فصلنامه علمی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 گروه مهندسی صنایع ، دانشکده فنی و مهندسی، دانشگاه تربت حیدریه، تربت حیدریه ، ایران

2 گروه مهندسی صنایع، دانشکده فنی و مهندسی، دانشگاه فردوسی مشهد، مشهد، ایران

چکیده

پیشینه و اهداف: در حال حاضر پیشرفت­های قابل توجهی در عرصه فناوری اطلاعات و ارتباطات در جوامع مختلف دیده می­شود. با توجه به این پیشرفت­ها، دانشگاه­ها به عنوان یک نهاد پیشرو در عرصه علم، به سمت فرآیندهای الکترونیکی در مسیر مدیریت آموزش حرکت نموده­اند و در محیط­های آموزشی، پایگاه­های اطلاعاتی با حجم اطلاعات زیاد وجود دارد. با تحلیل این داده­های انبوه سیستم­های آموزشی، می­توان روش­هایی را برای بهبود وضعیت آموزشی دانشجویان ارایه داد. داده­کاوی آموزشی به دنبال کشف دانش موجود در داده­های سیستم آموزشی بوده‌است.­ یکی از کاربردهای داده‌کاوی آموزشی، پیش‌بینی عملکرد تحصیلی دانشجویان است. پیش‌بینی عملکرد تحصیلی دانشجویان و ارائه راهکارهای مفید از اهمیت ویژه‌ای در موفقیت نظام‌های آموزشی برخوردار است و می­تواند به تصمیم­گیری درست مدیران، جهت افزایش بازدهی سیستم آموزشی و عملکرد بهتر دانشجویان، کمک شایانی کند. هدف مقاله حاضر، شناسایی شاخص‌های مؤثر بر عملکرد تحصیلی، پیش‌بینی وضعیت تحصیلی دانشجویان با استفاده از تکنیک‌های داده‌کاوی و در نهایت، ارائه روندی جدید برای اصلاح روش انتخاب واحد و راهکارهای آموزشی در جهت افزایش کارایی سیستم آموزش است.
روش‌ها‌: گام­های این پژوهش بر اساس مدل Crisp تعیین شده است. در پژوهش حاضر، پایگاه­داده­ای شامل 9 مجموعه داده از درس­های تخصصی رشته مهندسی صنایع  استفاده شدند. دوره تحصیلی دانشجویان در نظر گرفته شده کارشناسی بوده‌است. شاخص­های تاثیرگذار بر عملکرد دانشجویان، بر اساس تحقیقات قبلی و نظر خبرگان شناسایی شده‌است. داده‌های جمعیت‌شناختی و سوابق تحصیلی دانشجویان مقطع کارشناسی رشته مهندسی صنایع وارد پایگاه داده شدند. پس از پیش‌پردازش داده‌ها، 13 شاخص‌ در نظر گرفته شد و با کمک الگوریتم‌های مختلف، مدل‌های مختلفی برای پیش‌بینی وضعیت تحصیلی دانشجویان در نیمسال بعدی ارائه گردید. مدل­های شبکه بیزی، لوجیت بوست، پارت و درخت تصمیم به عنوان پرکاربردترین الگوریتم های داده­کاوی آموزشی در این پژوهش مورد استفاده قرار گرفته و جهت بررسی عملکرد الگوریتم­ها از دو شاخص صحت و سطح زیر نمودار عملکرد استفاده شد. 9 پایگاه داده دروس در دو حالت دو و چند کلاسه در نظر گرفته‌شدند. در ادامه، مقایسه‌ای میان نتایج حاصل از 4 الگوریتم‌ مختلف صورت گرفته‌است.
یافته‌ها: با توجه به شاخص­های بهره اطلاعات و نسبت بهره، تمامی 13 شاخص در نظر گرفته شده، به عنوان شاخص‌های مؤثر شناسایی شدند. این شاخص­ها عبارتند از: معدل، کل واحدهای گذرانده، تعداد ترم‌های مشروطی، نوع پذیرش، وضعیت تأهل، جنسیت، سال ورود به دانشگاه، سن، محل زندگی، ترم حاضر، نمره درس پیش­نیاز، استاد درس، تکرارد در اخذ واحد. از بین 4 مدل در نظر گرفته شده، بهترین مدل در دسته‌بندی و پیش­بینی عملکرد آموزشی دانشجویان ، الگوریتم Logit Boost شناخته شد. این الگوریتم، در هر دو حالت دو و چندکلاسه براساس شاخص‌های درصد صحت و سطح زیر نمودار ROC عملکرد بهتری از خود نشان داده‌است.
نتیجه‌گیری: با توجه به عملکرد قابل قبول الگوریتم­های داده­کاوی، استفاده از این الگوریتم­ها در پیش­بینی عملکرد دانشجویان مناسب است و  می‌توان مدل پیشنهادی را به عنوان یک ابزار پشتیبان تصمیم‌‌گیری در سیستم‌های آموزشی مورد استفاده قرار داد. در نهایت، با توجه به نتایج به‌دست آمده و نظرخواهی از خبرگان دانشگاهی، فرایند انتخاب واحد، بازطراحی گردید. فرایند ارایه شده با استفاده از داده­های موجود در سیستم­های آموزشی و علم داده‌کاوی، دانش مفیدی  به تصمیم­­گیرندگان جهت تصمیم صحیح و مناسب ارایه می­دهد. تصمیم­گیرندگان می­توانند با بررسی پیش­بینی­های انجام شده توسط الگوریتم داده­کاوی و کسب اطلاعات مفید، تصمیمات مناسب اخذ نمایند، تا سیستم آموزشی بازدهی بیشتری داشته‌باشد. 

