Table 2 Model fit statistics.

From: The effects of the aesthetics and composition of hotels’ digital photo images on online booking decisions

Model

AUC

CA

F1

Precision

Recall

Logistic regression

0.614

0.578

0.577

0.578

0.578

SVM

0.881

0.806

0.806

0.806

0.806

MLP Neural Network

0.903

0.830

0.830

0.830

0.830

  1. “Recall” is value implicit to the true positive values proportion in the set of really positive observations (Error type I); “AUC” is a square area below a ROC curve line of model prediction power (Fig. 2); “CA” is a classification accuracy and denotes the share of instances correctly classified; “F1” is a mean of precision and recall harmonically weighted, \(F1_{{\rm {score}}} = 2 \cdot \frac{{\left( {{\rm {Precision \cdot Recall}}} \right)}}{{\left( {{\rm {Precision + Recall}}} \right)}}\).
Back to article page