سامانه پشتیبانی خدمات اطلاعات

  اخبار و اعلانات

 آمار

تعداد نشریات162
تعداد شماره‌ها6,692
تعداد مقالات72,229
تعداد مشاهده مقاله129,180,670
تعداد دریافت فایل اصل مقاله102,008,979
Taher Mazandarani, Maryam, Zand, Zahra, Khodabandelou, Mohammad Hossein, Mozaffari, Fatemeh, Sohrabi, Babak. (1403). Predicting Student Academic Performance: A Machine Learning Approach and Feature Analysis. , (), -. doi: 10.22059/ijms.2025.362506.676053
Maryam Taher Mazandarani; Zahra Zand; Mohammad Hossein Khodabandelou; Fatemeh Mozaffari; Babak Sohrabi. "Predicting Student Academic Performance: A Machine Learning Approach and Feature Analysis". , , , 1403, -. doi: 10.22059/ijms.2025.362506.676053
Taher Mazandarani, Maryam, Zand, Zahra, Khodabandelou, Mohammad Hossein, Mozaffari, Fatemeh, Sohrabi, Babak. (1403). 'Predicting Student Academic Performance: A Machine Learning Approach and Feature Analysis', , (), pp. -. doi: 10.22059/ijms.2025.362506.676053
Taher Mazandarani, Maryam, Zand, Zahra, Khodabandelou, Mohammad Hossein, Mozaffari, Fatemeh, Sohrabi, Babak. Predicting Student Academic Performance: A Machine Learning Approach and Feature Analysis. , 1403; (): -. doi: 10.22059/ijms.2025.362506.676053

Predicting Student Academic Performance: A Machine Learning Approach and Feature Analysis

Interdisciplinary Journal of Management Studies
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 27 بهمن 1403
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22059/ijms.2025.362506.676053
نویسندگان
Maryam Taher Mazandarani1؛ Zahra Zand1؛ Mohammad Hossein Khodabandelou2؛ Fatemeh Mozaffari1؛ Babak Sohrabi* 3
1Department of Information Technology Management, University of Tehran, Tehran, Iran
2Department of Industrial Management, Islamic Azad University, Tehran, Iran
3Faculty of Management, University of Tehran
چکیده
Predicting student academic performance is a challenging task and, at the same time, has significant implications for educators and policymakers in the education field. By utilizing machine learning techniques, this article tries to explore the relationship between various features in six categories, i.e., demographic factors, personality traits, skills, favorite activities, relations with others, out-of-school activities on the one hand, and academic performance in terms of GPA, on the other. Data utilized in this study has been collected through several surveys in one of the schools in Iran over multiple years and educational levels, which form the basis of the analysis. Using CRISP-DM methodology, a predictive model is developed based on CatBoost Regressor. A predictive model with 0.87 R-squared is developed. Moreover, the analysis of features' importance reveals that positive personality traits such as "Interest in studying," "Quality of homework," "Contentment," "Self-regulation," and "Logical thinking and reasoning" skills are among the most predictive features affecting the students' academic performance which rooted in and supported by some of the famous psychological theories such as Self-Determination Theory. This study is unique in this field due to various features and data collection in different years and stages.
کلیدواژه‌ها
Educational Data Mining (EDM)؛ machine learning؛ academic performance؛ intrinsic motivation؛ regression algorithms
آمار
تعداد مشاهده مقاله: 117





سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب