Predicting term life insurance surrender using deep neural networks

Khandan, A.; Niakan, L.; Fakharinezhad, Z.

doi:10.22056/ijir.2023.04.02

Document Type : Original Research Paper

Authors

¹ Department of Economics of Public Affairs, Faculty of Economics, Kharazmi University, Tehran, Iran

² Department of Life Insurance, Dey Insurance Company, Tehran, Iran

https://doi.org/10.22056/ijir.2023.04.02

Abstract

BACKGROUND AND OBJECTIVES: Life insurance has a very low adoption rate in Iran, mainly due to policy surrender. This research aims to analyze the individual characteristics and insurance contract features that influence the surrendering of term life insurance policies.
METHODS: The study utilizes a pilot database of 35,171 policy-holders and pensioners registered by an Iranian insurance company in 2021. Data mining, deep learning, and neural network algorithms are used for analysis due to their high accuracy in prediction:
FINDINGS: The model demonstrates desirable performance based on evaluation metrics with a 74 percent accuracy in predicting both types of surrendered and non-surrendered insurance policies. The model performs better in predicting non-surrendered insurance policies more attention is given to interpreting those results. Despite imbalanced data, the model still performs well. In the dataset, surrendered policies make up only 3 percent of the total, leading to bias towards predicting the majority class. Nonetheless, the model accurately predicts and categorizes most surrendered policies, covering 59 percent of the total 244 cases.
CONCLUSION: The results indicate that certain demographic characteristics, such as age, female gender, health surcharge, and accident risk rate, as well as specific contract characteristics, including policy term, time since start date, longer premium payment methods, higher annual increase in capital and premium, fewer covered risks, and lower benefits, are negatively correlated with policy surrender. Furthermore, the results suggest that if the insured person is the policy surrender themselves, the probability of surrender is minimized. On the other hand, if the insured person is someone else, especially distant relatives, the probability of surrender increases.

Keywords

Main Subjects

Insurance pricing

References

Abbasi, E.; Sazgar, A., (2005). Understanding the reasons for life insurance surrender in Iran insurance company. Iran. J. Insur. Res., 74(2): 87-119 (33 Pages). [In Persian]

Azodi, C.B.; Tang, J.; Shiu, S.H., (2020). Opening the black box: Interpretable machine learning for geneticists. Trends. Genet., 36(6): 442-455 (14 Pages).

Azzone, M.; Barucci, E.; Mancayo, G.G.; Marazzina, D., (2022). A machine learning model for lapse prediction in life insurance contracts. Expert. Syst. Appl., 191(1): 116261.

Bakhtiar Nasrabadi, H.A.; Hassangholipoor, T.; Mira, S.A.; Vedadhir, A.A., (2020A). Developing a model of policyholder's surrender behavior‏:‏‎ A study based on the grounded theory. New. Mark. Res. J., 9(4): 33-54 (22 Pages). [In Persian]

Bakhtiar Nasrabadi, H.A.; Hassangholipoor, T.; Vedadhir, A.A.; Badin, M.; Mira, S.A., (2020B). Explanation of skepticism and trust dialectic in buying behavior of life insurance consumers: A grounded theory. Iran. J. Insur. Res., 9(4): 43-88 (46 Pages). [In Persian]

Balaji, S.; Srivatsa, S.K., (2012). Naive bayes classification approach for mining life insurance databases for effective prediction of customer preferences over life insurance products. Int. J. Comput. Appl., 51(3): 22-26 (5 Pages).

Bash Afshar, M.; SaeedPanah, M.; Tireh Eidouzhi, F., (2018). Clustering model of life insurance customers (Case study: An insurance company). Iran. J. Insur. Res., 7(2): 45-64 (20 Pages). [In Persian]

Berson, A.; Smith, S.; Thearling, K., (1999). Building data mining applications for CRM. New York, NY: McGraw-Hill.

Bimeh Markazi Centeral Insurance of Iran (2021). Statistical yearbook of insurance. Tehran: Bimeh Markazi Centeral Insurance of Iran.

Buhrmester, V.; Munch, D.; Arens, M., (2021). Analysis of explainers of black box deep neural networks for computer vision: A survey. Mach. Learn. Knowl. Extr., 3(4): 966-989 (24 Pages).

Dash, G., (2018). Determinants of life insurance demand: Evidences from India. Asia. Pac. Inst. Adv. Res., 4(2): 86-99 (14 Pages).

Deacon, R.E.; Firebaugh, F.M., (1988). Family resource management: Principles and applications. Allyn & Bacon.

Ghorbani, H.; Ghanbarzadeh, M.; Ofoghi, R., (2022). Investigating the churn of life insurance customers using data mining methods (A case study: One of the Iran’s insurance companies). Iran. J. Insur. Res., 11(4): 305-320 (16 Pages). [In Persian]

Guidotti, R.; Monreale, A.; Ruggieri, S.; Turini, F.; Giannotti, F.; Pedreschi, D., (2018). A survey of methods for explaining black box models. ACM. Comput. Surv., 51(5): 1-42 (42 Pages).

