PERSONALIZED CAREER RECOMMENDATION SYSTEM USING MACHINE

LEARNING
Mrs. Siddoju Divya *1, Mrs. VNS Manaswini*2
*1
Student Department of Computer Science and Engineering, Siddhartha Institute of Technology and Science
(Autonomous)Korremula Road, Narapally, Hyderabad
*2
Assistant Professor, Department of Computer Science and Engineering, Siddhartha Institute of Technology
and Science (Autonomous)Korremula Road, Narapally, Hyderabad

ABSTRACT
Choosing the right career path is a major decision, particularly for students and young professionals, who often struggle
with uncertainty due to the growing number of career options and rapidly evolving industry demands. Traditional
career counseling methods are typically generic and may not cater to individual strengths and preferences. This study
introduces a machine learning-based system designed to provide personalized career recommendations. The system
utilizes input features such as academic performance, skills, interests, personality traits, and extracurricular activities. A
comprehensive dataset was compiled from academic records, psychometric assessments, and user-submitted profiles.
Supervised machine learning algorithms—Decision Trees, Random Forests, Support Vector Machines (SVM), K-Nearest
Neighbors (KNN), and Neural Networks—were implemented and compared to determine the most effective model.
Feature preprocessing techniques, including normalization, one-hot encoding, and Principal Component Analysis (PCA),
were applied to improve model accuracy. The system predicts top career paths for users and offers explanations behind
the predictions. Results demonstrate that machine learning can significantly enhance the accuracy and relevance of
career guidance, offering a scalable and personalized alternative to conventional methods. The proposed model also has
potential for integration into academic and e-learning platforms to support broader access.
Keywords: Career prediction, Machine learning, Supervised learning, Personalization, Psychometric data, educational
technology

[Link]
Choosing the right career path is a crucial decision that significantly impacts an individual's future. However, with a
wide range of options available today, students and job seekers often face confusion and uncertainty. Traditional career
guidance methods, which rely on aptitude tests and counseling, can be time-consuming and may not always reflect real-
world opportunities or individual potential accurately.
Machine Learning (ML), a branch of Artificial Intelligence, offers a promising solution to this problem. By analyzing large
datasets containing academic records, personal interests, skill sets, and past career outcomes, ML models can identify
patterns and make intelligent predictions about suitable career paths for individuals. These systems can provide
personalized career suggestions based on a user's input, helping them make more informed decisions.
In this project, we explore the development of a machine learning-based career prediction system that aims to
recommend appropriate career options based on various input features. This not only enhances decision-making but
also promotes efficient career planning tailored to the individual's strengths and preferences.

1
OBJECTIVES
 Design and implement a machine learning model to predict suitable career options based on academic
performance, interests, and skill profiles.
 Collect, clean, and preprocess data relevant to career outcomes for training and validating ML models.
 Compare several ML algorithms (e.g. Decision Trees, Random Forest, KNN) to identify the most accurate for
career prediction.
 Develop a user-friendly interface (web or desktop) for inputting user data and displaying career
recommendations.
 Provide actionable, data-driven guidance to reduce uncertainty in career selection.
 Ensure the framework is scalable and adaptable to different educational systems and demographic groups.
 Aid career planning for underrepresented or rural students with limited access to expert counselors.

SCOPE OF THE PROJECT

This project involves the creation of a supervised machine learning system for career guidance. The focus is on high
school and early university students, along with early-career job seekers. The system will analyze individual profiles—
including academic grades, skills, and interests—to suggest matching career paths.
Key stages include data gathering from varied sources, preprocessing for quality and consistency, model training and
validation using different classification techniques, selection of the optimal model, and deployment with an accessible
interface. The system will be designed for continuous improvement via retraining with new data and adaptation to
diverse educational regions or demographics.