کلیدواژه‌ها

عنوان مقاله [English]

Predicting and analyzing the performance of students through data mining techniques to improve academic performance

نویسندگان [English]

  • M. Ghodoosi 1
  • F. Mirsaeedi 2
  • H. Koosha 2

1 Department of industrial Engineering, university of Torbat Heydarieh, Torbat Heydarieh,Iran

2 Department of Industrial Engineering, Ferdowsi University of Mashhad, Iran

چکیده [English]

Background and Objectives: Nowadays, significant advancements in information technology and communication field in different societies are seen. Given that these advancements, universities as a leading institution in the field of science, have moved towards electronic processes in the management of education and educational environments, there are databases with a large amount of information. By analyzing this massive data of educational systems, methods can be provided to improve the educational status of students. Educational data mining has sought to discover the knowledge contained in the data of the educational system. One of the applications of educational data mining is to predict students' academic performance. Predicting students' academic performance and providing useful solutions is of particular importance in the success of educational systems and can help managers make the right decisions to increase the efficiency of the educational system and better student performance. The purpose of this paper is to identify the effective indicators on academic performance, predict students' academic status using data mining techniques, and finally present a new trend for modifying unit selection and educational strategies to increase the efficiency of the education system.
Materials and Methods: steps of this research are determined according to CRISP model. In current research, Databases containing 9 datasets of specialized courses in industrial engineering were used. The students' grade was bachelor's degree. Indicators affecting student performance have been identified based on previous researches and expert opinions. Demographic data and academic records of undergraduate students are entered in database. After data preprocessing, 13 attributes are selected, different models were proposed to predict student's academic status in the next semester. Then, a comparison between the results of 4 different algorithms has been done.
Findings: All 13 attributes are identified to be effective according to information gain and gain ratio. This 13 attributes as follow: GPA, Total passed units, Number of conditional terms, Type of admission, Marital status, Gender, University admission year, Living place , Age, Current semester, Prerequisite course score, instructor of the course, Repeat the course. Between of 4 considered models, the Logit Boost algorithm is known as the best model in categorizing in two class and multi-class according to the accuracy rate and ROC.
Conclusion: Because of acceptable performance of data mining algorithms, the use of these algorithms in predicting student performance is appropriate and the proposed model can be used as a support tool for decision making in educational systems. Finally, according to the obtained results and the opinion of academic experts, the unit selection process was redesigned. The proposed model can be used as a decision support tool in educational systems. Finally, due to the results obtained and the opinions of the academic experts, the process of unit selection was redesigned. The presented process uses the available data in educational systems and data mining science, provides useful knowledge to decision-makers to make the right and appropriate decision. Decision makers can make appropriate decisions by examining the predictions made by the data mining algorithm and obtaining useful information, in order to make the educational system more efficient.

