Classification of life insurance customer point of views based on text mining algorithms

Aminpour, A.; Rabiei, M.

doi:10.22056/ijir.2023.01.02

Document Type : Original Research Paper

Authors

A. Aminpour ¹
M. Rabiei ²

¹ Department of Industrial Engineering, Faculty of Engineering, University of Eyvanekey, Eyvanekey, Iran

² Department of Electrical and Computer Engineering, Faculty of Engineering, University of Eyvanekey, Eyvanekey, Iran

https://doi.org/10.22056/ijir.2023.01.02

Abstract

BACKGROUND AND OBJECTIVES: In recent years, the insurance industry has grown significantly and different companies started working with various services in this field. Since successful marketing is one of the main goals of insurance companies, it is very important to find people who are likely to want to use life insurance services. This achievement can lead to better management of capital and costs. The main objective of this research is to classify the views of life insurance customers of an insurance company based on text mining algorithms, so that this classification can be used as a basis for predicting potential customers in the future. Anticipating this category of customers. In that case, we will be able to adopt a suitable marketing strategy to sell our services.
METHODS: In this research, we have analyzed a textual dataset, including life insurance customer’s opinions. Despite the growing volume of this type of data, there are applicable tools for organizing, retrieving and discovering useful knowledge from them. In this regard, this research has been carried out on text processing techniques. These techniques seek useful information from unstructured textual data using pattern recognition and discovery. In this article, the views of customers related to life insurance have been examined as an independent issue. The main goal is to categorize these comments into positive and negative categories based on text mining algorithms. To achieve this objective, for the first time in the insurance industry, four different machine algorithms are used in line with text mining of policyholders' points of view.
FINDINGS: According to the techniques used in this research and the obtained results, it can be said that the support vector machine algorithm has the highest prediction accuracy criterion with 73% compared to other algorithms used in this research. At the same time, most of the insurance policyholders have also expressed a positive opinion about the services received, and this means that most of the customers using the mentioned services were satisfied with the company.
CONCLUSION: The majority of insured would like to keep this insurance service in their shopping basket in the future. Therefore, company managers can find their potential customers from among these people and plan to sell their services to them. By adopting this type of marketing strategy, managers can reduce the costs of their company and reduce the price of their services by saving marketing costs. It is natural that one of the important goals of any company is to earn more profit, and this will not be possible unless it maintains its customers by offering optimal prices and increases them day by day. Achieving this depends on our cost understanding, price acceptance, consumer satisfaction and strategic marketing actions. By exploiting the results of this research, it is possible to achieve a suitable marketing strategy for determining the price of insurance services. Determining the optimal price of insurance premium is considered a competitive advantage for companies. The price in all industries is subject to the law of supply and demand. Since getting the best price is one of the top priorities of insurance customers, even a small percentage change in premium prices will cause many customers to switch insurers. Therefore, optimal pricing can be very effective in increasing insurance profits.

Keywords

Main Subjects

New Insurance Technologies

References

Amarasinghe, H.; Warnakulasuriya, S.; Johnson, N. W., (2021). Evaluation of a social marketing campaign for the early detection of oral potentially malignant disorders and oral cancer: Sri Lankan experience. J. Oral Biol. Cran. Res., 11(2): 204-208 (5 Pages).

Asghari, R., (2012). Application of N-gram model in statistical language modeling. International conference on nonlinear modeling and optimization (7 Pages). [In Persian]

Babania, M.; Pourdarvish, A.; Mirashrafi, S., (2020). The role of principal component analysis (PCA) in big data modeling. The third international conference on soft computing (9 Pages). [In Persian]

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

Boroun, G.; Raad, F.; Parvin, H., (2015). Evaluation analysis and combination of machine learning algorithms and data mining techniques for classification. The third international conference on applied research in computer engineering and information technology (13 Pages). [In Persian]

Cheo Yeo, A.; Smith, A.K.; Willis, R.J.; Brooks, M., (2001). Modeling the effect of premium changes on motor insurance customer retention rates using neural networks. International Conference on Computational Science: 390-399 (10 Pages).

Fadaei eslam, M.J., (2021). Co-partitioning using the two-stage structured matrix analysis method. Mach. Vision Image Process., 7(2): (11 Pages). [In Persian]

Farokhseir, G.; Esmaeelpour, M., (2015). Improvement of user behavior pattern recognition algorithms in web mining using link analysis. Second international conference on electrical engineering and computer science (8 Pages). [In Persian]

Gharakhani, M.; Abolghasemi, M., (2011). Applications of data mining in the insurance industry. J. News. World Insur., 6(158): 5-21 (17 Pages). [In Persian]

Hajiheydari, N.; Khaleh, S.; Farahi, A., (2011). Classification of the risk level of car body insurance policyholders using data mining algorithms (Case study: An insurance company). Iran. J. Insur. Res., 26(4): 107-129 (23 Pages). [In Persian]

Han, J.; Kamber, M.; Pei, J., (2012). Data mining concepts and techniques (Third edition). USA: Elsevier.

