Jennifer Anne A. Repaso

Work place: Bulacan State University

E-mail: jenniferanne.repaso@bulsu.edu.ph

Website:

Research Interests: Computer Science & Information Technology, Information Security, Information Systems, Multimedia Information System

Biography

Jennifer Anne Repaso is a faculty member from Bulacan State University Sarmiento Campus under the Information Technology Department. She has a degree of B.S.Ed. Computer Major taken from University of Santo Tomas Manila and earned her Master in Information Technology (MIT) from Technological Institute of the Philippines Q.C. Currently, she is finishing her Doctor in Information Technology also in Technological Institute of the Philippines, Manila Campus.

Author Articles
Determining Factors Resulting to Employee Attrition Using Data Mining Techniques

By Jennifer Anne A. Repaso Elenita T. Caparino Mary Grace G. Hermogenes Joann G. Perez

DOI: https://doi.org/10.5815/ijeme.2022.03.03, Pub. Date: 8 Jun. 2022

Business Process Outsourcing is a budding industry which currently employs millions of workers in the Philippines which draws applicants from undergraduate to professionals. It provides high-quality, well-paying jobs to millions of Filipinos while inspiring economic activity and investments all around. However, attrition rate of around 50 percent in the current year is a big challenge to predict employee turnover. This study came up with a model that can be adopted in the organization to predict possible attrition and guide the employers particularly the HR team in determining first-hand the type of applicant that they have by applying Data Mining techniques. The authors extracted significant predictors among the given data from a BPO company. Fast Correlation-Based Filtering Algorithm was performed to remove irrelevant data and increase learning accuracy. 1470 records with 21 attributes were initially provided and 17 were identified as significant after filtering and preprocessing of data was performed. The preprocessed data was used for model building with the application of Naïve Bayes Algorithm. The resulting model predicted percentage probability of hoppers and stayers. Among the 17 given variables, Total Working Years, Marital Status and Age ranked as the top predictors in determining possibility of attrition. The data was split into 60% training data or a total of 882 records and 40% testing data or a total of 588 records.  The predicted number of stayers is 542 or 92.2% and the predicted hoppers or who likely to resign are 46 or 7.8% The model was tested and evaluated to check accuracy of result through confusion matrix cross validation technique which yielded an accuracy percentage of 84.69%. 

[...] Read more.
Other Articles