Educational Data Mining Model to Attain Sustainability

I. INTRODUCTION The concept of sustainable development began in the 1980s with the introduction of different meanings and definitions. One of the definitions quoted most frequently comes from the Brundtland report [1]. The idea, in particular the basic needs of the poor in the world should be given priority, and secondly the idea that technology and social organizations impose restrictions on the capacity of the environment to meet present and future capabilities.

Typically, educational data mining (also called EDM) looks for new patterns in the data and analyzes the data gathered during education and learning, using statistics, artificial intelligence, and (of course) data mining . For example, in a learning analysis, we apply a prediction model known to the education system using various knowledge such as information science, sociology, psychology, statistics, artificial intelligence, data mining etc.

Educational data mining (EDM) is data mining applied to educational data sets. In most cases, EDM is similar to normal data mining. However, certain characteristics of the educational data set must be considered. Normally, data has multiple layers. Furthermore, since many studies are being conducted at one facility, it is not easy to generalize most of the research. If you want to know more about EDM, please check the paper by Romero and Ventura. Both authors wrote several literature reviews on this subject. It provides a clear outlook on the development of the field over time. Important topics related to EDM forecasting are: Prediction of registration, prediction of student performance, and forecast of exhaustion

In order to effectively analyze and control customer cancellation, it is important to establish an effective and accurate customer cancellation prediction model. We use statistical and data mining techniques to construct a churn prediction model. You can use data mining techniques to find interesting patterns and relationships in your data and predict or classify actions. In other words, the overall goal is to predict the outcome and to find hidden patterns, relevance, and anomalies of customer data using complex data processing algorithms.

Data mining algorithms are a mechanism for generating data mining models. To generate a data mining model, you need to define a data mining algorithm. The algorithm analyzes specific data sets and examines the identifiable hidden patterns and trend results. The algorithm then uses that result to define the parameters of the mining model. Then use these parameters throughout the data set to extract operational patterns and detailed statistics. Details of the data mining algorithm will be described later.