COMPARING STATISTICAL AND DEEP LEARNING METHODS FOR INSURANCE CLAIM ESTIMATION: A CASE STUDY OF HIDDEN MARKOV MODEL (HMM) AND CONVOLUTIONAL NEURAL NETWORK - LONG SHORTTERM MEMORY (CNN-LSTM)
Abstract
The insurance industry relies heavily on accurate claim prediction to support risk management, reserve allocation, and financial stability. However, motor vehicle insurance claim data are typically characterized by temporal dependency, highly skewed distributions, and fluctuating claim severity, making accurate prediction a challenging task. While deep learning approaches have recently gained attention for time-series forecasting, their effectiveness on moderate-scale insurance claim datasets remains uncertain. This study aims to compare the predictive performance of the Hidden Markov Model (HMM) and CNN-LSTM in modelling temporal patterns and predicting daily motor vehicle insurance claims. In addition, an Attention-LSTM + XGBoost ensemble model is included as a supplementary deep learning benchmark. This study utilizes historical motor vehicle insurance claim data collected from 2017 to 2021, consisting of 11,679 claim observations. The data preprocessing stage included data cleaning, missing value handling, outlier detection, and claim severity categorization for HMM modelling. The HMM parameters were estimated using the Baum–Welch algorithm, while the deep learning models were trained using sequential claim data. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and coefficient of determination (R^2) on the testing dataset to ensure objective comparison. The experimental results show that the HMM model achieved the best predictive performance, outperforming both the CNN-LSTM and Attention-LSTM + XGBoost models. The findings indicate that the probabilistic structure of HMM is more suitable for modelling the temporal risk patterns and fluctuating claim behavior observed in the motor vehicle insurance dataset. Furthermore, the study demonstrates that classical probabilistic models can remain competitive and even outperform more complex deep learning approaches when applied to moderately sized insurance claim datasets with limited hidden complexity.
Downloads
References
A. Bücher and A. Rosenstock, “MICRO-LEVEL PREDICTION OF OUTSTANDING CLAIM COUNTS BASED ON NOVEL MIXTURE MODELS AND NEURAL NETWORKS,” Eur. Actuar. J., vol. 13, no. 1, pp. 55–90, Jun. 2023, doi: https://doi.org/10.1007/s13385-022-00314-4.
B. Avanzi, Y. Li, B. Wong, and A. Xian, “ENSEMBLE DISTRIBUTIONAL FORECASTING FOR INSURANCE LOSS RESERVING,” Scand. Actuar. J., vol. 2024, no. 9, pp. 971–1012, 2024, doi: https://doi.org/10.1080/03461238.2024.2365392.
Verawaty Ompusunggu, “5 INSURANCE COMPANIES THAT WENT BANKRUPT AND DEFAULTED IN INDONESIA,” Lifepal. Accessed: May 10, 2025. [Online]. Available: https://lifepal.co.id/media/perusahaan-asuransi/perusahaan-asuransi-yang-bangkrut/
H. A. Surya, Sukono, H. Napitupulu, and N. Ismail, “A SYSTEMATIC LITERATURE REVIEW OF INSURANCE CLAIMS RISK MEASUREMENT USING THE HIDDEN MARKOV MODEL,” Risks, vol. 12, no. 11, p. 169, Oct. 2024, doi: https://doi.org/10.3390/risks12110169
M. T. Jatipaningrum, K. Suryowati, Libertania, M. Melania, and E. Un, “PREDICTING THE RUPIAH EXCHANGE RATE AGAINST THE DOLLAR USING FTS-MARKOV CHAINS AND HIDDEN MARKOV MODELS,” Jurnal Derivat, vol. 6, no. 1, pp. 32–41, Jul. 2019, doi: https://doi.org/10.31316/j.derivat.v6i1.334.
A. Alimansyah and A. Purqon, “APPLICATION OF HIDDEN MARKOV MODEL IN STOCK PRICE PREDICTION IN INDONESIA,” Bahasa, pp. 102–08, Jul. 2016, Accessed: Mar. 01, 2025. [Online]. Available: https://ifory.id/proceedings/2016/4chQ7E9Cp/snips_2016_arfian_alimansyah_1b09d74502f3144edef531cc4bda41db.pdf
M. A. Istiake Sunny, M. M. S. Maswood, and A. G. Alharbi, “DEEP LEARNING-BASED STOCK PRICE PREDICTION USING LSTM AND BI-DIRECTIONAL LSTM MODEL,” in 2nd Novel Intelligent and Leading Emerging Sciences Conference, NILES 2020, Institute of Electrical and Electronics Engineers Inc., Oct. 2020, pp. 87–92. doi: https://doi.org/10.1109/NILES50944.2020.9257950.
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, Mar. 2022, doi: https://doi.org/10.1017/S174849952100004X.
L. Alzubaidi et al., “REVIEW OF DEEP LEARNING: CONCEPTS, CNN ARCHITECTURES, CHALLENGES, APPLICATIONS, FUTURE DIRECTIONS,” J. Big Data, vol. 8, no. 1, Dec. 2021, doi: https://doi.org/10.1186/s40537-021-00444-8.
L. Zhang and D. Jánošík, “ENHANCED SHORT-TERM LOAD FORECASTING WITH HYBRID MACHINE LEARNING MODELS: CATBOOST AND XGBOOST APPROACHES,” Expert Syst. Appl., vol. 241, May 2024, doi: https://doi.org/10.1016/j.eswa.2023.122686.
