Abstract:
This study aims to develop an AI system that predicts students' success in gaining admission to UNSW Medical School. University application process is often characterized by uncertainty and extensive preparation. Predictive systems can help students understand their strengths and weaknesses, allowing for more efficient resource allocation and stress reduction (Williams et al., 2021).
This project utilizes advanced Artificial Neural Networks (ANNs) for accurate predictions, which is known for high accuracy and successful use in fields like finance (Huang et al., 2007). The AI model, leveraging Auto Machine Learning (AML) from Google Cloud, will be trained with relevant application data and validated by comparing predictions to actual outcomes. Students’ stress levels, in a two-group setting (control and treatment groups), will also be assessed via questionnaires. The results will reveal the AI's potential in alleviating application-related stress, aiding students in adjusting their study plans and fostering empowerment through self-knowledge. Overall, the project is expected to yield measurable outcomes in AI accuracy and stress reduction, making it suitable for applications to admission process of other majors/schools.
Huang, W., Lai, K. K., Nakamori, Y., Wang, S., & Yu, L. (2007). Neural networks in finance and economics forecasting. International Journal of Information Technology & Decision Making, 6(1), 113–140.
Williams, C., Perez, M. A., Vapiwala, N., & Shea, J. A. (2021). The impact of socioeconomic factors on medical school acceptance rates. Academic Medicine, 96(11S), S219–S220.
This project utilizes advanced Artificial Neural Networks (ANNs) for accurate predictions, which is known for high accuracy and successful use in fields like finance (Huang et al., 2007). The AI model, leveraging Auto Machine Learning (AML) from Google Cloud, will be trained with relevant application data and validated by comparing predictions to actual outcomes. Students’ stress levels, in a two-group setting (control and treatment groups), will also be assessed via questionnaires. The results will reveal the AI's potential in alleviating application-related stress, aiding students in adjusting their study plans and fostering empowerment through self-knowledge. Overall, the project is expected to yield measurable outcomes in AI accuracy and stress reduction, making it suitable for applications to admission process of other majors/schools.
Huang, W., Lai, K. K., Nakamori, Y., Wang, S., & Yu, L. (2007). Neural networks in finance and economics forecasting. International Journal of Information Technology & Decision Making, 6(1), 113–140.
Williams, C., Perez, M. A., Vapiwala, N., & Shea, J. A. (2021). The impact of socioeconomic factors on medical school acceptance rates. Academic Medicine, 96(11S), S219–S220.