Predicting students' success is crucial in educational settings to improve academic performance and prevent dropouts. This study aimed to improve student performance prediction by combining advanced machine learning (ML) approaches. Convolutional Neural Networks (CNNs) and attention mechanisms were used for extracting relevant features from…

School attendance and absenteeism are critical targets of educational policies and practices that often depend heavily on aggregated attendance/absenteeism data. School attendance/absenteeism data in aggregated form, in addition to having suspect quality and utility, minimizes individual student variation, distorts detailed and multilevel…

School attendance/absenteeism (SA/A) is a crucial indicator of health and development in youth but educational policies and health-based practices in this area rely heavily on a simple metric of physical presence or absence in a school setting. SA/A data suffer from problems of quality (reliability, construct validity, data integrity) and utility…

This article characterizes and reflects on the possible uses of early warning systems (hereafter, EWS) in the region as effective tools to support educational pathways, whenever they identify risks of dropout, difficulties for the achievement of substantive learning, and the possibility of organizing specific actions. This article was developed in…

The collection of data by government authorities has a complex history. In Australia, this began with the establishment of British government settlements as a way to account for fiscal viability and social prospects. As the colonies became self-governing entities, the collection of social and economic data increased in importance, and included…

Determining which students are at risk of poorer outcomes -- such as dropping out, failing classes, or decreasing standardized examination scores -- has become an important area of research and practice in both K-12 and higher education. The detectors produced from this type of predictive modeling research are increasingly used in early warning…

The purpose of this document is to recommend practices that will help education agencies collect, report, and use attendance data to improve student and school outcomes. This publication substantively revises and expands the information included in "Every School Day Counts: The Forum Guide to Collecting and Using Attendance Data,"…

This guide was designed to help state and local education agencies conduct needs assessments to better understand the strengths, challenges, and needs unique to schools serving American Indian students. It includes surveys developed collaboratively with communities that serve American Indian students to reflect the most relevant topics. Using…

In recent years, education data have become both more easily accessible and more important than ever to decisions about K-12 policies and practice. Under the "Every Student Succeeds Act" (ESSA), states are required to publish data on how students, including English Learners (ELs), are performing in areas such as reading, math, and…

Truant student behavior can be due to various reasons. Some of these reasons are located in schools. So far, little is known about how student perception of school rules is related to truancy. This study aims to identify types of school attendance policies and how these policies are associated with individual truancy. Self-reports from the German…

Issue 4 of the Australian Council for Educational Research's (ACER's) "Policy Insights" series commences with a synthesis of publicly available data on school attendance by Indigenous Australians, highlighting areas of major risk. It explores Australian and international literature to develop an understanding of the risk factors and…

As enrolment in online courses has grown and LMS data has become accessible for analysis, researchers have begun to examine the link between in-course behaviours and course outcomes. This paper explores the use of readily available LMS data generated by approximately 700 students enrolled in the 12 online courses offered by Pamoja Education, the…

Chronic absenteeism--or missing 10 percent or more of school days for any reason--is a proven early warning sign of academic risk and school dropout. Too often, though, this problem is overlooked, especially among elementary students, because of the way attendance data are tracked. This study confirms the premise that districts and schools may…

iMentor's College Ready Program is a unique approach that combines elements of school-based mentoring, whole school reform, and technology in an effort to help students develop the full suite of knowledge, behaviors, and skills they need to complete high school and enroll and thrive in college. iMentor partners with high schools that serve…

Nationally, more than one million youth drop out of high school each year. One in four young people do not graduate with their age mates. Thus, in recent years, national leaders have directed sustained attention to what they term the "dropout crisis," particularly in high schools that are graduating less than two-thirds of their…