[Link] DESIGN
ARCHITECTURE:

Architecture
A career prediction system starts with collecting various types of user data, such as personal details, academic records,
skills, interests, and personality traits. This information is essential because it forms the foundation for understanding the
user’s background and preferences. The data is then preprocessed to clean errors, fill missing values, and convert different
types of information into formats that machine learning algorithms can process efficiently. This step also includes selecting
the most important features that influence career outcomes.
2
Next, the preprocessed data is fed into the modeling layer, where machine learning algorithms analyze the information to
find patterns linking user profiles to suitable careers. Common techniques include classification models like decision
trees and neural networks, which categorize users into career options, or clustering methods that group similar careers
together. The models are trained on historical data containing previous users’ profiles and their chosen career paths,
enabling the system to make informed predictions for new users.
Finally, the system generates career recommendations by scoring and ranking options based on the user’s profile. These
suggestions are presented through an interactive interface that explains the suitability of each career choice. User
feedback is collected to improve future predictions, making the system more personalized and accurate over time.
Overall, this layered architecture ensures that users receive data- driven, customized career guidance in a user-friendly
manner.

[Link] METHODOLOGIES
Testing methodologies for a Career Prediction System include several approaches to ensure the system is reliable and
effective. Unit testing focuses on verifying individual components, such as input validation or prediction algorithms,
work as intended. Integration testing checks how different modules interact, ensuring data flows correctly between the
user interface, backend, and database. System testing evaluates the complete system’s overall functionality and
performance under real- world conditions. User acceptance testing (UAT) involves actual users testing the system to
confirm it meets their needs and expectations. Together, these methodologies help identify and fix defects early,
improving the system’s accuracy and user experience.
 Unit testing verifies individual components work correctly.
 Integration testing ensures smooth interaction between system modules.
 User acceptance testing checks if the system meets real user needs.

[Link] SCREENS
HOME PAGE

3
FEATURES

FINAL OUTPUTS

4
 [Link]
The Career Prediction System using Machine Learning represents a significant advancement in the domain of career
guidance and student support. By integrating intelligent algorithms with a user- friendly interface, the system
overcomes the limitations of traditional career counseling, which often relies on generalized suggestions and manual
effort. Instead, this system offers personalized, accurate, and real-time career recommendations tailored to each
individual’s academic performance, skills, and interests.
The use of machine learning allows the system to continuously improve and adapt to new data, ensuring that the
recommendations remain relevant to the evolving job market. The web-based platform ensures accessibility for a wide
range of users, including students, career counselors, and administrators, making it a scalable solution for educational
institutions and career advisory services. Furthermore, the feedback mechanism enhances the accuracy and
effectiveness of the model over time.
This project not only demonstrates the practical application of data science and artificial intelligence in education and
career planning but also emphasizes the importance of empowering individuals to make informed and confident career
choices. With further development, such systems can be expanded to include more features like resume building,
industry insights, and learning resource suggestions, making them a comprehensive career development tool.

[Link]
[1] Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018). MesoNet: a Compact Facial Video Forgery Detection
Network. IEEE International Workshop on Information Forensics and Security (WIFS).

[2] Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2019).

FaceForensics++: Learning to detect manipulated facial images. ICCV.

[3] Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. CVPR.

[4] Nguyen, T. T., Nguyen, C. M., Nguyen, D. T., Nguyen, D. T., & Nahavandi, S. (2019). Deep Learning for Deepfakes
Creation and Detection: A Survey. arXiv:1909.11573.

[5] Sabir, E., Cheng, J., Jaiswal, A., AbdAlmageed, W., Masi, I., & Natarajan, P. (2019). Recurrent Convolutional Strategies
for Face Manipulation Detection in Videos. arXiv:1905.00582.

[6] Li, Y., Chang, M. C., & Lyu, S. (2020). Exposing DeepFake Videos By Detecting Face Warping Artifacts. CVPR.
[7] Kumar, A., & Sinha, K. (2020). Career Prediction System Using Machine Learning. IJSRCSEIT, 6(1), 121–126.
[8] Scikit-learn Developers. (2023). Scikit-learn Documentation. Retrieved from [Link] [Link]
[9] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al. (2011).

Scikit-learn: Machine Learning in Python. JMLR, 12, 2825–2830.

[10] Microsoft Docs. (2023). Visual Studio Code Documentation. Retrieved from
[Link]

[11] Raschka, S. (2015). Python Machine Learning. Packt Publishing.

[12] Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow.

O’Reilly Media.

[13] Duda, R. O., Hart, P. E., & Stork, D. G. (2001). Pattern Classification. Wiley.

5
6