Providing a Model for Preprocessing the Organizational Data in Order to Predict Insurance Business Processes

Subject Areas : Statistics

Mehrdad Fadaei PellehShahi ¹ , Sohrab Kordrostami ² , Amir Hossein Refahi Sheikhani ³ , Marzieh Faridi Masouleh ⁴ , Soheil Shokri ⁵

1 - Applied Mathematics, Department of Mathematics, Lahijan Branch, Islamic Azad University, Lahijan, Iran
2 - Department of Mathematics, Lahijan Branch, Islamic Azad University, Lahijan, Iran
3 - Department of Mathematics, Lahijan Branch, Islamic Azad University, Lahijan, Iran
4 - Computer and Information Technology Department, Ahrar Institute of Technology and Higher Education, Rasht, Iran
5 - Department of Mathematics, Lahijan Branch, Islamic Azad University, Lahijan, Iran

Received: 2021-08-29 Accepted : 2022-06-01 Published : 2024-01-18

Keywords: پیش پردازش, شبکه عصبی بازگشتی, داده کاوی, کسب و کار بیمه های اجتماعی, پیش بینی,

Abstract :

In this paper , a new data preprocessing method for predicting business processes is presented , using recursive neural networks , Markov chains and recursive deep learning . The aim of this study is to obtain high quality data and extract the information of the most important variables involved in the disability process of the Social Security Organization (S S O ) . For this purpose, the proposed method includes reducing the number of features and normalizing the data compared to the initial features . The method is implemented for real data of the Social Security Organization and is applied in the form of predictive method . T he results show that the proposed method increases the amount of memory usage , but the amount of CPU usage time becomes significantly lower than the methods compared . In addition, the presented method signifi cantly increases the accuracy and efficiency .

References:

[1] A. Khan, H. Le, K. Do, T. Tran, A. Ghose, H. Dam, R. Sindhgatta. Memory-augmented neural networks for predictive process analytics: arXiv preprint arXiv: 1802. 00938 (2018).

[2] A. E. Márquez-Chamorro, M. Resinas, A. Ruiz-Corts.Predictive monitoring of business processes: a survey. IEEE Transactions on Services Computing 99:1-1 (2017).

[3] L. Lin, L. Wen, J. Wang. Mm-pred: A deep predictive model for multi-attribute event sequence. In Proceedings of the 2019 SIAM international conference on data mining: Society for Industrial and Applied Mathematics. 118-126 (2019).

[4] J.-P. Briot, G. Hadjeres, F. Pachet. Deep learning techniques for music generation-a survey. arXiv preprint arXiv: 1709.0162. (2019)

[5] J. Evermann, J.-R. Rehse, P. Fettke. A deep learning approach for predicting process behavior at runtime: in International Conference on Business Process Management, Springer 327-338 (2016).

[6] Y. LeCun, Y. Bengio, G. Hinton. Deep learning: Nature 521: 436–444 (2015).

[7] T. A. Gibson, J. A. Henderson, J. Wiles. Predicting temporal sequences using an event-based spiking neural network incorporating learnable delays 3213-3220 (2014).

[8] F. Daniel, K. Barkaoui, S. Dustdar,eds. Process Mining Manifesto: in Business Process Management Workshops. IEEE Task Force on Process Mining. vol. 99 of Lecture Notes in Business Information Processing, Springer-Verlag, Berlin 169-194 (2012).
[9] J. Kumar, A. K. Singh. Workload prediction in cloud using arti_cial neural network and adaptive di_erential evolution. Future Generation Computer Systems 81: 41-52 (2018).

[10] N. Tax, I. Verenich, M. La Rosa, M. Dumas. Predictive business process monitoring with lstm neural networks: In International Conference on Advanced Information Systems Engineering, 477–492 (2017).

[11] W. M. P. van der Aalst, M.H. Schonenberg, M. Song. Time prediction based on process mining. Inf. Syst 36(2): 450–475 (2011).

[12] X. Jiang, S. Pan, G. Long, F. Xiong, J. Jiang, C. Zhang. Cost-sensitive parallel learning framework for insurance intelligence operation. Transactions on Industrial Electronics 1–11 (2018).

[13] M.A. Jassim, S.N. Abdulwahid. Data Mining preparation: Process, Techniques and Major Issues in Data Analysis, IOP Conf. Ser.: Mater. Sci. Eng. 1090 012053 (2021).

[14] A.K. Dubey, A. Kumar, R . Agrawal. An efficient ACO‑PSO‑based framework for data classification and preprocessing in big data, Evolutionary Intelligence, part of Springer Nature 2020 https://doi. org/10. 1007/s12065-020-00477-7 (2020)

[15] S. García, S. Ramírez-Gallego, J. Luengo, J.M. Benítez, F.,Herrera. Big data preprocessing: methods and prospects, Big Data Analytics, DOI 10.1186/s41044-016-0014-0 (2016).

[16] J. A. Cortés-Ibáñez, S. González, J. J. Valle-Alonso, J. Luengo, S. García, F. Herrera. Preprocessing methodology for time series: an industrial world application case study. Information Sciences, 514, 385-401 (2020).

[17] H.woo, J. kim, W. Lee. Validation of Text Data Preprocessing Using a Neural Network Model: Mathematical Problems in Engineering. ) 2020).

[18] G. report.Critical Capabilities for Composite Content Management Applications (2010).

[19] G. T. Lakshmanan, D. Shamsi, Y. N. Doganata, M. Unuvar, R. Khalaf. A markov predictionmodel for data-driven semi-structured business processes: Knowledge and Information Systems 42: 97-126 (2015).

[20] W.V. Aalst, A. Adriansyah, A.K. Medeiros, F. Arcieri, T. Baier, T. Blickle, J. Chandra Bose, P.Van Den Brand, R. Brandtjen, J. Buijs. Process mining manifesto: In International Conference on Business Process Management 169–194 (2011).

[21] J. Schmidhuber. Deep learning in neural networks: An overview. Neural Networks 61: 85–117 (2015).

[22] N. Tax, I. Verenich, M. La Rosa, M. Dumas. Predictive business process monitoring with lstm neural networks: in International Conference on Advanced Information Systems Engineering. Springer 477-492 (2017).

[23] N. Navarin, B. Vincenzi, M. Polato, A. Sperduti. Lstm networks for data-aware remaining time prediction of business process instances: arXiv preprint arXiv: 1711.03822 (2017).

[24] J. Evermann, J. Rehse, P. Fettke. Predicting process behaviour using deep learning: Decision Support Systems. (2017).

[25] P.H. Klees, M. leoni A. W. Veenstra. The Application of Comparative Process Mining in Logistics.Student theses are made available in the TU/e repository upon obtaining the required degree. (2017).

[26] M. Fadaei Pellehshahi, S. Kordrostami, A.H. Refahi Sheikhani, M. Faridi Masouleh. Predicting business processes of the social insurance using recurrent neural network and Markov chain: Journal of Modelling in Management, Vol. ahead-of- print No. ahead- of- print. (2021).