This study enabled the researcher to create a graduate tracer monitoring platform. It aimed to provide a centralized channel to monitor institutions' graduates in terms of their job employment, to assess academic programs using modified instruments so necessary interventions may be provided, and to provide a matching algorithm that can be used both by industry partners and respective alumni. This study employed a Decision Support System and mapping recommendation analysis using a rule-based algorithm to evaluate the results of alumni program evaluation on five areas or dimensions, namely curriculum, faculty, facility, laboratory, and student services. It sets the threshold to determine if the results of the areas mentioned above are beyond the passing rate and implements the interventions for each area. The content management system was also used in this study to change the contents of the Alumni Program Evaluation, the interventions, the threshold, and many more. Based on the results, no intervention must be implemented in all areas/dimensions since the mean and the composite mean were more than the 4.0 threshold that was set in the proposed system. The overall rating of the respondents using the technology acceptance model numerical rating is 4.42 with an interpretation of “Agree.” As observed all criteria are rated either agree or strongly agree which indicates a high standard has been set in the development of the system. This means that the system is ready for deployment.

This descriptive-developmental study enables the authors to create a graduate tracer monitoring platform. The paper aims to provide a centralized channel to monitor institutions' graduates in terms of their job employment, assessing academic programs using modified instruments which determine necessary interventions that may be provided, and to provide a matching algorithm that can be used both by industry partners and respective alumni. This study used a Decision Support System and mapping recommendation analysis using time series analysis to evaluate the results of alumni program evaluation on five areas or dimensions such as curriculum, faculty, facility, laboratory, and student services. The study may set the threshold to determine if the results of the areas mentioned above are beyond the passing rate and implement the interventions for each area. A content management system was also used in this paper to change the contents of the Alumni Program Evaluation, the interventions, the threshold, and many more. The developed web-based system includes an evaluation of the Alumni Program across key areas such as Curriculum, Faculty, Facility, Laboratory, and Student Services. This study employed a purposive sampling technique to identify the group of respondents. There are a total of 152 respondents who participated in this study from the Information Technology department and IALAP office. The study results indicate that no interventions are necessary in any of these areas, as both the mean and the composite mean surpasses the 3.50 threshold set in the system. Among the five areas, the faculty received the lowest passing mean, followed by student services and the laboratory. This underscores the potential for continuous improvement in these specific areas influencing the employability rate and skills of the alumni-participants. The time series analysis was conducted on a two-year dataset, covering 6 trimesters. The analysis revealed a positive improvement in evaluation scores as the trimesters progressed across five dimensions of alumni program evaluation. This suggests that alumni respondents consistently agreed in their evaluations of appreciation on the improvements made by the school administration which enhances their life experiences and technical skills during their stay in the campus.

In the Philippines, according to Philippine Authority of Statistics, there is an imbalance between the student enrollment and student graduation. Almost half of the first-time freshmen full time students who began seeking a bachelor's degree do not graduate on time. The study aims to utilize how Naïve Bayes algorithm - a data classification algorithm that is based on probabilistic analysis - can be used in educational data mining specifically in student graduation. The study is focused on the application of the Naïve Bayes algorithm in predicting student graduation by generating a model that could early predict and identify students who are prone of not having graduation on time, so proper remediation and retention policies can be formulated and implemented by institutions.