Table 6 Performance Metrics.

From: Advanced and hybrid machine learning techniques for predicting compressive strength in palm oil fuel ash-modified concrete with SHAP analysis

Sr. No

Metric Equation

Range

Unit

1

\({R}^{2}= 1-\frac{{\Sigma }_{i=1}^{N}{\left({x}_{i}-{\widehat{x}}_{i}\right)}^{2}}{{\Sigma }_{i=1}^{N}{\left({x}_{i}-\overline{x }\right)}^{2}}\)

0 – 1

(1 = perfect fit)

Unitless

2

\(RMSE= \sqrt{\frac{1}{N}{\sum }_{i=1}^{N}{\left({x}_{i}-{\widehat{x}}_{i}\right)}^{2}}\)

0 = Best Result

MPa

3

\(NRMSE= \frac{RMSE}{\overline{x} }=\frac{ \sqrt{\frac{1}{N}{\sum }_{i=1}^{N}{\left({x}_{i}-{\widehat{x}}_{i}\right)}^{2}}}{\overline{x} }\)

0 = Best Result

Unitless

4

\(MAE= \frac{1}{N}{\sum }_{i=1}^{N}\left|{x}_{i}-{\widehat{x}}_{i}\right|\)

0 = Best Result

MPa

5

\(d= 1-\frac{{\Sigma }_{i=1}^{N}{\left({x}_{i}-{\widehat{x}}_{i}\right)}^{2}}{{\Sigma }_{i=1}^{N}{\left(\left|{\widehat{x}}_{i}-\overline{x }\right|+\left|{x}_{i}-\overline{x }\right|\right)}^{2}}\)

0 – 1

(1 = perfect agreement)

Unitless

  1. \({{\varvec{x}}}_{{\varvec{i}}}{\widehat{{\varvec{x}}}}_{{\varvec{i}}}\overline{{\varvec{x}} }:\overline{{\varvec{x}} }=\frac{1}{{\varvec{N}}}\sum_{{\varvec{i}}=1}^{{\varvec{N}}}{{\varvec{x}}}_{{\varvec{i}}}; {\varvec{N}}\): Actual observed values; : Predicted values generated by the model; Mean of the observed values, : Number of observations.