Optimizing Claims Risk Prediction for Commercial Health Insurance Users by Combining the DeepFM Algorithm
Main Article Content
Abstract
Commercial health insurance claims prediction is challenged by label delay, temporal distribution drift, and complex high-dimensional feature interactions, which reduce the reliability and stability of conventional risk assessment models. To address these issues, this study proposes a DeepFM-based dual-correction framework that integrates inverse probability weighting, symmetric cross-entropy loss, temporal adversarial learning, and maximum mean discrepancy constraints to jointly mitigate label lag and distribution drift. A shared embedding architecture is employed to capture both low-order and high-order feature interactions, while an adaptive gated fusion strategy balances the contributions of the FM and DNN branches for robust probability estimation. Experimental results demonstrate that the proposed model achieves an AUC of 0.853 under standard conditions and maintains competitive performance under severe label delay and temporal drift scenarios, with limited degradation in calibration metrics. The framework significantly enhances prediction accuracy, robustness, and probability consistency for commercial health insurance claims risk assessment. Furthermore, its capability for modeling dynamic feature interactions and time-varying data distributions provides methodological insights for intelligent signal interpretation and adaptive prediction tasks in electromagnetic wave propagation environments and related antenna data analysis applications.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
J. Wu, J. Qiao, S. Nicholas, Y. Liu, and E. Maitland, “The challenge of healthcare big data to China’s commercial health insurance industry: Evaluation and recommendations,” BMC Health Services Research, pp. 22(1), 2022, doi: 10.1186/s12913-022-08574-2.
L. Ajijola, O. Akindipe, A. Lawal, O. Afuwape, and P. Olaleye, “Evaluation of the effectiveness and accuracy of predictive modeling techniques on healthcare claims in Nigeria,” Nigerian Journal of Management Studies, vol. 27, no. 1, pp. 175-199, 2025, [Online]. Available: https://njms.unilag.edu.ng/article/view/2568.
A. Pnevmatikakis, S. Kanavos, G. Matikas, K. Kostopoulou, A. Cesario, and S. Kyriazakos, “Risk assessment for personalized health insurance based on real-world data,” Risks, vol. 9, no. 3, pp. 46, 2021, doi: 10.3390/risks9030046.
X. Liu, Y. Xiao, J. Chen, P. Ma, and W. Zhu, “Analysis of data exchange technology between medical and health insurance institutions from the perspective of patent measurement,” Journal of Medical Informatics, vol. 45, no. 5, pp. 59-64, 2024, doi: 10.3969/j.issn.1673-6036.2024.05.010.
G. Patra, C. Kuraku, S. Konkimalla, V. Boddapati, M. Sarisa, and M. Reddy, “An analysis and prediction of health insurance costs using machine learning-based regressor techniques,” Journal of Data Analysis and Information Processing, vol. 12, no. 4, pp. 581-596, 2024, doi: 10.4236/jdaip.2024.124031.
A. Abuzaid and I. Alkrunz, “Forecasting next year’s health insurance claims using machine learning models,” JITSI: Jurnal Ilmiah Teknologi Sistem Informasi, vol. 6, no. 2, pp. 120-131, 2025, doi: 10.62527/jitsi.6.2.443.
S. Moon, D. Jagadeesh, S. Sultana, and M. Prasanna, “AI-driven machine learning model for health insurance claim prediction,” International Journal of Communication Networks and Information Security, vol. 17, no. 3, pp. 900-906, 2025, [Online]. Available: https://www.proquest.com/scholarly-journals/ai-driven-machine-learning-model-health-insurance/docview/3232790510/se-2.
K. Kaushik, A. Bhardwaj, A. Dwivedi, and R. Singh, “Machine learning-based regression framework to predict health insurance premiums,” International Journal of Environmental Research and Public Health, vol. 19, no. 13, pp. 7898, 2022, doi: 10.3390/ijerph19137898.
A. Alam and V. Prybutok, “Use of responsible artificial intelligence to predict health insurance claims in the USA using machine learning algorithms,” Exploration of Digital Health Technologies, vol. 2, no. 1, pp. 30-45, 2024, doi: 10.37349/edht.2024.00009.
V. Thakre, R. Poul, and A. Sawarkar, “Predictive precision: Unraveling health insurance claim patterns with logistic regression and decision trees,” Cureus Journal of Computer Science, vol. 3, no. 1, pp. 1-10, 2025, doi: 10.7759/s44389-025-03010-y.
S. Devaguptam, S. Gorti, T. Akshaya, and S. Kamath, “Automated health insurance processing framework with intelligent fraud detection, risk classification and premium prediction,” SN Computer Science, pp. 5(5), 2024, doi: 10.1007/s42979-024-02801-9.
V. Nalluri, J. Chang, L. Chen, and J. Chen, “Building prediction models and discovering important factors of health insurance fraud using machine learning methods,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 7, pp. 9607-9619, 2023, doi: 10.1007/s12652-023-04633-6.
S. Anam, M. Putra, Z. Fitriah, I. Yanti, N. Hidayat, and D. Mahanani, “Health claim insurance prediction using support vector machine with particle swarm optimization,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 17, no. 2, pp. 797-806, 2023, doi: 10.30598/barekengvol17iss2pp0797-0806.
Q. Wang, M. Zhang, Y. Zhang, J. Zhong, and V. Sheng, “Location-based deep factorization machine model for service recommendation,” Applied Intelligence, vol. 52, no. 9, pp. 9899-9918, 2022, doi: 10.1007/s10489-021-02998-9.