کلیدواژه‌ها [English]

  • Educational data mining
  • unit selection
  • academic performance
  • Logit Boost

[1] Pokay, P., & Blumenfeld, P. C. (1990). Predicting achievement early and late in the semester: the role of motivation and use of learning strategies. Journal of Educational Psychology, 82(1), 41-50.

 [2] Grudnitski, G. (1997). A forecast of achievement from student profile data. Journal of Accounting Education, 15 (4), 549-558.

 [3] Ransdell, S. (2001). Predicting college success: the importance of ability and non-cognitive variables. International Journal of Educational Research, 35 (4), 357-364.

 [4] Asif, R., Merceron, A., Ali, S. A., & Haider, N. G.  (2017). Analyzing undergraduate students' performance using educational data mining. Computers & Education. doi:10.1016/j.compedu.2017.05.007.

 [5] Rostami, M., Ayat, S., Saghari, F., & Yaghoobi, F. (2015). Applying fuzzy clustering to assess and anticipate students' educational progress in learning environments. Technology of education, 10(1), 23-36. (In Persian)

[6] Akour, I. (2010). Factors influencing faculty computer literacy and use in Jordan: A multivariate analysis. D.B.A. dissertation. Louisiana Tech University, United States, Louisiana.

 [7] Sarboland, K. (2019). Providing an e-learning model on teachers' satisfaction of learning in Ardabil Islamic Azad University. Journal of Technology of education, 13(3), 603-614.

 [8] Romero, C., & Ventura, S. (2013). Data mining in education. Wiley Interdiscilinary Review: Data Mining Knowledge Discovery, 3(1), 12-27.

 [9]   Romero, C., & Ventura, S. (2007). Educational data mining: A Survey from 1995 to 2005. Expert Systems with Applications, 33, 135-146.

 [10] Yang, M. (2006). Data Mining Techniques Applied to Texas Woman’s University’s Enrollment data – What Can the Data Tell us? MS Thesis: Texaz Woman’s University.

 [11] Baker, R. (2010). Data mining for Education. International Encyclopedia of Education, 7(3), 112-118.

 [12]Aminbeidokhti, A., Fathian Boroojeni, M., &  Nameni, A. (2017). A Neural Network Based Model for Predicting Educational Vulnerability of Undergraduate Students. Journal of Management and Planning In Educational Systems, 10 (18). 81-102. (In Persian)

 [13]Ranjan, J., & Malik, K. (2007). Effective educational process: a datamining approach. Journal of information and knowledge management systems, 37(4), 502-515.

 [14]Romero, C., Ventura, S., & Garcia, E. (2008). Data mining in course management systems: Moodle case study and tutorial. Computers & Education, 51, 368-384.

 [15]Huang, S., & Fang, N. (2013). Predicting student academic performance in an engineering dynamics course: A comparison of four types of predictive mathematical models. Computers and Education, 61, 133-145.

 [16]Zhang, Y., Oussena, S., Clark, T., & Kim, H.  (2010). Use data mining to improve student retention in higher education – A case study. Proceedings of ICEIS.   

 [17]Sen, B., & Ucar , E. (2012). Evaluating the achievements of computer engineering department of distance education students with data mining methods. Procedia Technology, 1, 262-267.

 [18] Pena-Ayala, A.  (2014). Educational data mining: A survey and a data mining-based analysis of recent works. Expert Systems with Applications, 41, 1426-1432..

 [19] Shahiri, A. M., Husain, W., & Rashid, N. A. (2015). A Review on Predicting Student’s Performance using Data Mining Techniques. The Third Information Systems International Conference. Procedia Computer Science. 72, 414-422.

[20] Rodrigues. M. W. Zarate. L. E. & Isotani, S. (2018). Educational Data Mining: A review of evaluation process in the e-learning, Telematics and Informatics.

