IBM Attrition Prediction Analysis: Factors That Can Influence the Attrition Rate
DOI:
https://doi.org/10.54691/bcpbm.v36i.3448Keywords:
Attrition; Classification prediction; XGBoost.Abstract
This paper aims at solving the high level of attrition rate at IBM. Data scientists would like to measure the relationships between the attrition rate and other descriptive information such as gender, age, working experience and position, to predict the attrition status and look for commons on those who have left or will probably leave the corporation in the future. Based on those predictions, appropriate summaries of their characteristics can be sketched for the manager in IBM to provide better working conditions to lower the rate. The main prediction method in this paper will be tree-based including simple decision tree and other advanced techniques, and the prediction results will be shown as scatter plots. While XGBoost shows the highest performance in this study, it will be selected as the prediction method to predict the attrition status of IBM employees. With such a model, IBM data analysts will be able to do further research on the reasons for attrition and thus lower the attrition rate.
Downloads
References
Wushishi A.A., Fooi, F. S., Basri, R. et al. A qualitative study on the effects of teacher attrition. International Journal of Education and Literacy Studies, Australian International Academic, vol.2, no.1, pp.11-16, 2014.
Valier, K., What is Attrition rate and what does it mean for your company? Jun 7, 2022, Oct 23, 2022. https://factorialhr.com/blog/attrition-rate/#attrition
Dobhal, R., Dr. Nigam, A., Employee attrition and employee satisfaction: A study of H.R., performance appraisal & training practices in defense PSUs in India. IOSR Journal of Business and Management, vol. 20, pp. 1-27, 2018.
Mishra, P., Solanki, N., A study of the factors leading to attrition in employees of BPO Industry with special focus on attitude towards job and employee engagement. Barkatullah University, vol. 6, no. 2, pp. 158-165, 2018.
Goswami, B. K., Jha, S., Attrition issues and retention challenges of employees. International Journal of Scientific & Engineering Research, vol.3, no. 4, pp. 1-6, 2012.
Sakkaf, Y., Decision trees for classification: Id3 Algorithm explained. Mar 31, 2020, Oct 23 2022. https://towardsdatascience.com/decision-trees-for-classification-id3-algorithm-explained-89df76e72df1.
Arif, R., Classification in decision tree - a step by step cart (classification and regression tree). Apr 5, 2020, Oct 23, 2022. https://medium.com/analytics-vidhya/classification-in-decision-tree-a-step-by-step-cart-classification-and-regression-tree-8e5f5228b11e.
Arif, R., Regrssion in decision tree - a step by step cart (classification and regression tree). May 2, 2020, Oct 23, 2022. https://medium.com/@arifromadhan19/regrssion-in-decision-tree-a-step-by-step-cart-classification-and-regression-tree-196c6ac9711e.
Mavuduru, A., Why XGBoost can't solve all your problems. Nov 10, 2020, Oct 23, 2022. https://towardsdatascience.com/why-xgboost-cant-solve-all-your-problems-b5003a62d12a.
Przybyla M., Stop using XGBoost. Jun 25, 2021, Oct 23, 2022. https://towardsdatascience.com/stop-using-xgboost-660ed6718845.
Downloads
Published
How to Cite
Issue
Section
