Educational Data Mining (EDM) is a widely used methodology that overcomes big and complex educational data sets. Application of EDM unveils the information hidden in these data sets that cannot be revealed by use of the basic statistical methods that are often employed by educators in reading the data. The information revealed through EDM scrutinises the successes of students and, based on that information, helps policy-makers in the field of education form appropriate norms and policies for better education practices. The International Association for the Evaluation of Educational Achievement (IEA) is a notable international organisation that oversees the monitoring of educational evaluation in many countries. Effective application of EDM can occur only when there are reliable data sets that can be studied. The IEA makes such data sets available to participating countries. The organisation acquires these data sets by undertaking comparative studies among the participating countries which results in the above-mentioned data sets and helps them examine the various education practices being followed in various countries and their effects there. One of the more ambitious ventures that IEA has undertaken in recent times is called Trends in International Mathematics and Science Study (TIMSS) which is administered every four years to science and mathematics students in their fourth and eighth grades. Over 60 countries from across the world are participants in TIMSS. Not only does this test reveal information about the outcome of various education norms being followed in the paritcipating countries, it also allows the researchers to evaluate the success rates of the students in their respective countries and compare them with those from other countries (Mullis, Martin, Foy, & Arora, 2012). Many studies in the past dealing with subjects from the field of education have utilised data that was a result of TIMSS application. These research studies have incorporated the popular and commonly used statistical methods such as factor analysis and regression but it has been seen that these methods of analyses are not apt for large and complex data sets due to their inherent limitations. EDM is therefore gradually becoming more widespread Enes Filiz, Ersoy Öz Yildiz Technical University, Turkey Abstract. Educational Data Mining (EDM) is an important tool in the field of classification of educational data that helps researchers and education planners analyse and model available educational data for specific needs such as developing educational strategies. Trends International Mathematics and Science Study (TIMSS) which is a notable study in educational area was used in this research. EDM methodology was applied to the results of TIMSS 2015 that presents data culled from eighth grade students from Turkey. The main purposes are to find the algorithms that are most appropriate for classifying the successes of students, especially in science subjects, and ascertaining the factors that lead to this success. It was found that logistic regression and support vector machines – poly kernel are the most suitable algorithms. A diverse set of features obtained by feature selection methods are “Computer Tablet Shared”, “Extra Lessons Last 12 Month”, “Extra Lessons How Many Month”, “How Far in Education Do You Expect to Go”, “Home Educational Resources”, and “Student Confident in Science” and these features are the most effective features in science success.

中文翻译：

---

寻找土耳其科学学生成功分类的最佳算法和有效因素

教育数据挖掘 (EDM) 是一种广泛使用的方法，可以克服庞大而复杂的教育数据集。EDM 的应用揭示了隐藏在这些数据集中的信息，这些信息无法通过使用教育者在阅读数据时经常使用的基本统计方法来揭示。通过 EDM 揭示的信息仔细审查学生的成功，并根据该信息帮助教育领域的决策者制定适当的规范和政策，以实现更好的教育实践。国际教育成就评估协会 (IEA) 是一个著名的国际组织，负责监督许多国家的教育评估。只有当有可靠的数据集可以研究时，才能有效地应用 EDM。IEA 向参与国提供此类数据集。该组织通过在参与国之间进行比较研究来获得这些数据集，从而产生上述数据集，并帮助他们检查不同国家正在遵循的各种教育实践及其对那里的影响。IEA 最近开展的一项更雄心勃勃的项目被称为国际数学和科学研究趋势 (TIMSS)，每四年向四年级和八年级的科学和数学学生进行一次管理。来自世界各地的 60 多个国家是 TIMSS 的参与者。该测试不仅揭示了参与国所遵循的各种教育规范的结果的信息，它还允许研究人员评估各自国家学生的成功率，并将他们与其他国家的学生进行比较（Mullis、Martin、Foy 和 Arora，2012 年）。过去许多涉及教育领域学科的研究都利用了 TIMSS 应用程序的结果。这些研究结合了流行和常用的统计方法，如因子分析和回归，但已经看到，这些分析方法由于其固有的局限性而不适用于大型和复杂的数据集。因此，EDM 逐渐变得越来越普遍。 Enes Filiz，土耳其 Ersoy Öz Yildiz 技术大学 摘要。教育数据挖掘 (EDM) 是教育数据分类领域的重要工具，可帮助研究人员和教育规划人员针对特定需求（例如制定教育策略）分析和建模可用的教育数据。趋势国际数学和科学研究（TIMSS）是教育领域的一项著名研究，用于本研究。EDM 方法应用于 TIMSS 2015 的结果，该结果展示了从土耳其八年级学生中挑选出来的数据。主要目的是找到最适合对学生的成功进行分类的算法，尤其是在科学科目中，并确定导致这种成功的因素。发现逻辑回归和支持向量机 - 多核是最合适的算法。