Using advanced machine learning algorithms to predict academic major completion: A cross-sectional study

• Published in: Computers in biology and medicine 2025-01, Vol.184, p.109372, Article 109372
• Main Authors: Kordbagheri, Alireza, Kordbagheri, Mohammadreza, Tayim, Natalie, Fakhrou, Abdulnaser, Davoudi, Mohammadreza
• Format: Article
• Language: English
• Subjects: Academic achievement; Academic performance; Accuracy; Adult; Algorithms; Artificial intelligence; Behavioral sciences; Colleges & universities; Complexity; Cross-Sectional Studies; Female; Humans; K-nearest neighbors algorithm; Learning algorithms; Machine Learning; Male; Personality; Personality disorders; Personality traits; Predictions; Psychology; Regression analysis; Regression models; Resampling; Self-efficacy; Students; Success; Traits; Universities; Variables
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109372

Existing prediction methods for academic majors based on personality traits have notable gaps, including limited model complexity and generalizability.The current study aimed to utilize advanced Machine Learning (ML) algorithms with smoothing functions to predict academic majors completed based on personality subscales. We used reports from 59,413 individuals to perform the current study. All advanced algorithms implemented in this article were based on R software (version 4.1.3, R Core Team, 2021). All model parameters were optimized based on resampling and cross-validation (CV). In addition, pseudo-R2 as a robust metric has been used to compare the performance of models, which, unlike most studies, considers the quality of model-predicted probabilities. The results indicated that advanced ML models' performance on training and test data was superior to logistic regression. Pseudo-R2 and AUC results showed that advanced models such as kNN, GBE, and RF had the highest scores based on test data compared to other models. The pseudo-R2 values for the models used in this study varied across the test dataset; the lowest value belonged to the logistic regression algorithm at .022, and the highest value was recorded for the kNN algorithm at .099. The agreeableness subscale is the most influential component in predicting the completion of university education, followed by conscientiousness and emotional stability. The potential of advanced methods to enhance the accuracy and validity of predictions is a promising development in our field. Their performance, particularly in handling large data sets with complex patterns, is a reason for optimism about the future of research in this area. •Predict advanced machine learning algorithms in psychological assessment and compare them with traditional approaches.•Applying techniques and concepts of artificial intelligence and machine learning instead of developing and designing tests for psychological assessment.•Using probabilistic approaches such as pseudo R2 for evaluating models.•The model fitting parameters were meticulously tuned for all models using resampling and cross-validation (CV), ensuring the robustness and reliability of our research.•The agreeableness subscale emerged as the most influential component in predicting the completion of university education, followed by conscientiousness and emotional stability. This finding opens up intriguing possibilities for further research and potential implications for e