R. Madani, A. Ez-Zahout, F. Omary, and A. Chedmi, “Advancing context-aware recommender systems: A deep context-based factorization machines approach,” International Journal of Computing and Digital Systems, vol. 15, no. 1, pp. 353-363, 2024, doi: 10.12785/ijcds/160128.
L. Chen and H. Shi, “DexDeepFM: ensemble diversity enhanced extreme deep factorization machine model,” ACM Transactions on Knowledge Discovery from Data, vol. 16, no. 5, pp. 1-17, 2022, doi: 10.1145/3505272.
H. Yu and J. Yin, “Deep reinforcement factorization machines: A deep reinforcement learning model with random exploration strategy and high deployment efficiency,” Applied Sciences, vol. 12, no. 11, pp. 5314, 2022, doi: 10.3390/app12115314.
L. Ren, T. Wang, Y. Laili, and L. Zhang, “A data-driven self-supervised LSTM-DeepFM model for industrial soft sensor,” IEEE Transactions on Industrial Informatics, vol. 18, no. 9, pp. 5859-5869, 2022, doi: 10.1109/TII.2021.3131471.
E. Merza and N. Mohammed, “Fast ways to detect outliers,” Journal of Techniques, vol. 3, no. 1, pp. 66-73, 2021, doi: 10.51173/jt.v3i1.287.
Q. Zhou and N. Zhou, “Neural network-enhanced pairwise bilinear factorization machines,” Computer Engineering & Science, vol. 46, no. 9, pp. 1648-1659, 2024, [Online]. Available: http://joces.nudt.edu.cn/CN/.
J. Quan and X. Sun, “Credit risk assessment using the factorization machine model with feature interactions,” Humanities and Social Sciences Communications, pp. 11(1), 2024, doi: 10.1057/s41599-024-02700-7.
T. Liu and N. Zhou, “Deep input-aware factorization machine based on setwise sorting,” Computer Engineering & Science, vol. 45, no. 10, pp. 1891-1900, 2023, doi: 10.3969/j.issn.1007-130X.2023.10.020.
I. Cohen Sabban, O. Lopez, and Y. Mercuzot, “Automatic analysis of insurance reports through deep neural networks to identify severe claims,” Annals of Actuarial Science, vol. 16, no. 1, pp. 42-67, 2021, doi: 10.1017/S174849952100004X.
M. Samiuddin, G. Rajender, K. Varma, A. Kumar, and S. Shaik, “Health insurance cost prediction using deep neural network,” Asian Journal of Research in Computer Science, vol. 16, no. 2, pp. 46-53, 2023, doi: 10.9734/ajrcos/2023/v16i2338.
F. Vandervorst, W. Verbeke, and T. Verdonck, “Claims fraud detection with uncertain labels,” Advances in Data Analysis and Classification, vol. 18, no. 1, pp. 219-243, 2023, doi: 10.1007/s11634-023-00568-0.
X. Zhang, “Optimal strategies for multi-insurance company competition under time-delay effects,” Advances in Applied Mathematics, vol. 14, no. 5, pp. 476-489, 2025, doi: 10.12677/aam.2025.145276.
X. Ma and J. Wang, “Robust inference using inverse probability weighting,” Journal of the American Statistical Association, vol. 115, no. 532, pp. 1851-1860, 2019, doi: 10.1080/01621459.2019.1660173.
V. Avagyan and S. Vansteelandt, “Stable inverse probability weighting estimation for longitudinal studies,” Scandinavian Journal of Statistics, vol. 48, no. 3, pp. 1046-1067, 2021, doi: 10.1111/sjos.12542.
Y. Xie and Z. Li, “Health insurance actuarial theory and methodology,” Journal of Shandong University (Health Sciences), vol. 57, no. 8, pp. 20– 38, 2022, doi: 10.6040/j.issn.1671-7554.0.2018.1016.
Y. Gao, “Optimal reinsurance and investment problems with delay effects in a thinning dependent risk model,” Advances in Applied Mathematics, vol. 13, no. 4, pp. 1523-1535, 2024, doi: 10.12677/aam.2024.134143.
L. Settipalli, G. Gangadharan, and U. Fiore, “Predictive and adaptive drift analysis on decomposed healthcare claims using ART-based topological clustering,” Information Processing & Management, vol. 59, no. 3, Art. no. 102887, 2022, doi: 10.1016/j.ipm.2022.102887.
A. Gallego, J. Calvo-Zaragoza, and R. Fisher, “Incremental unsupervised domain-adversarial training of neural networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 11, pp. 4864-4878, 2021, doi: 10.1109/TNNLS.2020.3025954.
A. Ghosh, T. Schaaf, and M. Gormley, “Adafocal: Calibration-aware adaptive focal loss,” Advances in Neural Information Processing Systems, vol. 35, no. 116, pp. 1583-1595, 2022, doi: 10.48550/arXiv.2211.11838.
J. Singh, C. Beeche, Z. Shi, O. Beale, B. Rosin, J. Leader, and J. Pu, “Batch-balanced focal loss: A hybrid solution to class imbalance in deep learning,” Journal of Medical Imaging, pp. 10(5), 2023, doi: 10.1117/1.JMI.10.5.051809.
L. Yang and B. Shi, “Credit risk assessment model based on modified cross-entropy loss function with focal loss and empirical evidence,” Chinese Journal of Management Science, vol. 30, no. 5, pp. 65-75, 2022, doi: 10.16381/j.cnki.issn1003-207x.2020.2188.