پیش بینی عملکرد دانشجویان با استفاده از الگوریتم های یادگیری ماشین و داده کاوی آموزشی (مطالعه موردی دانشگاه شاهد)

هدف این تحقیق بررسی عوامل موثر در پیش بینی عملکرد تحصیلی دانشجویان مقطع کارشناسی در طبقه بندی چهار کلاسه می باشد. برای دستیابی به این هدف، مطالعه از روش داده کاوی کریسپ پیروی می کند. مجموعه داده ها از سیستم آموزشی ناد برای مقطع کارشناسی در دانشگاه شاهد برای ورودی سال های 1390 تا 1400 استخراج شده است. تعداد 1468 رکورد در داده کاوی استفاده شده است. ابتدا شاخص‌های موثر بر عملکرد تحصیلی دانشجویان استخراج شد. مدلسازی با استفاده از ابزار رپیدماینر9.9 انجام شد. برای بهبود عملکرد طبقه‌بندی و دقت پیش‌بینی رضایت‌بخش ، از ترکیبی از تجزیه و تحلیل مولفه اصلی همراه با الگوریتم های یادگیری ماشین و تکنیک‌های انتخاب ویژگی و الگوریتم‌های بهینه‌سازی استفاده می‌کنیم. عملکرد مدل‌های پیش‌بینی با استفاده از اعتبارسنجی متقاطع 10 برابری تایید شده است. نتایج نشان داد که الگوریتم درخت تصمیم بهترین الگوریتم در پیش‌بینی عملکرد دانشجویان با دقت 84.71 درصد است. این الگوریتم به درستی فارغ التحصیلی 77.88 درصد از دانشجویان عالی و 85.26 درصد از دانشجویان خوب و 84.69 درصد از دانشجویان متوسط و 85.96 درصد از دانشجویان ضعیف را بر اساس معدل نهایی پیش بینی کرد.متغیر معدل دیپلم بیشترین تاثیر را در پیش‌بینی عملکرد دانشجویان دارد.

predicting students’ performance using machine learning algorithms and educational data mining (a case study of shahed university)

abstractthe purpose of this research is to investigate the effective factors in predicting the academic performance of undergraduate students in the classification of four classes. to achieve this goal, the study follows the crisp data mining method. the data set was extracted from the nad educational system for the bachelor’s degree in shahed university for the entry of the years 2011 to 2021. 1468 records were used in data mining. first, the effective features on students’ academic performance were extracted. modeling was done using rapidminer9.9 tool. to improve classification performance and satisfactory prediction accuracy, we use a combination of principal component analysis combined with machine learning algorithms and feature selection techniques and optimization algorithms. the performance of the prediction models is verified using 10-fold cross-validation. the results showed that the decision tree algorithm is the best algorithm in predicting students’ performance with an accuracy of 84.71%. this algorithm correctly predicted the graduation of 77.88% of excellent students, 85.26% of good students, 84.69% of medium students, and 85.96% of weak students based on the final gpa. introductionthe main problem in this research is to identify the factors that are effective in predicting the academic performance of undergraduate students in shahed university. choosing the best machine learning algorithm in predicting academic performance among different modeling methods based on validation and evaluation of models is another issue in the present research. the purpose of this research is to investigate the effective factors in predicting the academic performance of undergraduate students in shahed university using educational data mining based on classification models.research questionsthe main question in this research is what factors affect the prediction of undergraduate students’ performance and improving their performance?sub questions1- which modeling algorithms have better results in predicting student performance?2- what methods have been used to predict students’ performance?3- what is the validity of the developed model for shahed university students? 2- research background1-2- theoretical foundationseducational data miningthe processing of educational data improves the prediction of student behavior and new approaches to educational policies (capuano toti, 2019) (viberg et al., 2018)academic performanceacademic performance of students means the extent to which they achieve educational goals (banik kumar, 2019).2-2- review of past studiesthe highlighted cells in table 1, based on past research, show the classification algorithms that have the most accuracy and effectiveness in predicting students’ performance in the relevant research. the decision tree algorithm has been used the most in previous researches. the nb algorithm has been the most used in research after the decision tree. rf and ann algorithms are next in use. after that, svm and knn algorithms have been used in researchtable 1. the results of research literature based on the use of classification algorithmsdata mining algorithmdtrfnbknnsvmannline rllraccuracy(batool et al., 2023) *   *   (marjan et al., 2023)******   (abdelmagid qahmash, 2023) * **  * (manoharan et al., 2023)** * * * (alghamdi rahman, 2023)***     99.34%(alboaneen et al., 2022) * ****  (yağcı, 2022)* ***  *70-75%(dabhade et al., 2021)*   * * 83.44%(najafi etal,2021)*       95%(soltani etal,2021)*  **    (cruz-jesus et al., 2020) * **  *50-81%(sokkhey okazaki, 2020)*** *    (rebai et al., 2020)**       (jayaprakash et al., 2020)***      (zulfiker et al., 2020)**   *   (musso et al., 2020)     *   (waheed et al., 2020)     *  85%(salal abdullaev, 2019)* ****   (turabieh, 2019)* ** *   (xu et al., 2019)*   **   (ghodoosi etal,2019)* *      (fadavi etal,2019)  *     95.84%(ajibade et al., 2019)* ***   91.5%(ahmad shahzadi, 2018)     *  85%(hasani bazrafshan, 2018)* *      (hussain et al., 2018)***   *  (umer et al., 2017)****   * (khasanah, 2017)* *      (asif et al., 2017)*        (hoffait schyns, 2017) *   * *92.34%(khosravi etal,2017)*    *   (mueen et al., 2016)* *  *  86%(amrieh et al., 2015)* **     (yehuala, 2015)* *     92.34%(zahedi etal,2015)*   *  * (punlumjeak rachburee, 2015)*        (osmanbegović et al., 2014)**      71%(shamloo et al.,2014)*        (asadi et al.,2013)*        (kabakchieva, 2013)* **    60-75%(oskouei askari, 2014)***  *  96%(nghe et al., 2007)* *      present research******  94.17%3- methodthis study follows the popular training data mining method crisp. the data collection of nad educational system for bachelor’s degree in non-medical fields of shahed university has been extracted from 2011 to 2021. we used the label encoder technique to encode the features. in this research, c4.5 and id3 decision tree classification algorithms, random forest, naïve bayes, k-nearest neighbor and artificial neural network and gradient enhanced tree were used to analyze and classify students and predict the final gpa.