Open Access Open Access  Restricted Access Subscription or Fee Access

Predicting the Specialized Areas of Computer Science Students of Bachelor of Science Level Analyzing Academic Statements Using Machine-learning Approaches

Md. Alamgir Hossain, Md. Imtiaz Ahmed, Md. Kawsar Ahmed, Rabeya Sultana, Omlan Jyoti Mondal, Md. Shihabul Islam, Minarul Islam

Abstract


Knowing the specialized fields of students is very much important in this challenging world for the betterment of their future careers. Especially the job and higher education fields of computer science students are going to be multi-dimensional. In this research, a new architecture is introduced for finding the specialized areas of computer science students by analyzing the whole academic statements. The academic courses are divided into ten specific areas depending on the job market. By getting the help of machine learning techniques, the proposed approach will predict the specialized area of any student. For implementing the whole procedure of prediction, TensorFlow, an open-source library developed by Google, is used. In total, 536 samples are used in this research, where 75% as training and 25% are testing data. Depending on the course dimension and divided areas category, different machine learning algorithms are used. From the used algorithms, Linear Regression provides the best result and the accuracy is almost 99%. Finally, the comparisons of the accuracy of the model with different used algorithms and existing models has been shown.


Full Text:

PDF

References


Zahedi L, Lunn S, Pouyanfar S, Ross M, Ohland M. Leveraging Machine-learning Techniques to Analyze Computing Persistence in Undergraduate Programs. In 2020 ASEE Virtual Annual Conference Content Access Proceedings, Virtual On line. 2020 Jun; 34921. doi: 10.18260/1-2--34921.

Hussain S, Dahan NA, Ba-Alwi FM, Ribata N. Educational Data Mining and Analysis of Students’ Academic Performance Using WEKA. Indones J Electr Eng Comput Sci. 2018 Feb; 9(2): 447–459. doi: 10.11591/ijeecs.v9.i2.pp447-459.

Asif R, Merceron A, Ali SA, Haider NG. Analyzing undergraduate students’ performance using educational data mining. Comput Educ. 2017 Oct; 113: 177–194. doi: 10.1016/j.compedu.2017.05.007.

Durik AM, Lovejoy CM, Johnson SJ. A longitudinal study of achievement goals for college in general: Predicting cumulative GPA and diversity in course selection. Contemp Educ Psychol. 2009 Apr; 34(2): 113–119. doi: 10.1016/j.cedpsych.2008.11.002.

Vandamme J-P, Meskens N, Superby J-F. Predicting Academic Performance by Data Mining Methods. Educ Econ. 2007 Dec; 15(4): 405–419. doi: 10.1080/09645290701409939.

Ibrahim W, Abdullaev S, Alkattan H, Adelaja OA, Subhi AA. Development of a Model Using Data Mining Technique to Test, Predict and Obtain Knowledge from the Academics Results of Information Technology Students. Data. 2022 May; 7(5): 67. doi: 10.3390/data7050067.

Kabakchieva D. Predicting Student Performance by Using Data Mining Methods for Classification. Cybern Inf Technol. 2013 Mar; 13(1): 61–72. doi: 10.2478/cait-2013-0006.

Okewu E, Daramola O. Design of a learning analytics system for academic advising in Nigerian universities. In 2017 International Conference on Computing Networking and Informatics (ICCNI). 2017 Oct; 1–8. doi: 10.1109/ICCNI.2017.8123785.

Ognjanovic I, Gasevic D, Dawson S. Using institutional data to predict student course selections in higher education. Internet Higher Educ. 2016 Apr 1;29:49-62. doi: 10.1016/j.iheduc.2015.12.002.

Ashraf A, Anwer S, Khan M. G. A Comparative Study of Predicting Student’s Performance by use of Data Mining Techniques. Am Acad Sci Res J Eng Technol Sci. 2018; 44(8): 122–136.

Zollanvari A, Kizilirmak RC, Kho YH, Hernandez-Torrano D. Predicting Students’ GPA and Developing Intervention Strategies Based on Self-Regulatory Learning Behaviors. IEEE Access. 2017; 5: 23792–23802. doi: 10.1109/ACCESS.2017.2740980.

Luo T, So WWM, Wan ZH, Li WC. STEM stereotypes predict students’ STEM career interest via self-efficacy and outcome expectations. Int J STEM Educ. 2021 Dec; 8(1): 36. doi: 10.1186/s40594-021-00295-y.

Shahiria AM, Husaina W, Rashid NA. A Review on Predicting Student’s Performance using Data Mining Techniques. In The 3rd Information Systems International Conference. 2015; 414–422.

Xu J, Moon KH, Schaar MVD. A machine learning approach for tracking and predicting student performance in degree programs. IEEE J Sel Top Signal Process. 2017; 11(5): 742–753.

Nie M, Xiong Z, Zhong R, Deng W, Yang G. Career Choice Prediction Based on Campus Big Data-Mining the Potential Behavior of College Students. Appl Sci. 2020 Apr; 10(8): 2841. doi: 10.3390/app10082841.

Thapaswini PS. Predicting the Course Knowledge Level of Students using Data Mining Techniques. Int J Sci Res (IJSR). 2021 Aug; 10(8): 1068–1070.

Shetu SF, Saifuzzaman M, Moon NN, Sultana S, Yousuf R. Student’s Performance Prediction Using Data Mining Technique Depending on Overall Academic Status and Environmental Attributes. In International Conference on Innovative Computing and Communications: Proceedings of ICICC 2020. 2020; 757–769.

Ahmed RM, Omran NF, Ali AA. Predicting and analysis of students’ academic performance using data mining techniques. Int J Comput Appl. 2018;975:8887.