D. C. R Novitasari et al., “WIND SPEED ANALYSIS IN TIDAL WATER USING THE FORWARD-BACKWARD ALGORITHM IN HIDDEN MARKOV MODELS IN THE TANJUNG PERAK PORT AREA OF SURABAYA,” Jurnal Sains Matematika dan Statistika, vol. 4, no. 1, 2018, doi: http://dx.doi.org/10.24014/jsms.v4i1.5254 .
C. Wang, K. Li, and X. He, “NETWORK RISK ASSESSMENT BASED ON BAUM WELCH ALGORITHM AND HMM,” Mobile Networks and Applications, vol. 26, no. 4, pp. 1630–1637, Aug. 2021, doi: https://doi.org/10.1007/s11036-019-01500-7.
G. F. Dar, T. R. Padi, S. Rekha, and Q. F. Dar, “STOCHASTIC MODELING FOR THE ANALYSIS AND FORECASTING OF STOCK MARKET TREND USING HIDDEN MARKOV MODEL,” Asian Journal of Probability and Statistics, pp. 43–56, Jun. 2022, doi: https://doi.org/10.9734/ajpas/2022/v18i130436.
Z. Su and B. Yi, “RESEARCH ON HMM-BASED EFFICIENT STOCK PRICE PREDICTION,” Mobile Information Systems, vol. 2022, pp. 1–8, Mar. 2022, doi: https://doi.org/10.1155/2022/8124149.
I. Sassi, S. Anter, and A. Bekkhoucha, “A NEW IMPROVED BAUM-WELCH ALGORITHM FOR UNSUPERVISED LEARNING FOR CONTINUOUS-TIME HMM USING SPARK,” International Journal of Intelligent Engineering and Systems, vol. 13, no. 1, pp. 214–226, Feb. 2020, doi: https://doi.org/10.22266/ijies2020.0229.20.
S. Kim and M. Kang, “FINANCIAL SERIES PREDICTION USING ATTENTION LSTM,” Feb. 2019, doi: https://doi.org/10.48550/arXiv.1902.10877 .
S. Trihandaru, H. A. Parhusip, A. W. Goni, S. Trihandaru, H. A. Parhusip, and A. W. Goni, “OVERCOMING OVERFITTING IN MONKEY VOCALIZATION CLASSIFICATION: USING LSTM AND LOGISTIC REGRESSION,” BAREKENG: J. Math. & App, vol. 19, no. 2, pp. 973–0986, 2025, doi: https://doi.org/10.30598/barekengvol19iss2pp973-986
M. A. Istiake Sunny, M. M. S. Maswood, and A. G. Alharbi, “DEEP LEARNING-BASED STOCK PRICE PREDICTION USING LSTM AND BI-DIRECTIONAL LSTM MODEL,” in 2nd Novel Intelligent and Leading Emerging Sciences Conference, NILES 2020, Institute of Electrical and Electronics Engineers Inc., Oct. 2020, pp. 87–92. doi: https://doi.org/10.1109/NILES50944.2020.9257950.
C. Yu et al., “GRADIENT BOOSTING DECISION TREE WITH LSTM FOR INVESTMENT PREDICTION,” May 2025, doi: https://doi.org/10.1109/ACCTCS66275.2025.00017.
W. Lu, J. Li, Y. Li, A. Sun, and J. Wang, “A CNN-LSTM-BASED MODEL TO FORECAST STOCK PRICES,” Complexity, vol. 2020, no. 1, Nov. 2020, doi: https://doi.org/10.1155/2020/6622927
W. Gamaleldin, O. Attayyib, M. M. Alnfiai, F. A. Alotaibi, and R. Ming, “A HYBRID MODEL BASED ON CNN-LSTM FOR ASSESSING THE RISK OF INCREASING CLAIMS IN INSURANCE COMPANIES,” PeerJ Comput. Sci., vol. 11, 2025, doi: https://doi.org/10.7717/peerj-cs.2830/supp-1
S. Mehtab and J. Sen, “STOCK PRICE PREDICTION USING CNN AND LSTM-BASED DEEP LEARNING MODELS,” in 2020 International Conference on Decision Aid Sciences and Application, DASA 2020, Institute of Electrical and Electronics Engineers Inc., Nov. 2020, pp. 447–453. doi: https://doi.org/10.1109/DASA51403.2020.9317207
R. U. Din, S. Ahmed, S. H. Khan, A. Albanyan, J. Hoxha, and B. Alkhamees, “A NOVEL DECISION ENSEMBLE FRAMEWORK: ATTENTION-CUSTOMIZED BILSTM AND XGBOOST FOR SPECULATIVE STOCK PRICE FORECASTING,” PLoS One, vol. 20, no. 4 April, Apr. 2025, doi: https://doi.org/10.1371/journal.pone.0320089
A.-H. Rahmani, J. Salehi, and M. Shafie-Khah, “AN ADVANCED HYBRID CNN-LSTM-XGBOOST MODEL WITH WAVELET TRANSFORM AND ATTENTION MECHANISM FOR ACCURATE SHORT-TERM ELECTRICITY PRICE FORECASTING,” Jun. 2025. doi: https://dx.doi.org/10.2139/ssrn.5314801
M. S. Hossain and F. Parvin, “A COMPARATIVE STUDY OF VARIOUS STATISTICAL AND MACHINE LEARNING MODELS FOR PREDICTING RESTAURANT DEMAND IN BANGLADESH,” PLoS One, vol. 20, no. 6 June, Jun. 2025, doi: https://doi.org/10.1371/journal.pone.0325449
Copyright (c) 2026 Ainun Mawaddah Abdal, Andi Muhammad Anwar, Illuminata Wynnie, Amil Siddik, Edy Saputra Rusdi, Mauliddin Mauliddin
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. 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 websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.
1.gif)