 [21] Heydari , S., Yaghini, M. (2011). Classification and prediction of students’ educational status using data mining techniques. Higher Educaion Letter, 12. 107-124. (In Persian)

 [22] Maghsoudi, B., Sulaimany, S., Amiri, A., & Afsharchi, M. (2013). Teaching Quality Improvement of Electronic Learning Systems Using Educational Data Mining. Journal of Technology of Education, 6 (4), 277-286. (In Persian)

 [23] Sen, B., Ucar, E., & Delen, D.  (2012). Predicting and analyzing secondary education placement-test scores: A data mining approach. Expert Systems with Applications, 39, 9468-9476.

 [24] Natek, S., & Zwilling, M. (2014). Student data mining solution–knowledge management system related to higher education institutions. Expert Systems with Applications, 41(14), 6400-6407.

 [25] Strecht, P., Cruz, L., Soares, C., Merdes-Moreria, J., & Abren, R. (2015). A Comparative Study of Classification and Regression Algorithms for Modelling Students’ Academic Performance. Madrid, Spain: 8th International Conference on Educational Data Mining. 392-395.

 [26] Rachburee, N., Punlumjeak, W., Rugtanom, S., Jaithavil, D., & Pracha, M.  (2018). A Prediction of Engineering Students Performance from Core Engineering Course using Classification. Computer science and engineering, 6(7), 43-48.

 [27] Nghe, T. N., Janecek, P., & Haddawy, P. (2007). A Comparative Analysis of Techniques for Predicting Academic Performance. In 37th ASEE /IEEE Frontiers in Education Conference.

 [28] Kabakchieva, D., Stefanova, K., & Kismov, V. S. (2011). Analyzing University Data for Determining Student Profiles and Predicting Performance. In 4th International Conference on Educational Data Mining. the Netherlands.

 [29] Kabakchieva, D. (2013). Predicting Student Performance by Using Data Mining Methods for classification. Cybernetics and Information Technologies, 13(1), 61-72.

 [30] Oskouei, R. J., & Askari, M. (2014). Predicting Academic Performance with Applying Data Mining Techniques (Generalizing the results of two Different Case Studies). Computer Engineering and Applications Journal, 79-88.

 [31] Yehuala, M. A. (2015). Application of Data Mining Techniques for Student Success and Failure Prediction (The Case of Debre Markos University). International Journal of Scientific & Technology Research, 4(4), 91-94.

[32] Kaur, P., Singh, M., & Josan, G. S. (2015). Classification and prediction based data mining algorithms to predict slow learners in education sector. In 3th International Conference on Recent Trends in Computing 2015(ICRTC-2015). Procedia Computer Science, 57, 500-508. 

 [33] Pandey, M., & Taruna, S. (2016). Towards the integration of multipleclassifier pertaining to the Student’sperformance prediction. Perspectives in Science, 8, 364-366.

 [34] Abu Saa, A. (2016). Educational Data Mining & Students’ Performance Prediction. International Journal of Advanced Computer Science and Applications, 5(7). 212-220.

 [35] Yahya, A. A. (2018). Swarm intelligence-based approach for educational data classification. Journal of King Saud University – Computer and Information Sciences.

 [36] Santana, M. A., Costa, E. B., Fonseca, B., Rego, J., & Araujo, F. F.  (2017). Evaluating the effectiveness of educational data mining techniques for early prediction of students' academic failure in introductory programming courses. Computers in Human Behavior.

 [37] Fernandes, e. P., Holanda, M., Victorino, M., Borges, V., Carvalho, R., & Erven, G. V. (2018). Educational data mining: Predictive analysis of academic performance of public school students in the capital of Brazil. Journal of Business Research.

 [38] Wanli, X., Rui, G., Eva, P., & Sean, G. (2015). Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory. Computers in Human Behavior, 47, 168-181.

