طراحی مدل تعامل انسان و سیستم‌های یادگیری ماشین برای ارتقای عملکرد فردی در سازمان تأمین اجتماعی

مهدی  باقری میمندی; عباس بابایی نژاد; عمید خطیبی بردسیری

Authors

Mahdi Baqeri Meymandi Department of Management, Ke.C., Islamic Azad University, Kerman, Iran Author https://orcid.org/0009-0000-5505-7088
Abbas Babaeinejad Department of Public Administration, Kerman Branch, Islamic Azad University, Kerman, Iran https://orcid.org/0000-0003-3090-7589
Amid Khatibi Bardsiri Department of Computer Engineering, Ke.C., Islamic Azad University, Kerman, Iran Author https://orcid.org/0000-0001-9640-498X

Keywords:

Human, Machine Interaction, Machine Learning, Individual Performance, Social Security Organization, Agent, Based Simulation

Abstract

This study aimed to design and validate a human–machine learning interaction model for enhancing individual performance in the Social Security Organization, with emphasis on adaptive task allocation, trust, explainability, and preservation of human oversight. This applied mixed-methods study used a multilevel design at the individual, team, and organizational levels. At the individual level, 12 experts were purposively selected, and semi-structured interview data were analyzed through two-cycle content analysis using NVivo 12. At the team level, digital trace data from 1,510 cases across five work teams, including four experimental teams and one control team, were examined over a five-month period. Main variables included rework, re-referral, decision accuracy, processing time, and user responses to system recommendations. At the organizational level, an agent-based simulation model was developed in AnyLogic 8 and calibrated using observed data, expert judgments, and inverse calibration procedures. Difference-in-differences analysis showed that, compared with the control team, machine learning implementation reduced rework by 6.7 percentage points (z = -3.42, p = 0.001), reduced re-referral by 7.1 percentage points (z = -3.61, p < 0.001), and increased correct final decisions by 7.6 percentage points (z = 4.18, p < 0.001). Completion without returning to a previous workflow stage increased by 9.2 percentage points (z = 4.36, p < 0.001). Cramer’s V ranged from 0.14 to 0.18. Performance scores also differed substantially between accepted and rejected recommendations, with a large effect size (Cohen’s d = 1.67). Simulation results identified adaptive human–machine collaboration with 60% task allocation to the system as the highest-performing scenario. Maximum automation did not produce the best outcomes; instead, adaptive human–machine collaboration yielded superior performance when task allocation was adjusted to complexity, decision sensitivity, and system capability while preserving meaningful human review in complex and high-risk cases.

Downloads

Download data is not yet available.

References

Abbasi Bastami, R., Hamidi, N., Rezaei, A., & Akbari, A. (2019). Simulating a human resource retention model using a system dynamics approach: Social Security Organization of Alborz Province 3rd International Conference on Management, Industrial Engineering, Economics and Accounting,

Abbaszadeh Karati, L., Safa, R., & Sarvarkhah, A. (2022). Developing a model for predicting health insurance premiums using machine learning. Ayandegan Institute of Higher Education, Faculty of Engineering

Ahmad, A. K., Younis, S. Q., Ahmad, S. R., Al-Jubouri, S., & Fadhil, M. A. (2023). A machine learning approach to predicting employee performance in administrative information systems 7th International Symposium on Innovative Approaches in Smart Technologies,

Alinejad, A., Nourani, A., & Jabraeili, M. (2022). Evaluating the usability of user interfaces of electronic prescribing systems of Iran's Social Security and Health Insurance Organizations. Health Management, 25(88).

Alkhawaldah, R. A., Alshalabi, F. S., Alshawabkeh, Z. A. E., Almarshad, M. N., Al-Tahrawi, M. H., & Alshawabkeh, T. Z. A. (2025). The role of e-government in organizational effectiveness: The mediating role of administrative empowerment. Human Systems Management, 44(3), 432-447. https://doi.org/10.1177/01672533241295510

Goodhue, D. L., & Thompson, R. L. (1995). Task-technology fit and individual performance. MIS quarterly, 19(2), 213-236. https://doi.org/10.2307/249689

Hosseini, S., & Bazaei, G. (2021). Examining the consequences of implementing a centralized registration system for insured persons of the Social Security Organization: A case study of the Western General Directorate of the Social Security Organization. Business Management, 13(49).

