To read this content please select one of the options below:

Employee attrition prediction in a pharmaceutical company using both machine learning approach and qualitative data

Fatemeh Mozaffari (University of Tehran, Tehran, Iran)
Marzieh Rahimi (Allameh Tabataba'i University, Tehran, Iran)
Hamidreza Yazdani (University of Tehran, Tehran, Iran)
Babak Sohrabi (University of Tehran, Tehran, Iran)

Benchmarking: An International Journal

ISSN: 1463-5771

Article publication date: 16 December 2022




This research intends to develop a model for predicting employees at a high-risk attrition and identify the most important factors affecting them.


In this study, using the triangulation technique of a mixed research method, the employee attrition problem is investigated by identifying its affecting factors. For that matter, data related to the human resources department of a pharmaceutical company in Iran are used. And to achieve the intended goal, advanced data mining algorithms and interviews with human resource managers are applied.


A model for predicting employees at a high-risk attrition is presented based on the gradient boosting machine algorithm with 89% accuracy. The use of the mixed research approach shows that qualitative and quantitative methods can be more effective in identifying the factors affecting employee churn or loss of staff. The results also contain a new situation arising out of the COVID-19 pandemic and remote working scenarios having impact on employee attrition. Finally, human resource policies are presented based on variables related to each of the identified factors.


The novel contributions of this study include real data related to a leading pharmaceutical company as well as a combination of two quantitative and qualitative methods. The hybrid approach can identify the reasons for attrition and, consequently, retention policies to benefit from the advantage of both approaches. Data mining can be useful to identify the factors, which are usually not mentioned in termination interviews, such as direct managers. On the other hand, the results obtained from termination interviews can also include features that the authors cannot identify through data mining, which are specifically related to the characteristics of the pharmaceutical industry such as building a more professional career path. From a practical perspective, since this company specializes in pharmaceutical marketing in a new way and is primarily comprised graduates, it is important to note that the churn of specialized people disperses organizational and technological know-how. On the other hand, the pharmacist community in Iran is small, and their attrition might adversely affect not only the reputation of an organization but the employer's brand as well. So, this research would help other similar firms in retaining their valuable human capital.



The authors would like to thank Ms. Fatemeh Jafari for her assistance with data preparation.


Mozaffari, F., Rahimi, M., Yazdani, H. and Sohrabi, B. (2022), "Employee attrition prediction in a pharmaceutical company using both machine learning approach and qualitative data", Benchmarking: An International Journal, Vol. ahead-of-print No. ahead-of-print.



Emerald Publishing Limited

Copyright © 2022, Emerald Publishing Limited

Related articles