dc.contributor.author |
Alwis, Mewan |
|
dc.date.accessioned |
2020-07-24T18:12:45Z |
|
dc.date.available |
2020-07-24T18:12:45Z |
|
dc.date.issued |
2019 |
|
dc.identifier.citation |
Alwis, Mewan (2019) New Employee Attrition prediction in the field of medical marketing personnel in Sri Lanka. MSc. Dissertation Informatics Institute of Technology |
en_US |
dc.identifier.other |
2017036 |
|
dc.identifier.uri |
http://dlib.iit.ac.lk/xmlui/handle/123456789/479 |
|
dc.description.abstract |
Employees are considered as one of the most valuable assets of any organization. Modern day organizations invest considerably on them and therefore unexpected early departures would be costly in terms of money, time and loss of business. Many attempts have been made in the area of attrition prediction but lacks in the scope of new medical marketing rep hiring and the aim is to find a solution. Employee attrition prediction has been researched in the past and mix of algorithms, such as SVM, Logistic Regression, Random Forest and KNN, have been tested for their suitability. Having a unique situation and dataset, this research aims to find suitable algorithm through an optimum parameter selection. This research as able develop a classification model for new employee attrition and a unique dataset with fresh recruiter attrition that performs well at an 70% accuracy. The applications and implications of the classification model applied is debated and assessed in the project report. |
en_US |
dc.subject |
Azure Machine Learning services |
en_US |
dc.subject |
Machine Learning |
en_US |
dc.subject |
Data mining |
en_US |
dc.subject |
Supervised Learning |
en_US |
dc.title |
New Employee Attrition prediction in the field of medical marketing personnel in Sri Lanka |
en_US |
dc.type |
Thesis |
en_US |