The development of technology and the introduction of the Internet into our lives, on the one hand, facilitate the storage of extensive data; on the other hand, it has led to the formation of huge amounts of data of many different types. In parallel with the size of the resulting data stacks, an increase was observed in the size of the databases where the data is kept.

These data, stored in large databases, are worthless on their own, with a wide variety of features, and can only be transformed into information and gain value when processed for a purpose. However, classical statistical methods are insufficient to extract meaningful information from this large amount of raw data by analyzing it. Therefore, different disciplines were needed by researchers to make raw data meaningful. As a result, data mining has been applied (1).

If we look at the educational process, factors such as family, friends, teachers, school environment, classroom environment, lessons have positive or negative effects on the student during the realization of this process. The important thing is to determine which of these factors or to what extent the student is affected. However, after determining the factors affecting the student's education process, the effectiveness of education can be increased by taking necessary precautions (2). However, the data that need to be evaluated to identify these factors and take the required precautions are numerous and complex. It is challenging to analyze and evaluate the collected data and transform it into meaningful data.

Data mining methods can be used to make significant and use this large amount of data. For this reason, researchers stated that data mining techniques that will respond to the needs of the participants who take an active role in the education-training process should be used in education systems in the examinations to be made on the data stacks because data mining methods can be used in every field where data stacks are found (3).

There are databases in the field of education where meaningful relationships will be determined using data mining methods, and information that can shed light on the future can be derived. There are many data types in 21st-century learning environments, such as learning management systems, smart teaching systems, adaptive hypermedia systems. However, not all students using these environments exhibit the same learning performance due to differences in their motivation, readiness, and self-regulation skills.

Based on research, Educational_data_mining is the essential element of the education process, such as students' personal information, grades, absenteeism, successful and unsuccessful courses, to determine the reasons for success, to increase their success, to prevent their absenteeism, to define the reasons for the lessons they will take. The advice can be provided regarding the selection and career goals (3).

Educational Data Mining (3)

In addition, data mining techniques are used in education in forming groups according to students' characteristics, individual learning similarities, detecting undesirable student behaviors such as low motivation, absenteeism, dropping out of school, and not following school rules, predicting and taking necessary precautions (4). It is possible to detect the problems that may arise in the education and training environment in advance and improve the education and training environments. For educators, using data mining techniques in education, feedback can be reached on how students can make the learning process more efficient and take corrective measures.

1- C. Romero and S. Ventura, ``Educational data mining: A review of the state of the art,'' IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 40, no. 6, pp. 601-618, Nov. 2010.

2- R. S. J. D. Baker and K. Yacef, ``The state of educational data mining in 2009: A review and future visions,'' J. Edu. Data Mining, vol. 1, no. 1, pp. 3-17, 2009.

3- Romero, C. ve Ventura, S. (2013). Data mining in education. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 3(1), 12-27.

4- Rizvi, S., Rienties, B. ve Khoja, S. A. (2019). The role of demographics in online learning; A decision tree based approach. Computers & Education, 137, 32-47.