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. Furthermore, the paper also seeks to identify the most influential predictors of the models. Ensemble machine learning algorithms such as bagging, boosting, and voting were utilized to develop the models, and an evolutionary optimization technique was used to identify the most relevant attributes. The results reflected the voting ensemble as the model achieving the highest accuracy (88.29%) followed by random forest (82.28%). The optimizer algorithm identified job placement, IT experience, degree, high school, final and last semester GPA, IT project research, study frequency, mother's educational level, sibling number, and living accommodation as the most influential predictors. Random forest also ranked first in the optimized models by garnering an 84.27 accuracy rating. The research results will greatly benefit educational institutions, school administrators, and educators by giving them a deeper insight into their job placement programs. IT graduating students can also use the research output to improve their job placement chances. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://bibliotheek.ehb.be:2222/en-US/products/dissertations/individuals.shtml.]