Namoun A, Alshanqiti A. Predicting Student Performance Using Data Mining and Learning Analytics Techniques: A Systematic Literature Review. Appl Sci. 2020 Dec; 11(1): 237. doi: 10.3390/app11010237.

Umer R, Susnjak T, Mathrani A, Suriadi S. On predicting academic performance with process mining in learning analytics. J Res Innov Teach Learn. 2017 Jul; 10(2): 160–176. doi: 10.1108/JRIT- 09-2017-0022.

Bhagavan KS, Thangakumar J, Subramanian DV. RETRACTED ARTICLE: Predictive analysis of student academic performance and employability chances using HLVQ algorithm. J Ambient Intell Humaniz Comput. 2021 Mar; 12(3): 3789–3797. doi: 10.1007/s12652-019-01674-8.

Yağcı M. Educational data mining: prediction of students’ academic performance using machine learning algorithms. Smart Learn Environ. 2022 Dec; 9(1): 11. doi: 10.1186/s40561-022-00192-z.

Ahmad Z, Shahzadi E. Prediction of Students’ Academic Performance Using Artificial Neural Network. Bull Educ Res. 2018 Dec; 40(3): 157–164.

Chernykh S, Stepnov A, Lukyanova O. Data Preprocessing for Machine Learning in Seismology. In CEUR Workshop Proceedings (CEUR-WS.org), Khabarovsk, Russia. 2021 Sep; 119–123.

Hasan R, Palaniappan S, Mahmood S, Abbas A, Sarker KU, Sattar MU. Predicting Student Performance in Higher Educational Institutions Using Video Learning Analytics and Data Mining Techniques. Appl Sci. 2020 Jun; 10(11): 3894. doi: 10.3390/app10113894.

Tomasevic N, Gvozdenovic N, Vranes S. An overview and comparison of supervised data mining techniques for student exam performance prediction. Comput Educ. 2020 Jan; 143: 103676. doi: 10.1016/j.compedu.2019.103676.

Saa AA, Al-Emran M, Shaalan K. Factors Affecting Students’ Performance in Higher Education: A Systematic Review of Predictive Data Mining Techniques. Technol Knowl Learn. 2019 Dec; 24(4): 567–598. doi: 10.1007/s10758-019-09408-7.

Kumari K, Yadav S. Linear regression analysis study. J Pract Cardiovasc Sci. 2018; 4(1): 33–36. doi: 10.4103/jpcs.jpcs_8_18.

Awad M, Khanna R. Support Vector Regression. In Efficient Learning Machines. Berkeley, CA: Apress; 2015; 67–80. doi: 10.1007/978-1-4302-5990-9_4.

Rokach L, Maimon O. Decision Trees. In: Maimon O, Rokach L, editors. Data Mining and Knowledge Discovery Handbook. New York: Springer-Verlag; 2005; 165–192. doi: 10.1007/0-387-25465-X_9.

Ho TK. Random decision forests. In Proceedings of 3rd International Conference on Document Analysis and Recognition. 1995; 278–282. doi: 10.1109/ICDAR.1995.598994.

Pedregosa F, et al. Scikit-learn: Machine Learning in Python. J Mach Learn Res. 2011; 12: 2825–2830. [Online]. Available: https://scikit-learn.org/stable/about.html#citing-scikit-learn

Novakovic JĐ, Veljovic A, Ilic Sinisa S, Milos Papic. Experimental study of using the k-nearest neighbour classifier with filter methods. In Computer science and technology. 2016; 90–99.

Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016 Aug; 785–794. doi: 10.1145/2939672.2939785.

Witten IH, Frank E, Hall MA, Pal CJ. Extending instance-based and linear models. In Data Mining. Elsevier; 2017; 243–284. doi: 10.1016/B978-0-12-804291-5.00007-6.

Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011 Nov 1; 12: 2825–30.

Bartlett PL, Long PM, Lugosi G, Tsigler A. Benign overfitting in linear regression. Proc Natl Acad Sci. 2020 Dec; 117(48): 30063–30070. doi: 10.1073/pnas.1907378117.

Rodríguez-Pérez R, Fernández L, Marco S. Overoptimism in cross-validation when using partial least squares-discriminant analysis for omics data: a systematic study. Anal Bioanal Chem. 2018 Sep; 410(23): 5981–5992. doi: 10.1007/s00216-018-1217-1.

Ghojogh B, Crowley M. The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial. arXiv:1905.12787 [stat.ML]. 2019. doi: 10.48550/ARXIV.1905.12787.

Karale DA, Narlawar A, Bhujba B, Bharit S. Student Performance Prediction using AI and ML. Int J Res Appl Sci Eng Technol. 2022 Jun; 10(6): 1644–1650. doi: 10.22214/ijraset.2022.44032.

Mesarić J, Šebalj D. Decision trees for predicting the academic success of students. Croat Oper Res Rev. 2016 Dec; 7(2): 367–388. doi: 10.17535/crorr.2016.0025.

Hayder A. Predicting Student Performance Using Machine Learning: A Comparative Study Between Classification Algorithms. Thesis Project. Sweden: Mid Sweden University; 2022.

Su Y-S, Lin Y-D, Liu T-Q. Applying machine learning technologies to explore students’ learning features and performance prediction. Front Neurosci. 2022 Dec; 16: 1018005. doi: 10.3389/fnins.2022.1018005.

Sudais M, Safwan M, Khalid MA, Ahmed S. Students’ Academic Performance Prediction Model Using Machine Learning. Res Sq. 2022 Jan 25.




DOI: https://doi.org/10.37628/ijocspl.v8i2.883

Refbacks

  • There are currently no refbacks.