Smart Academic Forecasting Using Data-Driven Approaches

Simple item page
dc.contributor.authorSmita, Most.Nosin Nahar
dc.contributor.authorLipi, Farhana Akter
dc.contributor.authorShrabonti, Sultana Razia
dc.contributor.authorNayeem, Mishkatul
dc.date.accessioned2026-07-13T10:16:29Z
dc.date.issued2025-10-25
dc.descriptionSupervised by Mr. Shahriar Ivan, Assistant Professor, Islamic University of Technology (IUT), Board Bazar, Gazipur-1704, Bangladesh This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Technical and Vocational Education, 2025
dc.description.abstractProper prediction of student academic performance is critical to supporting timely interventions and improving learning results. The article is an evaluation of clas sical machine learning models, including Logistic Regression, Decision Tree, Ran dom Forest, K-Nearest Neighbors, and Support Vector Machine, and a transformer based foundation model based on benchmark academic performance datasets. Transformer-based approach had the best predictive accuracy, whereas Decision Tree provided a good compromise between predictive accuracy and Interpretability. Be sides model benchmarking, the study was aimed at exploring the importance of fea tures in addition to analysing Principal Component Analysis (PCA) and Linear Dis criminant Analysis (LDA). These methods pointed out that behavioral attributes like participation, resource use and absence days were the strongest predictors of perfor mance. The consistency of these results was validated on another dataset and the strength of the feature analysis was established. On the whole the study shows that predictive modeling combined with dimensionality reduction gives reliable and ex plainable information that can be used to build trustworthy academic prediction sys tems.
dc.identifier.citation[1] H. Abdi and L. J. Williams, “Principal component analysis,” Wiley interdisci plinary reviews: computational statistics, vol. 2, no. 4, pp. 433–459, 2010. [2] G.Akçapınar,A.Altun,andP.Aşkar,“Usinglearninganalyticstodevelopearly warning system for at-riskstudents,”InternationalJournalofEducationalTech nology in Higher Education, vol. 16, no. 1, pp. 1–20, 2019. [3] K. Ali et al., “Fusion visualization technique to improve a three-dimensional isotope-selective ct image based on nuclear resonance fluorescence with a gamma-ct image,” Applied Sciences, vol. 11, no. 24, p. 11866, 2021. [4] A. Allahyari et al., “Comparing efficacy and safety of p013, a proposed per tuzumab biosimilar, with the reference product in her2-positive breast can cer patients: A randomized, phase iii, equivalency clinical trial,” BMC cancer, vol. 22, no. 1, p. 960, 2022. [5] E. Alyahyan and D. Düştegör, “Predicting academic success in higher educa tion: Literature review and best practices,” International journal of educational technology in higher education, vol. 17, no. 1, p. 3, 2020. [6] S. Ö. Arik and T. Pfister, “Tabnet: Attentive interpretable tabular learning,” in Proceedings of the AAAI conference on artificial intelligence, vol. 35, 2021, pp. 6679–6687. [7] R.Baker et al., “Data mining for education,” International encyclopedia of edu cation, vol. 7, no. 3, pp. 112–118, 2010. [8] P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. fisher faces: Recognition using class specific linear projection,” IEEE Transactions on pattern analysis and machine intelligence, vol. 19, no. 7, pp. 711–720, 1997. [9] A. Bhusal, “Predicting student’s performance through data mining,” arXiv preprint arXiv:2112.01247, 2021. 31 [10] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” in Proceedings of the fifth annual workshop on Computa tional learning theory, 1992, pp. 144–152. [11] L. Breiman, “Random forests,” Machine learning, vol. 45, no. 1, pp. 5–32, 2001. [12] C.-H. Chen, S. J. Yang, J.-X. Weng, H. Ogata, and C.-Y. Su, “Predicting at-risk university students based on their e-book reading behaviours by using machine learning classifiers,” Australasian Journal of Educational Technology, vol. 37, no. 4, pp. 130–144, 2021. [13] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Pro ceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794. [14] Q.Conley, R. K. Atkinson, F. Nguyen, and B. C. Nelson, “Mantarayar: Leverag ing augmented reality to teach probability and sampling,” Computers & Educa tion, vol. 153, p. 103895, 2020. [15] C.Cortes and V. Vapnik, “Support-vector networks,” Machine learning, vol. 20, no. 3, pp. 273–297, 1995. [16] T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE transac tions on information theory, vol. 13, no. 1, pp. 21–27, 1967. [17] G. W. Dekker, M. Pechenizkiy, and J. M. Vleeshouwers, “Predicting students drop out: A case study,” in Proceedings of the 2nd International Conference on Educational Data Mining, EDM 2009, July 1-3, 2009. Cordoba, Spain, 2009, pp. 41–50. [18] A.Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020. [19] M.Feurer, A. Klein, K. Eggensperger, J. Springenberg, M. Blum, and F. Hutter, “Efficient and robust automated machine learning,” Advances in neural infor mation processing systems, vol. 28, 2015. [20] R.A.Fisher, “The use of multiple measurements in taxonomic problems,” An nals of eugenics, vol. 7, no. 2, pp. 179–188, 1936. [21] Y.Gorishniy,I.Rubachev,V.Khrulkov,andA.Babenko,“Revisitingdeeplearn ing models for tabulardata,”Advancesinneuralinformationprocessingsystems, vol. 34, pp. 18932–18943, 2021. [22] T. Hastie, The elements of statistical learning: Data mining, inference, and pre diction, 2009. 32 [23] T.Hofmann,B.Schölkopf,andA.J.Smola,“Kernelmethodsinmachinelearn ing,” 2008. [24] N.Hollmann,S.Müller,K.Eggensperger,andF.Hutter,“Tabpfn:Atransformer that solves small tabular classification problems in a second,” arXiv preprint arXiv:2207.01848, 2022. [25] D.W.HosmerJr,S.Lemeshow,andR.X.Sturdivant,Appliedlogisticregression. John Wiley & Sons, 2013. [26] I.T.Jolliffe and J. Cadima, “Principal component analysis: A review and recent developments,” Philosophical transactions of the royal society A: Mathematical, Physical and Engineering Sciences, vol. 374, no. 2065, p. 20150202, 2016. [27] D. Kabakchieva, “Predicting student performance by using data mining meth ods for classification,” Cybernetics and information technologies, vol. 13, no. 1, pp. 61–72, 2013. [28] G.Keetal., “Lightgbm: A highly efficient gradient boosting decision tree,” Ad vances in neural information processing systems, vol. 30, 2017. [29] S. Kotsiantis, C. Pierrakeas, and P. Pintelas, “Predicting students’performance in distance learning using machine learning techniques,” Applied Artificial In telligence, vol. 18, no. 5, pp. 411–426, 2004. [30] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model pre dictions,” Advances in neural information processing systems, vol. 30, 2017. [31] F.Marbouti, H. A. Diefes-Dux, and K. Madhavan, “Models for early prediction of at-risk students in a course using standards-based grading,” Computers&Ed ucation, vol. 103, pp. 1–15, 2016. [32] H.Pallathadka, A. Wenda,E.Ramirez-Asís, M. Asís-López, J. Flores-Albornoz, and K. Phasinam, “Classification and prediction of student performance data using various machine learning algorithms,” Materials today: proceedings, vol. 80, pp. 3782–3785, 2023. [33] Z. Papamitsiou and A. A. Economides, “Learning analytics and educational data mining in practice: A systematic literature review of empirical evidence,” Journal of educational technology & society, vol. 17, no. 4, pp. 49–64, 2014. [34] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “Cat boost: Unbiased boosting with categorical features,” Advances in neural infor mation processing systems, vol. 31, 2018. [35] J. R. Quinlan, C4. 5: programs for machine learning. Elsevier, 2014. 33 [36] L.V.Ravn-Nielsenetal.,“Effectofanin-hospitalmultifaceted clinical pharma cist intervention on the risk of readmission: Arandomizedclinicaltrial,” JAMA internal medicine, vol. 178, no. 3, pp. 375–382, 2018. [37] M.T.Ribeiro, S. Singh, and C. Guestrin, “" why should i trust you?" explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD in ternational conference on knowledge discovery and data mining, 2016, pp. 1135 1144. [38] C. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Transactions on Systems, Man, and Cybernetics, Part C (applica tions and reviews), vol. 40, no. 6, pp. 601–618, 2010. [39] M. Sakib, S. Mustajab, and M. Alam, “Ensemble deep learning techniques for time series analysis: A comprehensive review, applications, open issues, chal lenges, and future directions,” Cluster Computing, vol. 28, no. 1, p. 73, 2025. [40] A.Silva,“Usingdataminingtopredictsecondaryschoolstudentperformance,” 2008. [41] G. Somepalli, M. Goldblum, A. Schwarzschild, C. B. Bruss, and T. Goldstein, “Saint: Improved neural networks for tabular data via row attention and con trastive pre-training,” arXiv preprint arXiv:2106.01342, 2021. [42] B.Tang,S.Li,andC.Zhao,“Predicting the performance of students using deep ensemble learning,” Journal of Intelligence, vol. 12, no. 12, p. 124, 2024. [43] W.M.VanderAalst, “The application of petri nets to workflow management,” Journal of circuits, systems, and computers, vol. 8, no. 01, pp. 21–66, 1998. [44] A. Vaswani et al., “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017. [45] P. Yadav et al., “Investigation and empirical analysis of transfer learning for industrial iot networks,” IEEE Access, 2024. [46] N.YılmazandB.Sekeroglu,“Studentperformanceclassificationusingartificial intelligence techniques,” in International Conference on Theory and Applica tion of Soft Computing, Computing with Words and Perceptions, Springer, 2019, pp. 596–603.
dc.identifier.urihttps://repository.iutoic-dhaka.edu/handle/123456789/2752
dc.language.isoen
dc.publisherDepartment of Technical and Vocational Education(TVE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
dc.titleSmart Academic Forecasting Using Data-Driven Approaches
dc.typeThesis

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
07 TVE_Smart Academic Forecasting Using Data-Driven Approaches_220032401,220032403,220032405,220032406_.pdf
Size:
1.55 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
Turnitin Report_ _220032401,220032403,220032405,220032406_.pdf
Size:
1.11 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

2025