Computational Statistics and Machine Learning Techniques for Effective Decision Making on Student’s Employment for Real-Time
Open Access
- 21 May 2021
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 9 (11) , 1166
Abstract
The present study accentuated a hybrid approach to evaluate the impact, association and discrepancies of demographic characteristics on a student’s job placement. The present study extracted several significant academic features that determine the Master of Business Administration (MBA) student placement and confirm the placed gender. This paper recommended a novel futuristic roadmap for students, parents, guardians, institutions, and companies to benefit at a certain level. Out of seven experiments, the first five experiments were conducted with deep statistical computations, and the last two experiments were performed with supervised machine learning approaches. On the one hand, the Support Vector Machine (SVM) outperformed others with the uppermost accuracy of 90% to predict the employment status. On the other hand, the Random Forest (RF) attained a maximum accuracy of 88% to recognize the gender of placed students. Further, several significant features are also recommended to identify the placement of gender and placement status. A statistical t-test at 0.05 significance level proved that the student’s gender did not influence their offered salary during job placement and MBA specializations Marketing and Finance (Mkt&Fin) and Marketing and Human Resource (Mkt&HR) (p > 0.05). Additionally, the result of the t-test also showed that gender did not affect student’s placement test percentage scores (p > 0.05) and degree streams such as Science and Technology (Sci&Tech), Commerce and Management (Comm&Mgmt). Others did not affect the offered salary (p > 0.05). Further, the test revealed a significant association between a student’s course specialization and student’s placement status (p < 0.05). It also proved that there is no significant association between a student’s degree and placement status (p > 0.05). The current study recommended automatic placement prediction with demographic impact identification for the higher educational universities and institutions that will help human communities (students, teachers, parents, institutions) to prepare for the future accordingly.
Keywords
This publication has 39 references indexed in Scilit:
- XGBoost-Based Algorithm Interpretation and Application on Post-Fault Transient Stability Status Prediction of Power SystemIEEE Access, 2019
- Educational data mining for student placement prediction using machine learning algorithmsInternational Journal of Engineering & Technology, 2017
- A Machine Learning Approach for Tracking and Predicting Student Performance in Degree ProgramsIEEE Journal of Selected Topics in Signal Processing, 2017
- Gender difference towards information and communication technology awareness in Indian universitiesSpringerPlus, 2016
- Teaching Programming in the Higher Education not for Engineering StudentsProcedia - Social and Behavioral Sciences, 2013
- Predicting and analyzing secondary education placement-test scores: A data mining approachExpert Systems with Applications, 2012
- RECENT ADVANCES ON SUPPORT VECTOR MACHINES RESEARCHTechnological and Economic Development of Economy, 2012
- Applications of Chi-Square Test and Contingency Table Analysis in Customer Satisfaction and Empirical Analyses2009
- Random ForestsMachine Learning, 2001
- Gender differences in Scholastic Aptitude Test: Mathematics problem solving among high-ability students.Journal of Educational Psychology, 1994