Izadbakhsh, H., Chaharmahali, H., & Kordlouei, H. (2022). Modeling and simulating pension fund sustainability based on wage and salary risks and capital return rates using a system dynamics approach: A case study of the Social Security Organization. Executive Management Research, 14(28).

Jahani, A., Rasouli, M. R., & Shahmansouri, B. (2022). The role of modern communication technologies in developing audience orientation in the Social Security Organization: A case study of visitors to Social Security Organization branches in Tehran, 2018–2020. Society, Culture, Media, 11(42).

Jamshidi Zarmehri, M. (2025). Human–artificial intelligence coexistence: From personal assistants to intelligent colleagues 12th International Conference on Applied Research in Basic Sciences, Engineering and Technology,

Karimian Sichani, Z., Cheraghali, M. H., & Dehghani, A. (2022). A comparative analysis of the financial sustainability of DB-PAYG and NDC schemes for regularized retirements in the Social Security Organization using a system dynamics approach. New Research in Decision Making, 7(3).

Khalil, A. A., Mandour, M. A., & Ali, A. (2024). The benefits of social insurance system prediction using a hybrid fuzzy time series method. Peerj Computer Science, 10, e2500. https://doi.org/10.7717/peerj-cs.2500

Kheirallahi, H., Saber Afsharian, M. R., & Bakhshi, R. (2021). Evaluating the capabilities of outpatient and inpatient electronic prescribing systems from the perspectives of physicians working in Social Security Organization hospitals in Razavi Khorasan 2nd National Conference on New Research in Management, Economics and Accounting,

Lee, G., & Lee, W. S. (2024). Why and how does a machine learning algorithm coexist with alternative methods? The case of the social welfare blind spot identification system. MIS quarterly, 48(4), 1838-1841.

Levitt, B., & March, J. G. (1988). Organizational learning. Annual Review of Sociology, 14(1), 319-338. https://doi.org/10.1146/annurev.so.14.080188.001535

Madadi, Y., Rouhani, S., & Gholipour, A. (2021). A systems model of human resource management based on machine learning in the healthcare sector. University of Tehran, Regional Campuses, Aras International Campus

Najarpour, H. A., Nili Ahmadabadi, M., & Mohammadinasab, M. (2023). Designing a model for structuring the financial crisis of the Social Security Organization using soft systems methodology. Organizational Resources Management Research, 13(2).

Pap, J., Makó, C., Illéssy, M., Kis, N., & Mosavi, A. (2022). Modeling organizational performance with machine learning. Journal of Open Innovation: Technology, Markets, and Complexity, 8(4), 177. https://doi.org/10.3390/joitmc8040177

Rabiei, A., Rezaei, G., & Gharakhani, D. (2025). Detecting wage fraud among Social Security insured persons using machine learning algorithms. Social Security Quarterly, 115-146. https://doi.org/10.22034/qjo.2026.555073.1448

Raisch, S., & Krakowski, S. (2021). Artificial intelligence and management: The automation-augmentation paradox. Academy of Management Review, 46(1), 192-210. https://doi.org/10.5465/amr.2018.0072

Saeidi, F., & Khateri, A. (2022). Examining the relationship of human–machine interaction in the Technical and Vocational Organization 1st International Conference on the Built Environment in the Digital Age,

Schmager, S., Pappas, I. O., & Vassilakopoulou, P. (2025). Understanding human-centred AI: A review of its defining elements and a research agenda. Behaviour & Information Technology, 1-40. https://doi.org/10.1080/0144929X.2024.2448719

Sturm, T., Gerlach, J. P., Pumplun, L., Mesbah, N., Peters, F., Tauchert, C., Nan, N., & Buxmann, P. (2021). Coordinating human and machine learning for effective organizational learning. MIS quarterly, 45(3), 1581-1602. https://doi.org/10.25300/MISQ/2021/16543

Tugarin, N., & van Husen, C. (2025). Development and integration of human-AI interactions in service applications: Conceptual framework and review. International Journal of Information Management Data Insights, 5(2), 100357. https://doi.org/10.1016/j.jjimei.2025.100357

Vazifeh, R., & Darvishi, A. (2018). Examining the relationship of business intelligence system implementation and e-learning with dimensions of succession planning among Social Security employees in Ardabil Province 2nd National Conference on Sustainable Development in Management and Accounting Sciences in Iran,