Current research on the career satisfaction of graduates limits educational institutions in devising methods to attain high career satisfaction. Thus, this study aims to use data science models to understand and predict career satisfaction based on information collected from surveys of university alumni. Five machine learning (ML) algorithms were used for data analysis, including the decision tree, random forest, gradient boosting, support vector machine, and neural network models. To achieve optimal prediction performance, we utilized the Bayesian optimization method to fine-tune the parameters of the five ML algorithms. The five ML models were compared with logistic and ordinal regression. Then, to extract the most important features of the best predictive model, we employed the SHapley Additive exPlanations (SHAP), a novel methodology for extracting the significant features in ML. The results indicated that gradient boosting is a marginally superior predictive model, with 2–3% higher accuracy and area under the receiver operating characteristic curve (AUC) compared to logistic and ordinal regression. Interestingly, concerning low career satisfaction, those with the worst scores for the phrase “how frequently applied knowledge, skills, or technological tools from the academic training” were less satisfied with their careers. To summarize, career satisfaction is related to academic training, alumni satisfaction, employment status, published articles or books, and other factors.

This study shows the significant features predicting graduates’ job levels, particularly high-level positions. Moreover, it shows that data science methodologies can accurately predict graduate outcomes. The dataset used to analyze graduate outcomes was derived from a private educational institution survey. The original dataset contains information on 17,898 graduates and approximately 148 features. Three machine learning algorithms, namely, decision trees, random forest, and gradient boosting, were used for data analysis. These three machine learning models were compared with ordinal regression. The results indicate that gradient boosting is the best predictive model, which is 6% higher than the ordinal regression accuracy. The SHapley Additive exPlanations (SHAP), a novel methodology to extract the significant features of different machine learning algorithms, was then used to extract the most important features of the gradient boosting model. Current salary is the most important feature in predicting job levels. Interestingly, graduates who realized the importance of communication skills and teamwork to be good leaders also had higher job positions. Finally, general relevant features to predict job levels include the number of people directly in charge, company size, seniority, and satisfaction with income.

Genomic selection (GS) is revolutionizing plant breeding. However, its practical implementation is still challenging, since there are many factors that affect its accuracy. For this reason, this research explores data augmentation with the goal of improving its accuracy. Deep neural networks with data augmentation (DA) generate synthetic data from the original training set to increase the training set and to improve the prediction performance of any statistical or machine learning algorithm. There is much empirical evidence of their success in many computer vision applications. Due to this, DA was explored in the context of GS using 14 real datasets. We found empirical evidence that DA is a powerful tool to improve the prediction accuracy, since we improved the prediction accuracy of the top lines in the 14 datasets under study. On average, across datasets and traits, the gain in prediction performance of the DA approach regarding the Conventional method in the top 20% of lines in the testing set was 108.4% in terms of the NRMSE and 107.4% in terms of the MAAPE, but a worse performance was observed on the whole testing set. We encourage more empirical evaluations to support our findings.

Data science analysis was used to investigate the association between Research-Based Learning (RBL) and student’s academic performance. The research professors certified in RBL participated in this research. The participants used an advanced platform with over 500 resources. Tutors guided students in designing, implementing, and evaluating the RBL. We employed a quantitative and quasi-experimental design without a control group, correlational analysis, and ex post facto elements. A satisfaction survey was administered after the capacitation. In total, 342 teachers were trained and received accreditation. The analyses incorporated non-conventional data science methods such as correlation analysis, principal component analysis, and unsupervised learning utilizing the Density-Based Spatial Clustering Application with Noise algorithm. The professors’ satisfaction with RBL was related to student’s academic performance, which was found in clustering analysis.