RETRACTED: Prediction poverty levels of needy college students using RF-PCA model

Abstract

Nowadays, poverty-stricken college students have become a special group among college students and occupied a higher proportion in it. How to accurately identify poverty levels of college students and provide funding is a new problem for universities. In this study, a novel model, which incorporated Random Forest with Principle Components Analysis (RF-PCA), is proposed to predict poverty levels of college students. To establish this model, we collect some useful information is to construct the datasets which include 4 classes of poverty levels and 21 features of poverty-stricken college students. Furthermore, the feature dimension reduction consists of two steps: the first step is to select the top 16 features with the ranking of feature, according to the Gini importance and Shapley Additive explanations (SHAP) values of features based on Random Forest (RF) model; the second step is to extract 11 dimensions by means of Principle Components Analysis (PCA). Subsequently, confusion metrics and receiver operating characteristic (ROC) curves are utilized to evaluate the promising performance of the proposed model. Especially the accuracy of the model achieves 78.61% . Finally, compared with seven states of the art classification algorithms, the proposed model achieves a higher prediction accuracy, which indicates that the results provide great potential to identify the poverty levels of college students.

Forecasting GPU Type Allocation via Demand Feature Extraction in Heterogeneous Clusters

“…Here, N denotes the total number of decision trees [12]. A higher feature importance score indicates a more important feature, which has a larger effect on the prediction task [38].…”

“…Here, n is the number of classes in the specific classification problem, T P i is the number of samples that are correctly classified into the i-th class (T P i = T i P i ), F P i is the number of samples that are incorrectly classified into the j-th class as the i-th class and F N i is the number of samples that are incorrectly classified into the j-th class as other classes. A higher value for Equations ( 22)-( 24) indicates better model performance [38]. For regression models, the mean absolute error (MAE) and root mean squared error (RMSE) [21] are two essential metrics to measure the accuracy of the regression model's predictions.…”

Workload Analysis and Prediction of Multi-type GPU in Heterogeneous GPU Clusters

“…Here, f ′ denotes the standardized feature importance values of a decision tree, and N denotes the total number of decision trees [39]. A higher feature importance score indicates a more important feature, which has a larger effect on the model [40].…”

“…Here, n represents the number of classes in the particular classification problem; T P i represents the number of samples correctly classified into the ith class (T P i = T i P i ); F P i represents the number of samples incorrectly classified into the jth class into the i th class; And F N i represents the number of samples incorrectly classified into the jth class into other classes.The higher the Equations ( 12) -( 14) value, the better the model performance [40]. For regression models, Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) are two key metrics to measure accuracy of prophecy regression models [42].…”