PREDICTING SALARY OUTCOME IN THE FIELD OF DATA SCIENCES WITH EXTREME GRADIENT BOOSTING ALGORITHM

ERPAPALEMLAH, MUHAMMAD ANDRY and Yusliani, Novi and Rizqie, M. Qurhanul (2023) PREDICTING SALARY OUTCOME IN THE FIELD OF DATA SCIENCES WITH EXTREME GRADIENT BOOSTING ALGORITHM. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021381823094.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021381823094_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021381823094_0008118205_0203128701_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021381823094_0008118205_0203128701_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (170kB) | Request a copy
	Text RAMA_55201_09021381823094_0008118205_0203128701_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (116kB) | Request a copy
	Text RAMA_55201_09021381823094_0008118205_0203128701_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (529kB) | Request a copy
	Text RAMA_55201_09021381823094_0008118205_0203128701_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (204kB) | Request a copy
	Text RAMA_55201_09021381823094_0008118205_0203128701_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (30kB) | Request a copy
	Text RAMA_55201_09021381823094_0008118205_0203128701_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (99kB) | Request a copy

Abstract

In this study, the crucial aspect of job marketing was addressed, specifically the need for accurate salary predictions based on job seekers' skills. It is vital to minimize disparities between applicants' actual abilities and their salary expectations to ensure fairness and transparency in the hiring process. To tackle this challenge, the development of a salary prediction system tailored to data science jobs within the data science domain was proposed. This system would provide employers with valuable insights into the appropriate compensation they could offer to potential employees, considering their skill levels and expertise. To achieve this goal, the Extreme Gradient Boosting Algorithm was implemented into the system, leveraging its powerful predictive capabilities. Employing this algorithm, was aimed to enhance the accuracy and reliability of the salary predictions, ultimately facilitating better decision-making for both job seekers and employers. The findings from the Scenarios conducted show that the metric evaluation of the system is highly promising. The impressive mean absolute errors (MAE) of 0.321, 0.316, and 0.325 for Scenario 1, Scenario 2, and Scenario 3, respectively, indicate that the model's predictions are remarkably close to the actual salary values. Additionally, the mean absolute percentage errors (MAPE) of 2.856%, 2.797%, and 2.871% further confirm the system's exceptional accuracy in predicting salary outcomes for data science jobs

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Job Marketing
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Andry Erpapalemlah
Date Deposited:	21 Aug 2023 07:28
Last Modified:	21 Aug 2023 07:28
URI:	http://repository.unsri.ac.id/id/eprint/127309

Actions (login required)

View Item