Advertisement

Classification Model for Student Performance Amelioration

  • Stewart MuchuchutiEmail author
  • Lakshmi Narasimhan
  • Freedmore Sidume
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 69)

Abstract

Higher Educational Institutes (HEI) still experience a myriad of challenges with student performance ranging from low student achievements, dropouts, high levels of unemployment among others. These institutes collect lots of potentially useful data as they admit students, process their progression and eventually graduate them. Analyzing student performance, though complex, offers huge benefits to all stakeholders involved, students, parents, government and financiers. It has the potential to increase student success, optimize on use of resources, financial or otherwise. This paper compares various classification algorithms for student performance prediction and amelioration. Five classifiers were fitted on a 124-observation, 10 feature, Computer Systems Engineering students’ data spanning from 2010 to 2017, on the WEKA data mining workbench, an open source machine learning platform. The student data consisted of 9 predictor variables representing year 1 and 2 students results in the business, programming, mathematics, research and systems thematic areas. The class variable was the final degree classification. The NaiveBayse classifier had an overall superior performance, over 5 performance metrics, compared to the rest of the classifiers. Feature selection algorithms were used to reduce the feature vectors from 9 to 4 resulting in improvements in computational efficiency but with insignificant classifier performance degradation. The results obtained help to predict the final performance of students in time to design interventions that have the potential of improving their final grade. The identification of critical features will help in prioritization of resource allocation and in future curriculum revision exercises.

Keywords

Student performance prediction Classification Educational data mining 

References

  1. 1.
    Abu Saa, A.: Educational data mining & students’ performance prediction. Int. J. Adv. Comput. Sci. Appl. 7(5), 212–220 (2016)Google Scholar
  2. 2.
    Algur, S.P., Bhat, P., Ayachit, N.H.: Educational data mining: RT and RF classification models for higher education professional courses. Inf. Eng. Electron. Bus. 2(2), 59–65 (2016)Google Scholar
  3. 3.
    Alshammari, I.A., Aldhafiri, M.D., Al-Shammari, Z.: A meta-analysis of educational data mining on improvements in learning outcomes. Coll. Stud. J. 47(2), 326–333 (2013)Google Scholar
  4. 4.
    Asif, R., Merceron, A., Ali, S.A., Haider, N.G.: Analyzing undergraduate students’ performance using educational data mining. Comput. Educ. 113, 177–194 (2017)CrossRefGoogle Scholar
  5. 5.
    Dietz-Uhler, B., Hurn, J.: Using learning analytics to predict (and improve) student success: a faculty perspective. J. Interact. Online Learn. 12(1), 17–26 (2013)Google Scholar
  6. 6.
    Harb, H.M., Moustafa, M.A.: Selecting optimal subset of features for student performance model. Int. J. Comput. Sci. Issues 9(5), 253–262 (2012)Google Scholar
  7. 7.
    Alfiani, A.P., Wulandari, F.A.: Mapping student’s performance based on data mining approach (a case study). Agric. Agric. Sci. Proc. 3, 173–177 (2015)Google Scholar
  8. 8.
    Kabakchieva, D.: Predicting student performance by using data mining methods for classification. Cybern. Inf. Technol. 13(1), 61–72 (2013)Google Scholar
  9. 9.
    Kılıç Depren, S., Aşkın, Ö.E., Öz, E.: Identifying the classification performances of educational data mining methods: a case study for TIMSS. Educ. Sci.: Theory Pract. 17(5), 1605–1623 (2017)Google Scholar
  10. 10.
    Kotsiantis, S.B.: Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades. Artif. Intell. Rev. 37(4), 331–344 (2012)CrossRefGoogle Scholar
  11. 11.
    Kumar Pal, A., Pal, S.: Classification model of prediction for placement of students. Int. J. Mod. Educ. Comput. Sci. 5(11), 49–56 (2013)CrossRefGoogle Scholar
  12. 12.
    Lee, S., Harrison, M.C., Pell, G., Robinson, C.L.: Predicting performance of first year engineering students and the importance of assessment tools therein. Eng. Educ. 3(1), 44–51 (2008)CrossRefGoogle Scholar
  13. 13.
    Madhubala, V., Jeya, T.: Educational data mining and student’ s performance prediction. Int. J. Comput. Eng. Appl. 12(1), 54–59 (2018)Google Scholar
  14. 14.
    Márquez-Vera, C., Cano, A., Romero, C., Ventura, S.: Predicting student failure at school using genetic programming and different data mining approaches with high dimensional and imbalanced data. Appl. Intell. 38(3), 315–330 (2013)CrossRefGoogle Scholar
  15. 15.
    Onan, A., Bal, V., Bayam, B.Y.: The use of data mining for strategic management: a case study on mining association rules in student information system. Croatian J. Educ. 18(1), 41–70 (2016)CrossRefGoogle Scholar
  16. 16.
    Padhy, N., Mishra, P., Panigrahi, R.: The survey of data mining applications and feature scope. Int. J. Comput. Sci. Eng. Inf. 2(3), 43–58 (2012)Google Scholar
  17. 17.
    Qian, Y., Lehman, J.: Students’ misconceptions and other difficulties in introductory programming: a literature review. ACM Trans. Comput. Educ. (TOCE) 18(1), 1 (2017)CrossRefGoogle Scholar
  18. 18.
    Romero, C., Espejo, P.G., Zafra, A., Romero, J.R., Ventura, S.: Web usage mining for predicting final marks of students that use Moodle courses. Comput. Appl. Eng. Educ. 21(1), 135–146 (2013)CrossRefGoogle Scholar
  19. 19.
    Song, J.H., Woo, H.Y.: A study on AQ (adversity quotient), job satisfaction and turnover intention according to work units of clinical nursing staffs in Korea. Indian J. Sci. Technol. 8, 74–78 (2015)CrossRefGoogle Scholar
  20. 20.
    Tair, M.M.A., El-Halees, A.M.: Mining educational data to improve students’ performance: a case study. Int. J. Inf. Commun. Technol. Res. 2, 140–146 (2012)Google Scholar
  21. 21.
    Tekin, A.: Early prediction of students’ grade point averages at graduation: a data mining approach. Eurasian J. Educ. Res. 14(54), 207–226 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Stewart Muchuchuti
    • 1
    Email author
  • Lakshmi Narasimhan
    • 2
  • Freedmore Sidume
    • 1
  1. 1.School of Computing and Information SystemsBotswana Accountancy CollegeGaboroneBotswana
  2. 2.Department of Computer ScienceUniversity of BotswanaGaboroneBotswana

Personalised recommendations