{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:54:19Z","timestamp":1771955659829,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>We developed a methodology for the neural network boosting of logistic regression aimed at learning an additional model structure from the data. In particular, we constructed two classes of neural network-based models: shallow\u2013dense neural networks with one hidden layer and deep neural networks with multiple hidden layers. Furthermore, several advanced approaches were explored, including the combined actuarial neural network approach, embeddings and transfer learning. The model training was achieved by minimizing either the deviance or the cross-entropy loss functions, leading to fourteen neural network-based models in total. For illustrative purposes, logistic regression and the alternative neural network-based models we propose are employed for a binary classification exercise concerning the occurrence of at least one claim in a French motor third-party insurance portfolio. Finally, the model interpretability issue was addressed via the local interpretable model-agnostic explanations approach.<\/jats:p>","DOI":"10.3390\/a16020099","type":"journal-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T05:51:06Z","timestamp":1676008266000},"page":"99","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Enhancing Logistic Regression Using Neural Networks for Classification in Actuarial Learning"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4072-1454","authenticated-orcid":false,"given":"George","family":"Tzougas","sequence":"first","affiliation":[{"name":"Department of Actuarial Mathematics and Statistics, School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UK"}]},{"given":"Konstantin","family":"Kutzkov","sequence":"additional","affiliation":[{"name":"Teva Pharmaceuticals, 1407 Sofia, Bulgaria"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Parodi, P. (2014). Pricing in General Insurance, CRC Press.","DOI":"10.1201\/b17525"},{"key":"ref_2","unstructured":"W\u00fcthrich, M.V., Buser, C., and Data Analytics for Non-Life Insurance Pricing (2023, January 30). Swiss Finance Institute Research Paper 2020. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=2870308."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1017\/S1748499520000238","article-title":"AI in actuarial science\u2014A review of recent advances\u2014Part 1","volume":"15","author":"Richman","year":"2020","journal-title":"Ann. Actuar. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1017\/S174849952000024X","article-title":"AI in actuarial science\u2014A review of recent advances\u2014Part 2","volume":"15","author":"Richman","year":"2020","journal-title":"Ann. Actuar. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/asb.2018.42","article-title":"Yes, we CANN!","volume":"49","author":"Merz","year":"2019","journal-title":"ASTIN Bull. J. IAA"},{"key":"ref_6","unstructured":"Schelldorfer, J., and W\u00fcthrich, M.V. (2023, January 30). Nesting Classical Actuarial Models into Neural Networks. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3320525."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1515\/demo-2018-0022","article-title":"Predictive analytics of insurance claims using multivariate decision trees","volume":"6","author":"Quan","year":"2018","journal-title":"Depend. Model."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Gabrielli, A., and V W\u00fcthrich, M. (2018). An individual claims history simulation machine. Risks, 6.","DOI":"10.3390\/risks6020029"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1080\/07350015.2016.1200981","article-title":"Insurance premium prediction via gradient tree-boosted Tweedie compound Poisson models","volume":"36","author":"Yang","year":"2018","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1080\/10920277.2018.1431131","article-title":"Delta boosting machine with application to general insurance","volume":"22","author":"Lee","year":"2018","journal-title":"N. Am. Actuar. J."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1007\/s13385-018-0184-4","article-title":"Neural networks applied to chain\u2013ladder reserving","volume":"8","year":"2018","journal-title":"Eur. Actuar. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1080\/03461238.2018.1428681","article-title":"Machine learning in individual claims reserving","volume":"2018","year":"2018","journal-title":"Scand. Actuar. J."},{"key":"ref_13","unstructured":"Richman, R., von Rummell, N., and W\u00fcthrich, M.V. (2023, January 30). Believing the Bot-Model Risk in the Era of Deep Learning. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3444833."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/s13385-019-00209-x","article-title":"Insurance: Models, digitalization, and data science","volume":"9","author":"Albrecher","year":"2019","journal-title":"Eur. Actuar. J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Trufin, J., Denuit, M., and Hainaut, D. (2019). Effective Statistical Learning Methods for Actuaries\u2014Tree-Based Methods, Springer.","DOI":"10.1007\/978-3-030-25820-7"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1017\/asb.2019.33","article-title":"A neural network boosted double overdispersed Poisson claims reserving model","volume":"50","author":"Gabrielli","year":"2020","journal-title":"ASTIN Bull. J. IAA"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1017\/asb.2019.12","article-title":"A tree-based algorithm adapted to microlevel reserving and long development claims","volume":"49","author":"Lopez","year":"2019","journal-title":"ASTIN Bull. J. IAA"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"De Felice, M., and Moriconi, F. (2019). Claim watching and individual claims reserving using classification and regression trees. Risks, 7.","DOI":"10.3390\/risks7040102"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1002\/asmb.2455","article-title":"A machine learning approach for individual claims reserving in insurance","volume":"35","author":"Baudry","year":"2019","journal-title":"Appl. Stoch. Model. Bus. Ind."