S., & Perc, M. (2023). Deep learning criminal networks. Chaos, Solitons & Fractals, 172, Article 113579.","journal-title":"Chaos, Solitons & Fractals"},{"issue":"3","key":"429_CR44","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0378-8733(91)90008-H","volume":"13","author":"MK Sparrow","year":"1991","unstructured":"Sparrow, M. K. (1991). The application of network analysis to criminal intelligence: An assessment of the prospects. Social Networks, 13(3), 251\u2013274.","journal-title":"Social Networks"},{"key":"429_CR45","unstructured":"Sullivan, J. P. (2012). From drug wars to criminal insurgency: Mexican cartels, criminal enclaves and criminal insurgency in mexico and central America. implications for global security. Working Paper No. 9. Paris: Fondation Maison des sciences de l\u2019homme."},{"key":"429_CR46","unstructured":"Sullivan, J. P. (2019). Criminal enclaves: When gangs, cartels or kingpins try to take control. Stratfor Threat Lens."},{"issue":"1","key":"429_CR47","doi-asserted-by":"publisher","first-page":"51","DOI":"10.5038\/1944-0472.16.1.2049","volume":"16","author":"JP Sullivan","year":"2023","unstructured":"Sullivan, J. P. (2023). The information age: Transnational organized crime, networks, and illicit markets. Journal of Strategic Security, 16(1), 51\u201371.","journal-title":"Journal of Strategic Security"},{"key":"429_CR48","unstructured":"Sullivan, J. P., & Elkus, A. (2008). State of siege: Mexico\u2019s criminal insurgency. Small Wars Journal."},{"key":"429_CR49","unstructured":"Surden, H. (2023). Values embedded in legal artificial intelligence. U of Colorado Law Legal Studies."},{"key":"429_CR50","doi-asserted-by":"crossref","unstructured":"Tilly, C. (1985). War making and state making as organized crime. In P.\u00a0Evans, D.\u00a0Rueschemeyer, & T.\u00a0Skocpol, editors, Bringing the State Back In, pp 169\u2013191. Cambridge University Press.","DOI":"10.1017\/CBO9780511628283.008"},{"key":"429_CR51","unstructured":"Veli\u010dkovi\u0107 P., et\u00a0al. (2018). Graph attention networks. In ICLR \u201918."},{"issue":"5","key":"429_CR52","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3390\/info10050172","volume":"10","author":"W Wang","year":"2019","unstructured":"Wang, W., Ling, W., Huang, Y., Wang, H., & Zhu, R. (2019). Link prediction based on deep convolutional neural network. Information, 10(5), 172.","journal-title":"Information"},{"key":"429_CR53","doi-asserted-by":"crossref","unstructured":"Wasserman, S., & Faust, K. (1994). Social Network Analysis: Methods and Applications. Cambridge University Press.","DOI":"10.1017\/CBO9780511815478"},{"issue":"3","key":"429_CR54","first-page":"76","volume":"55","author":"J Xu","year":"2012","unstructured":"Xu, J., & Chen, H. (2012). Criminal network analysis and visualization. Communications of the ACM, 55(3), 76\u201384.","journal-title":"Communications of the ACM"},{"key":"429_CR55","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1140\/epjb\/e2009-00335-8","volume":"71","author":"T Zhou","year":"2009","unstructured":"Zhou, T., L\u00fc, L., & Zhang, Y.-C. (2009). Predicting missing links via local information. The European Physical Journal B, 71, 623\u2013630.","journal-title":"The European Physical Journal B"}],"container-title":["Journal of Computational Social Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42001-025-00429-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42001-025-00429-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42001-025-00429-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T04:13:41Z","timestamp":1764389621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42001-025-00429-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["429"],"URL":"https:\/\/doi.org\/10.1007\/s42001-025-00429-0","relation":{},"ISSN":["2432-2717","2432-2725"],"issn-type":[{"value":"2432-2717","type":"print"},{"value":"2432-2725","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"15 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"101"}}