FORMATIVE AND SUMMATIVE EVALUATION OF DEEP LEARNING ENVIRONMENT-BASED ECONOMICS LEARNING AT SMAS IT FAGOGORU

Abstract

This study aims to explore the application of Deep Learning technology in improving formative and summative evaluation at SMAS IT FAGOGORU. The results show that the application of Deep Learning has significant potential in improving the effectiveness of evaluation, by providing feedback and improvements, or learning units to measure the achievement of learning objectives. The Deep Learning model is able to analyze student performance data in real-time, identify patterns of difficulties faced by students, and provide more focused recommendations for improvement, which were previously difficult to achieve with conventional assessment methods. This study also identified challenges in integrating this technology, such as the diversity of student characteristics, limited resources, and curriculum that requires adjustments to fully accommodate this technology. Nevertheless, the application of Deep Learning increases the objectivity of assessment, reduces human bias, and increases time efficiency for teachers by automating many aspects of assessment. Overall, Deep Learning technology can have a positive impact in improving the quality of learning evaluation at SMAS FOGOGORU, but more attention is needed to teacher training, curriculum adjustments, and improvements to the technology infrastructure to ensure long-term success.