Homburg, C.; Jozić, D.; Kuehnl, C., (2017). Customer experience management: Toward implementing an evolving marketing concept. J. Acad. Marketing. Sci., 45(3): 377-401 (25 Pages).

Hsia, J.; Kemper, E.; Kiefe, C.; Zapka, J.; Sofaer, S.; Pettinger, M.; Bowen, D.; Limacher, M.; Lillington, L.; Mason, E., (2000). The importance of health insurance as a determinant of cancer screening: Evidence from the Women's Health Initiative. Preventive. Med., 31(3): 261-270 (10 Pages).

Izadparast, M.; Farahi, A.; Fathnezhad, F.; Teimourpour, B., (2022). Using data mining methods to predict the damage level of car body insurance customers. J. Inf. Process. Manage., 27(3): 699-722 (24 Pages). [In Persian]

Jun mei, D.; Gui Quan, L.; Hui, L., (2015). The Application of Improved Random Forest in the Telecom Customer Churn Prediction. J. Telecom. Res. App, 28(11): 1041-1049 (9 Pages ).

Kiadaliri, F.; Azizi, A., (2020). An overview of performance evaluation indicators of control charts. The first international conference on new challenges and solutions in industrial engineering and management and accounting (10 Pages). [In Persian]

Manteghipour, M.; Alaei, M., (2022). Discount effects on the composition of the risk portfolio of the third-party vehicle insurance. Iran. J. Insur. Res., 10(2): (28 Pages). [In Persian]

Momeni, F.; Ghodousi, M., (2016). Decision support systems and business intelligence and design and implementation of a decision support system (case study of insurance industry). The 4th International conference on information, communication and computer technology (11 Pages). [In Persian]

Motarjem, K.; Niakan, L., (2020). Measuring and evaluating the satisfaction of life insurance customers. Iranian J., 10(1): 87-119 (33 Pages). [In Persian]

Motevali Haghi, M.; Ahmadian Tabasi, H.; Sajadi, N., (2012). Data preparation for data mining techniques and its application. The first national conference of information technology and computer networks of PNU (16 Pages). [In Persian]

Oliaei, A.; Hazeri, A.; Jamali, M.; Khazaee, A., (2018). Finding potential customers to buy insurance with data mining techniques. The second national conference of computer, information technology and artificial intelligence applications (7 Pages). [In Persian]

Oshini, G. T. L.; Caldera, H. A., (2013). Mining life insurance data for customer attrition analysis. J. Indust. Intellig. Inf., 1(1): 52-58 (7 Pages).

Pahlevani Ghomi, M.; Osati Araghi, N.; Nazari, S., (2020). Machine learning techniques and algorithms. The second national conference of new skills in electrical engineering, computer and communication technology (7 Pages). [In Persian]

Palakshappa, A.; Patil, M.M., (2022). RFM model for customer purchase behavior using K-Means algorithm. J. King Saud Univ. Comput. Inf. Sci., 34(5): 1785-1792 (8 Pages).

Rezaei navaei, S.; Koosha, H., (2017). Applying and evaluating data mining techniques to predict customer turnover in the insurance industry. Int. J. Ind. Eng. Oper. Manage., 27(4): 635-653 (19 Pages). [In Persian]

Senousy, Y.; Nashaat El-Khamisy, M.; Alaa El-din, R., (2018). Recent trends in big data analytics towards more enhanced insurance business models. Int. J. Comp. Sci Inf. Secur., 16(12): 39-45 (7 Pages).

Sagiroglu, S.; Sinanc, D., (2013). Big data: A review. Collaboration technologies and systems (CTS). 2013 International conference on collaboration technologies and systems.

Turney, P.D., (2002). Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv preprint cs/0212032.

Vali Mohammadi, S.; Shekarchi, A., (2010). The application of data mining in improving customer relationship management. The first national industrial and systems engineering conference (11 Pages). [In Persian]

Yoon, S. J.; Lee, H.J., (2017). Does customer experience management pay off? Evidence from local versus global hotel brands in South Korea. J. Hospitaly marketing manage., 26(6): 585-605 (21 Pages).

Zaresaadabadi, E.; Zaresaadabadi, M., (2014). Data mining is a new way to face challenges. The third national accounting and management conference (16 Pages). [In Persian]

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

Classification of life insurance customer point of views based on text mining algorithms

References

References

Letters to Editor

Send comment about this article

Volume 12, Issue 1 - Serial Number 43
February 2023
Pages 15-26

Classification of life insurance customer point of views based on text mining algorithms

References

References

Letters to Editor

Send comment about this article

Volume 12, Issue 1 - Serial Number 43February 2023Pages 15-26

Volume 12, Issue 1 - Serial Number 43
February 2023
Pages 15-26