Developing and Comparing Data Mining algorithms that Work Best for Predicting Student’s Performance

Learning data analytics improves the learning field in higher education using educational data for extracting useful patterns and making better decision. Identifying potential at-risk students may help instructors and academic guidance to improve the students’ performance and the achievement of learning outcomes. The aim of this research study is to predict at early phases the student’s failure in a particular course using the standards-based grading. Several machines learning techniques were implemented to predict the student failure based on Support Vector Machine, Multilayer Perceptron, Naïve Bayes, and decision tree. The results on each technique shows the ability of machine learning algorithms to predict the student failure accurately after the third week and before the course dropout week. This study provides a strong knowledge for student performance in all courses. It also provides faculty members the ability to help student at-risk by focusing on them and providing necessary support to improve their performance and avoid failure.

Improving Teacher Evaluation: Walking the Talk of Standards-Based Grading

Teachers and school leaders frequently express a disconnect in the purpose and importance of teacher evaluation, particularly as it relates to educator growth. At the same time, some schools are beginning to communicate student growth through a standards-based grading philosophy. One way schools might “walk the talk” of their grading reform efforts designed to communicate student growth is through the use of proficiency scales to prioritize growth in teacher evaluation. This paper describes implications of simultaneously utilizing a growth model for teacher evaluation and a student growth model via standards-based grading.

Points, Points, and More Points: High School Grade Inflation and Deflation when Homework and Employability Scores are Incorporated

With a strong movement of schools starting to use standards-based grading practices, one of the aims of this study was to learn if traditional grading practices communicate grades that are accurate based on the students’ learning of the course objectives. The purpose of this study was to determine the extent to which employability and homework scores within a traditional points- and percentages-weighted grading model inflates or deflates grades. This study analyzed 795 students’ semester math grades at an urban high school to see if, and to what extent, students’ grades were inflated or deflated due to including homework and employability scores in the grade. Final grades, which included homework and employability points, were compared to each student’s overall summative assessment scores to determine grade inflation or deflation. The study also analyzed how changing grading practices to eliminate homework and employability points would impact the number of students that ultimately passed or failed the course. Results of this study indicated 336 (43.2%) students had their grades inflated or deflated by 5% or more and 97 (12.6%) students had their grades inflated or deflated by 10% or more, which is equivalent to moving up or down a full letter grade. School leaders should consider separately communicating academic and non-academic factors to minimize grade inflation/deflation in order to make decisions based upon grades more justifiable.