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3390\/risks7030079","article-title":"Individual loss reserving using a gradient boosting-based approach","volume":"7","author":"Duval","year":"2019","journal-title":"Risks"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Gao, G., and W\u00fcthrich, M.V. (2019). Convolutional neural network classification of telematics car driving data. Risks, 7.","DOI":"10.3390\/risks7010006"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1002\/asmb.2543","article-title":"Machine learning applications in nonlife insurance","volume":"36","author":"Grize","year":"2020","journal-title":"Appl. Stoch. Model. Bus. Ind."},{"key":"ref_23","unstructured":"Noll, A., Salzmann, R., and W\u00fcthrich, M.V. (2023, January 30). Case Study: French Motor Third-Party Liability Claims. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3164764."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"5507","DOI":"10.1080\/03610918.2020.1772302","article-title":"Tweedie gradient boosting for extremely unbalanced zero-inflated data","volume":"51","author":"Zhou","year":"2020","journal-title":"Commun. Stat.-Simul. Comput."},{"key":"ref_25","first-page":"568","article-title":"Use of optimized Fuzzy C-Means clustering and supervised classifiers for automobile insurance fraud detection","volume":"32","author":"Subudhi","year":"2020","journal-title":"J. King Saud-Univ.-Comput. Inf. Sci."},{"key":"ref_26","first-page":"255","article-title":"Boosting insights in insurance tariff plans with tree-based machine learning methods","volume":"25","author":"Antonio","year":"2020","journal-title":"N. Am. Actuar. J."},{"key":"ref_27","first-page":"3428","article-title":"A proposed model to predict auto insurance claims using machine learning techniques","volume":"98","author":"Abdelhadi","year":"2020","journal-title":"J. Theor. Appl. Inf. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.51483\/IJDSBDA.1.1.2021.1-19","article-title":"Algorithms in future insurance markets","volume":"1","author":"Koshiyama","year":"2021","journal-title":"Int. J. Data Sci. Big Data Anal."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hanafy, M., and Ming, R. (2021). Machine learning approaches for auto insurance big data. Risks, 9.","DOI":"10.3390\/risks9020042"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s10994-021-05957-0","article-title":"Boosting Poisson regression models with telematics car driving data","volume":"111","author":"Gao","year":"2021","journal-title":"Mach. Learn."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/03461238.2021.1921836","article-title":"Collective reserving using individual claims data","volume":"2022","author":"Delong","year":"2021","journal-title":"Scand. Actuar. J."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1080\/03461238.2020.1793218","article-title":"Individual reserving and nonparametric estimation of claim amounts subject to large reporting delays","volume":"2021","author":"Lopez","year":"2021","journal-title":"Scand. Actuar. J."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1007\/s13385-021-00271-4","article-title":"An individual claims reserving model for reported claims","volume":"11","author":"Gabrielli","year":"2021","journal-title":"Eur. Actuar. J."},{"key":"ref_34","unstructured":"Blier-Wong, C., Baillargeon, J.T., Cossette, H., Lamontagne, L., and Marceau, E. (2021). Rethinking Representations in P&C Actuarial Science with Deep Neural Networks. arXiv."},{"key":"ref_35","first-page":"4","article-title":"Machine learning in P&C insurance: A review for pricing and reserving","volume":"9","author":"Cossette","year":"2021","journal-title":"Risks"},{"key":"ref_36","first-page":"1","article-title":"The balance property in neural network modelling","volume":"6","year":"2021","journal-title":"Stat. Theory Relat. Fields"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"W\u00fcthrich, M.V., and Merz, M. (2023). Statistical Foundations of Actuarial Learning and Its Applications, Springer Nature.","DOI":"10.1007\/978-3-031-12409-9"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1214\/ss\/1009213726","article-title":"Statistical modeling: The two cultures (with comments and a rejoinder by the author)","volume":"16","author":"Breiman","year":"2001","journal-title":"Stat. Sci."},{"key":"ref_39","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","unstructured":"Bengio, Y., Schwenk, H., Sen\u00e9cal, J.S., Morin, F., and Gauvain, J.L. (2006). Innovationsin Machine Learning, Springer."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_42","unstructured":"Guo, C., and Berkhahn, F. (2016). Entity embeddings of categorical variables. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1080\/03461238.2020.1867232","article-title":"Time-series forecasting of mortality rates using deep learning","volume":"2021","author":"Perla","year":"2021","journal-title":"Scand. Actuar. J."},{"key":"ref_44","unstructured":"W\u00fcthrich, M.V. (2023, January 30). From Generalized Linear Models to Neural Networks, and Back. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3491790."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Richman, R., and V W\u00fcthrich, M. (2020). Nagging predictors. Risks, 8.","DOI":"10.3390\/risks8030083"},{"key":"ref_46","first-page":"1","article-title":"Bias regularization in neural network models for general insurance pricing","volume":"10","year":"2019","journal-title":"Eur. Actuar. J."},{"key":"ref_47","unstructured":"Goodfellow, I.J., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_48","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Charpentier, A. (2014). Computational Actuarial Science with R, CRC Press.","DOI":"10.1201\/b17230"},{"key":"ref_50","unstructured":"Ferrario, A., Noll, A., and W\u00fcthrich, M.V. (2023, January 30). Insights from Inside Neural Networks. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3226852."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7\u201313). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_52","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/2\/99\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:29:24Z","timestamp":1760120964000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/2\/99"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,9]]},"references-count":53,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["a16020099"],"URL":"https:\/\/doi.org\/10.3390\/a16020099","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,9]]}}}