 [39] Tari, M., Minai, B., Farahi. A., & Niknam Pirzadeh, M. (2011). Prediction of educational performance using CART algorithm, neural network and predictive accuracy increase using combination model. 3rd Iranian Conference on Electrical and Electronics Engineering (ICEEE2011), Gonabad. (In Persian)

  [40] Ahmadi, A., Karimzadgan, D., & Khairati Kazeroon, T. (2015). Data mining of Students Withdrawal at University of Tehran, Focusing on Fee Paid Students (to prevent customer churn). Journal of Information Technology Management, 7 (2). 217-238. (In Persian)

  [41] Rahmati, A., Lesani, M., & Khalilzadeh, R. (2012).The related factors to the students of Shahid Bahonar Kerman in 2009-2010 and its analytical model. Kerman: Shahid Bahonar University,(In Persian)

  [42] Deypir, M., & Raboo. A. (2018). Using Educational Data Mining for Grouping Learners in an E-Learning Environment for Customizing Learning Program. Journal of Management and Planning in Educational Systems, 11 (1), 83-108. (In Persian)

  [43] Shukor, N. A., Tasir, Z., & Meijden, H. V.  (2014). An examination of online learning effectiveness using data mining. Global Conference on Business & Social Science. Kuala Lumpur.

 [44]Buldu, A., & Ucgun, K. (2010). Data mining application on students’ data. Procedia Social and Behavioral Sciences, 2, 5251-5259.

  [45]Abdullah, Z., Herawan, T., Ahmad, N., & Deris, M. M. (2011). Mining significant association rules from educational data using critical relative support approach. Procedia - Social and Behavioral Sciences, 28, 97-101.

  [46] Hamsa, H., Indiradevi, S., & Kizhakkethottam, J. J.  (2016). Student academic performance prediction model using decision tree and fuzzy genetic algorithm. Global Colloquium in recent Advancement and Effectual Researches in Engineering, Science and Technology (RAEREST 2016). Procedia Technology, 25, 326-332.

  [47]Gitue, A. (2014). The intelligent algorithm is to advise on the selection of student units based on the analysis of the chart of courses, the prediction of the grades and the pattern chosen by the previous students. University of Kordestan. (In Persian)

  [48] ElGamal, A. F. (2013). An Educational Data Mining Model for Predicting Student Performance in Programming Course. International Journal of Computer Applications, 70(17), 22-28.

  [49]Wirth, R., & Hipp, J. (2000). CRISP-DM: Towards a Standard Process Model for Data Mining. Proceedings of the Fourth International Conference on the Practical Application of Knowledge Discovery and Data Mining.

  [50]Bagherzadeh, F., Ramezankhani, A., Azizi, F., Hadaegh, F., & Khalili, D. (2015). A tutorial on variable selection for clinical prediction models: Feature selection methods in data-mining could improve the results. Journal of Clinical Epidemiology.

  [51] Cai, Y. D., & Chou, K. C. (2006). Using LogitBoost classifier to predict protein structural classes. Journal Theoretical Biology, 238(1), 172-176.    

  [52]Setayesh, M., Fatahi Nafchi, H., Abaspoor, S., & Roostayi, M. (2014). Providing a New Approach to Issuing Audit Report Using Data Mining (Case Study: Companies Listed in Tehran Stock Exchange). Audit Science, 19 (57), 5-26. (In Persian)  

  [53]Toloui Ashlaghi, A., Nikoumaram, H., & Maghdoori Sharbiani, F. (2010). Classification of applicants for credit facilities of banks using Support Vector Machine. Management Researches, 84, 1-19. (In Persian)

  [54]Han, J., Kamber, M., & Pei, J.  (2012). Data Mining: Concepts and Techniques.( Morgan Kaufman).

  [55]Alimohammadi, A, M. Abbasimehr, M, H. & Javaheri, A. (2016). Prediction of Stock Return Using Financial Ratios: A Decision Tree Approach. Journal of Financial Management Strategy, 3(4), 125-146.

 [56] Hand, D., Mannila, H., & Smyth, P. (2001). Principles of Data Mining. Cambridge: MIT Press.

  [57]  Giudici, P. (2003). Applied data mining: statistical methods for business and industry. New York: John Wiley & Sons Ltd.

  [58]Asif, R., Merceron, A., & Pathan, M. (2015). Predicting student academic performance at degree level: A case study. Intelligent Systems and applications, 1, 49-61.