Table 1 Recent studies on income prediction summary recollection
From: Supervised machine learning predictive analytics for alumni income
Source | Task | Methods | Results |
|---|---|---|---|
Lazar [5] | Classification | SVM | Acc = 0.84 |
Hartog and Webbink [6] | Regression | OLS | R2 = 0.14 |
Lee and Lee [7] | Quantile regression | 5th 25th 50th 75th 95th | Pseudo-R2 = 0.29 Pseudo-R2 = 0.33 Pseudo-R2 = 0.34 Pseudo-R2 = 0.34 Pseudo-R2 = 0.32 |
Oehlrein [8] | Regression | OLS | R2 = 0.37 |
Stran and Truong [9] | Regression | Lasso OLS | USD $6,394.64 (RMSE) |
Figueiredo and Fontainha [10] | Quantile regression | 10th 50th 90th | Pseudo-R2 = 0.27 Pseudo-R2 = 0.45 Pseudo-R2 = 0.50 |
Sharath et al. [11] | Classification | NB C4.5 Boosted C4.5 | Acc = 0.48 Acc = 0.51 Acc = 0.53 |
Khongchai and Songmuang [12] | Multi-class classification | DT SVM MLP KNN NB | Acc = 0.73 Acc =0.43 Acc =0.38 Acc = 0.84 Acc =0.43 |
Chen et al. [13] | Multi-class classification | SVM DT LR RF GBM NN LSTM DNN | Acc = 0.74 Acc = 0.74 Acc = 0.72 Acc = 0.71 Acc = 0.70 Acc = 0.68 Acc = 0.65 Acc =0.65 |