Habibi Marand, N., (2016). Factors affecting redemption of life insurance and investments with an emphasis on microeconomic factors (The case study of Parsian insurance company). [In Persian]

Helmzadeh, A.; Hamidi, K.; Heidarzadeh Hanzaei, K., (2020). Investigating factors affecting the tendency to life insurance surrender. Iran. J. Insur. Res., 9(2): 67-98 (32 Pages). [In Persian]

Heo, W., (2020). The demand for life insurance: Dynamic ecological systemic theory using machine learning techniques. Palgrave Macmillan.

Hozarmoghaddam, N.; Ghanbarzadeh, M.; Hamze, A.; Ghafoor Boroujerdi, M., (2020). Investigating the effects of the coronavirus outbreak on life, health and travel insurance. Iran. J. Health. Insur., 3(3): 148-161 (14 Pages). [In Persian]

Hu, S.; O’Hagan, A.; Sweeney, J.; Ghahramani, M.H., (2021). A spatial machine learning model for analysing customers’ lapse behaviour in life insurance. Anal. Actuarial. Sci., 15(2): 367-393 (27 Pages).

Khandan, A., (2022). Prediction and investigation of various factors’ effect on the surrender of life insurance constracts. Insur. Res. Center. Res. Project. [In Persian]

Kudyba, S.; Kwatinetz, M., (2014). Introduction to the big data era. In Big Data, Mining, and Analytics. Taylor & Francis Group.

Liang, Y.; Li, S.; Yan, C.; Li, M.; Jiang, C., (2021). Explaining the black-box model: A survey of local interpretation methods for deep neural networks. Neuro. Comput., 419: 168-182 (15 Pages).

Mahdavi, G.; Ofoghi, R.; Abed, M., (2015). The impact of risk aversion on surrender of life insurance policies case study (Iranian life insurance market). Iran. J. Insur. Res., 4(3): 61-75 (15 Pages). [In Persian]

Milhaud, X., Loisel, S.; Maume-Deschamps, V., (2011). Surrender triggers in life insurance: What main features affect the surrender behavior in a classical economic context? Bull. Fr. d'Actuariat., 11(22): 5-48 (44 Pages).

Olden, J.D.; Jackson, D.A., (2002). Illuminating the “black box”: A randomization approach for understanding variable contributions in artificial neural networks. Ecol. Model., 154(1/2): 135-150 (16 Pages).

Sazgar, A.; Abed, M., (2018). Explaining factors affecting life insurance surrender. Life insurance development seminar. [In Persian]

Sulaiman, L.A.; Migiro, S.; Yeshihareg, T., (2015). Investigating the factors influencing the life insurance market in Ethiopia. Probl. Perspect. Manage., 13(2): 152-160 (9 Pages).

Vazan, M., (1992). Deep learning: Bases, concepts, and approches. Miad Andisheh publication. [In Persian]

Yaari, M.E., (1965). Uncertain lifetime, life insurance, and the theory of the consumer. Rev. Econ. Stud., 32(2): 137-150 (14 Pages).

Zietz, E.N., (2003). An examination of the demand for life insurance. Risk Manag. Insur. Rev., 6(2): 159-191 (33 Pages).

Letters to Editor

IJIR Journal welcomes letters to the editor for the post-publication discussions and corrections which allows debate post publication on its site, through the Letters to Editor. Letters pertaining to manuscript published in IJIR should be sent to the editorial office of IJIR within three months of either online publication or before printed publication, except for critiques of original research. Following points are to be considering before sending the letters (comments) to the editor.

[1] Letters that include statements of statistics, facts, research, or theories should include appropriate references, although more than three are discouraged.

[2] Letters that are personal attacks on an author rather than thoughtful criticism of the author’s ideas will not be considered for publication.

[3] Letters can be no more than 300 words in length.

[4] Letter writers should include a statement at the beginning of the letter stating that it is being submitted either for publication or not.

[5] Anonymous letters will not be considered.

[6] Letter writers must include their city and state of residence or work.

[7] Letters will be edited for clarity and length.

Name *

Email Address *

Affiliation *

Comments *

Security Code *

Iranian Journal of Insurance Research

Predicting term life insurance surrender using deep neural networks

References

References

Letters to Editor

Send comment about this article

Volume 12, Issue 4 - Serial Number 46
August 2023
Pages 265-282

Predicting term life insurance surrender using deep neural networks

References

References

Letters to Editor

Send comment about this article

Volume 12, Issue 4 - Serial Number 46August 2023Pages 265-282

Volume 12, Issue 4 - Serial Number 46
August 2023
Pages 265-282