Job position prediction based on skills and experience using machine learning algorithm / Ezaryf Hamdan
In response to the intensifying competition in the job market, job seekers often grapple with the challenge of identifying the most suitable positions based on their skills and experience. This paper proposes a sophisticated Job Position Prediction system utilizing Machine Learning algorithms and le...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/95550/1/95550.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In response to the intensifying competition in the job market, job seekers often grapple with the challenge of identifying the most suitable positions based on their skills and experience. This paper proposes a sophisticated Job Position Prediction system utilizing Machine Learning algorithms and leveraging data from LinkedIn profiles. The objective is to develop an innovative and user-friendly platform offering accurate job position predictions to aid job seekers in finding optimal career opportunities. The proposed system integrates data processing modules to preprocess and analyse LinkedIn job posting pages, extracting crucial information such as job titles, company names, years of experience, qualifications, and skills. Text preprocessing ensures consistent data representation and facilitates validation. The Machine Learning algorithm, comprising Random Forest, Linear Regression, XGBoost, SVM, and Stacking Ensemble, is embedded in the system for job position predictions based on the analysed data. The algorithm undergoes rigorous training with a vast dataset to ensure high prediction accuracy and reliability. Accessible through a desktop application, the Job Position Prediction System prioritizes userfriendliness for job seekers. Users input their job skills and years of experience, receiving personalized job position predictions as the system analyses the input and provides the most suitable job positions based on LinkedIn data. The success of this project is evaluated using various metrics, including prediction accuracy, precision, recall, and F1 score. Cross-validation techniques are employed to validate the model's performance and ensure robustness. The development and evaluation of the prediction system adhere to a comprehensive research methodology encompassing data understanding, description, preprocessing, feature extraction, and model evaluation. This research culminates in the creation of an efficient and accurate Job Position Prediction System, empowering job seekers with valuable insights to enhance their job search process. |
|---|