Documents

The main goal of employee retention is to avoid dysfunctional turnover. When analysing the main reasons why employees leave and when determining the turnover probability, the question rises how turnover can be minimized and which retention strategies have an actual effect on turnover.
To determine the efficacy of different retention strategies, an overview is given of the retention strategies that can be found in literature. Next, uplift techniques are used to test the efficacy of the different strategies. The uplift model is based on random forest estimation. In addition, subgroup analysis is conducted to be able to customize the retention strategies.
Almost all retention strategies are found not effective for the entire population. However, for each strategy, subgroups of the population were determined to learn which strategy works for which type of employee.
The results yield useful information for Human Resources practitioners. The subgroup analysis results in detailed retention information for these practitioners, which allows them to target each employee with the strategies that are most likely to succeed in retaining their employment.
With the uplift techniques, the actual effectiveness of retention strategies is tested on existing data in a Human Resources dataset without supplementary data collection.
Original languageEnglish
Title of host publicationBook of Abstracts 5th Stochastic Modeling Techniques and Data Analysis International Conference - SMTDA2018
EditorsChristos H. Skiadas
PublisherISAST-International Society for the Advancement of Science and Technology
Pages96-96
ISBN (Electronic)978-618-5180-29-4
ISBN (Print)978-618-5180-27-0
Publication statusPublished - 2018
Event5th Stochastic Modeling Techniques and Data Analysis International Conference - Chania, Greece
Duration: 12 Jun 201816 Jun 2018
http://www.smtda.net/smtda2018.html

Conference

Conference5th Stochastic Modeling Techniques and Data Analysis International Conference
Abbreviated titleSMTDA2018
CountryGreece
CityChania
Period12/06/1816/06/18
Internet address

    Research areas

  • retention strategies

ID: 38209377