This quantitative study investigates the predictive power of machine learning (ML) models on degree completion among adult learners in higher education, emphasizing the enhancement of data-driven decision-making (DDDM). By analyzing three ML models - Random Forest, Gradient-Boosting machine (GBM), and CART Decision Tree - within a not-for-profit,…

This descriptive correlational study examined the predictive relationships between ACT composite scores, high school GPA, ACT testing attempts, and gender with teacher candidate's overall performance on the edTPA and each of the three edTPA instructional tasks (Task 1, Task 2, and Task 3). The edTPA is a portfolio-based subject-specific teaching…

Given the rapid growth of K-12 online learning, research is needed in the effective identification of at-risk students so that administrators and teachers can develop appropriate supports and interventions. The purpose of this research was to determine if student success in an online course could be predicted for English Learners (EL) using…

Having a job immediately after graduation is the dream of every IT graduate. However, not everyone can achieve this outcome. The study's primary goal is to develop predictive models to forecast IT graduates' chances of finding a job based on factors such as academic performance, socioeconomic status, academic habits, and demographic data.…

The gap in supply (i.e., shortage) and demand of the STEM workforce have prompted extensive research on identifying factors that predict STEM outcomes and retention of students. Few studies, however, have examined the relationships between STEM outcomes and predictors in an integrated model, taking into account measurement errors in the…

Teacher retention is a foundational issue and schools have historically struggled to retain teachers. Previous research indicates that teachers leave the profession at high rates before year five of teaching expertise. Lack of teacher retention contributes to instability and lack of trust in school districts. This secondary data study explores…

This quantitative study examined the retention of new hires at a Midwestern, K-12, public school district using the scores of an application screening assessment as a predictor. New teacher hires' overall performance results on a screening assessment were compared to the retention of those hires after 1 year of employment. In addition to the…

This study aimed to assess the effectiveness of existing insolvency predictive models employed for non-profit Higher Education Institutions (HEIs) and test a proposed predictive model utilizing statistical and ratio analysis by comparing HEIs in operations with those that closed from 2017 to 2020. The researcher incorporated a non-experimental,…

This study investigated the relationship between teachers' mindsets (growth mindset and fixed mindset), teachers' digital competence, teachers' age, gender, years of teaching experience, and information and communication technology (ICT) use in teaching in elementary schools, in a city located at the Northwest region of Saudi Arabia. This study…

Evidence-based early interventions for autism spectrum disorder (ASD) have been shown to improve child outcomes and quality of life (Lord et al., 2018; Reichow et al., 2018; Smith & Iadarola, 2015). However, response to intervention is variable across both children and implementation contexts. Understanding factors that influence this…

Community colleges experience difficulties in effectively placing students in the first college-level, gateway mathematics course. The use of one standardized exam, such as the Texas Success Initiative Assessment (TSIA) has been proven ineffective. The effectiveness of using multiple measures is not known. This quantitative predictive…

A historic period of state divestment in public higher education, exacerbated by the "Great Recession" and attendant financial repercussions, has significantly altered public higher education financing. The most significant impact has been cost shift from the state to students via increasing tuition rates. These changes threaten student…

Learning probabilistic classification and prediction models that generate accurate probabilities is essential in many prediction and decision-making tasks in machine learning and data mining. One way to achieve this goal is to post-process the output of classification models to obtain more accurate probabilities. These post-processing methods are…

The purpose of this study is to ascertain whether a student's sense of financial security can increase the degree of predictability of retention over and above the more traditional predictors typically found in the literature, and to get a better sense for how student financial security impacts student persistence decision-making in college. To…

The study was designed to examine the relationship among computer anxiety, computer self-efficacy, computer experience, performance, and engagement. Previous research has demonstrated that these topics are related; however, few studies have included all of these variables. Specifically, this study was designed to answer the following research…