The week's pick
Reseach Article
Optimizing the k value in the k Nearest Neighbor Algorithm for Academic Prediction of Working Students
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 25 |
| Year of Publication: 2024 |
| Authors: Rakhi Paul, Mithun Das |
10.5120/ijca2024923759
|
Rakhi Paul, Mithun Das . Optimizing the k value in the k Nearest Neighbor Algorithm for Academic Prediction of Working Students. International Journal of Computer Applications. 186, 25 ( Jun 2024), 33-39. DOI=10.5120/ijca2024923759
Abstract
This study highlights the dedication of the institution to cultivating scholastic distinction, specifically among pupils who are managing the concurrent obligations of employment and education. This study endeavors to establish a resilient framework for forecasting and categorizing scholastic achievement by utilizing the K nearest neighbor algorithm and optimizing the value of k via 5-fold cross-validation. By including three distinct label classes—satisfactory, very satisfactory, and with honors—the model's predictive capability is enhanced, providing more nuanced insights into the academic accomplishments of students. Significantly, the accuracy rate of 85.71% achieved in determining k=3 highlights the effectiveness of the proposed methodology in accurately predicting academic outcomes. The results of this study have substantial ramifications for policymakers in academia, providing them with empirical data that can guide the creation of individualized interventions and policies that promote the comprehensive growth of working students. Furthermore, this study makes a valuable contribution to the wider academic conversation regarding predictive analytics in the field of education by providing a balanced analysis of the complex elements that impact student achievement. This study sheds light on potential areas for targeted support and intervention by examining the relationship between employment obligations and academic achievement. As a result, it promotes a more favorable learning environment for every student. Moreover, the incorporation of sophisticated machine learning methods highlights the establishment's dedication to harnessing state-of-the-art approaches to improve academic achievements. The high accuracy rate of the predictive model serves as evidence of the K nearest neighbor algorithm's effectiveness in capturing the intricate dynamics that are intrinsic to the academic trajectories of students. In general, this study signifies a substantial progression in the direction of enhancing educational policies and practices to more effectively address the requirements of a heterogeneous student population, thereby furthering the overarching objective of scholastic distinction and student achievement.
References
- F. Okubo, “A Neural Network Approach for Students ’ Performance Prediction,” no. March, pp. 5–7, 2017, doi: 10.1145/3027385.3029479.
- L. Mahmoud and A. Zohair, “Prediction of Student ’ s performance by modelling small dataset size,” 2019.
- A. Olawoyin, Y. Chen, A. Olawoyin, and Y. Chen, “ScienceDirect ScienceDirect ScienceDirect Predicting the Future with Artificial Neural Network Predicting the Future with Artificial Neural Network,” Procedia Comput. Sci., vol. 140, pp. 383–392, 2018, doi: 10.1016/j.procs.2018.10.300.
- A. A. Aryaguna and D. O. Anggriawan, “Identifikasi Jenis Gangguan Pada Jaringan Distribusi Menggunakan Metode Artificial Neural Network,” no. April, pp. 27–35, 2021.
- Abhijit Pathak, Arnab Chakraborty, Minhajur Rahaman, Taiyaba Shadaka Rafa, and Ummay Nayema, “Enhanced Counterfeit Detection of Bangladesh Currency through Convolutional Neural Networks: A Deep Learning Approach”, IJIRCST, vol. 12, no. 2, pp. 10–20, Mar. 2024.
- A. Çetinkaya and Ö. K. Baykan, “Prediction of middle school students’ programming talent using artificial neural networks,” Eng. Sci. Technol. an Int. J., no. xxxx, 2020, doi: 10.1016/j.jestch.2020.07.005.
- E. Bahadır, “Prediction of Prospective Mathematics Teachers’ Academic Success in Entering Graduate Education by Using Back- propagation Neural Network,” J. Educ. Train. Stud., vol. 4, no. 5, pp. 113–122, 2016, doi: 10.11114/jets.v4i5.1321.
- Ş. Aydoğdu, “Predicting student final performance using artificial neural networks in online learning environments,” 2019, doi: doi.org/10.1007/s10639-019-10053.
- A. Ali and N. Senan, “The Effect of Normalization in Violence Video Classification Performance,” IOP Conf. Ser. Mater. Sci. Eng., vol. 226, no. 1, 2017, doi: 10.1088/1757-899X/226/1/012082.
- Streamlining Visitor Appointments: Automated Scheduling System for BGC Trust University Bangladesh. (2023). International Research Journal of Modernization in Engineering Technology and Science. https://doi.org/10.56726/irjmets44679.
- G. Jiang and W. Wang, “Error estimation based on variance analysis of k-fold cross-validation,” Pattern Recognit., vol. 69, pp. 94– 106, 2017, doi: 10.1016/j.patcog.2017.03.025.
- Ali and N. Senan, “The Effect of Normalization in Violence Video Classification Performance,” IOP Conf. Ser. Mater. Sci. Eng., vol. 226, no. 1, 2017, doi: 10.1088/1757-899X/226/1/012082.
- Hossen, H., Shuvon, M. S. S., Barsha, J. B., Chy, A. A., & Pathak, A. (2023). Ultimate cricket experience: Dynamic web app for a real-time scoring system in university cricket. World Journal of Advanced Research and Reviews, 19(02), 1269–1280. DOI: 10.30574/wjarr.2023.19.2.1721.
- S. Eker, E. Rovenskaya, S. Langan, and M. Obersteiner, “Model validation: A bibliometric analysis of the literature,” Environ. Model. Softw., vol. 117, no. December 2018, pp. 43–54, 2019, doi: 10.1016/j.envsoft.2019.03.009.
- S. Jain, S. Shukla, and R. Wadhvani, “Dynamic selection of normalization techniques using data complexity measures,” Expert Syst. Appl., vol. 106, pp. 252–262, 2018, doi: 10.1016/j.eswa.2018.04.008.
Index Terms
Keywords