Viability Study of Machine Learning Models to Identify Talented Students at the Early Stage of Their College Study.
Saved in:
| Title: | Viability Study of Machine Learning Models to Identify Talented Students at the Early Stage of Their College Study. |
|---|---|
| Authors: | Wu, Qixuan1 (AUTHOR), Chang, Hyung Jae2 (AUTHOR) hjchang@troy.edu, Ma, Long2 (AUTHOR) |
| Source: | Journal of Advanced Academics. Nov2025, Vol. 36 Issue 4, p766-787. 22p. |
| Subject Terms: | *Talented students, *Machine learning, *Higher education, *Academic achievement, *Computer science, *Ability grouping (Education), *Data analysis, Classification algorithms |
| Abstract: | It is very important to identify talented students as soon as they are admitted to college so that appropriate resources are provided and allocated to them to optimize and excel in their education. Currently, this process is labor-intensive and time-consuming, as it involves manual reviews of each student's academic record. This raises the question "Is there any way to automate this process by using computers and AI methodology as tools?" In this study, we answer this question by showing various machine learning models used to analyze students' academic data to identify talented students. For this, various academic data for Computer Science undergraduate students at Troy University is collected and used to train several machine learning-based classification models to identify/predict talented students. Moreover, 90% of the data was used to train the model, while the remaining 10% was used to verify our hypothesis; the model could identify talented Computer Science students based on various aspects of their past academic histories. This division ensures that the model is trained on a substantial portion of the data while retaining a separate set for unbiased evaluation of its performance. By training several machine learning-based classification models and analyzing the results, we confirmed that the models could be used to identify/predict talented students based on their academic performance in the past by carefully selecting features for the models. In addition, the models can also detect false positives. This means it can filter out students who were initially identified as talented but ultimately proven to be "not talented" during their college studies. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Advanced Academics is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Education Research Complete |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | It is very important to identify talented students as soon as they are admitted to college so that appropriate resources are provided and allocated to them to optimize and excel in their education. Currently, this process is labor-intensive and time-consuming, as it involves manual reviews of each student's academic record. This raises the question "Is there any way to automate this process by using computers and AI methodology as tools?" In this study, we answer this question by showing various machine learning models used to analyze students' academic data to identify talented students. For this, various academic data for Computer Science undergraduate students at Troy University is collected and used to train several machine learning-based classification models to identify/predict talented students. Moreover, 90% of the data was used to train the model, while the remaining 10% was used to verify our hypothesis; the model could identify talented Computer Science students based on various aspects of their past academic histories. This division ensures that the model is trained on a substantial portion of the data while retaining a separate set for unbiased evaluation of its performance. By training several machine learning-based classification models and analyzing the results, we confirmed that the models could be used to identify/predict talented students based on their academic performance in the past by carefully selecting features for the models. In addition, the models can also detect false positives. This means it can filter out students who were initially identified as talented but ultimately proven to be "not talented" during their college studies. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 1932202X |
| DOI: | 10.1177/1932202X251362944 |
