Figure 18
Both plots are titled “Offices - R F Model” and “Offices - N N Model,” respectively. The horizontal axis in both plots represents the “SHAP value (impact on model output),” and the vertical axis lists the features considered by the models: “Thermal Satisfaction,” “Air Quality,” “Daylight Perception,” “Thermal Sensation,” “Sound Satisfaction,” “Daylight Satisfaction,” and “Sound Perception.” A color scale on the right of each plot indicates the “Feature value,” ranging from Low (blue) to High (red). In the “R F Model” plot, the horizontal axis ranges from negative 0.2 to 0.5 in increments of 0.1 units. The most impactful features are “Thermal Satisfaction,” “Thermal Sensation,” and “Air Quality.” “Thermal Satisfaction” shows a distribution skewed positively (up to 0.35). The distribution for “Sound Satisfaction” is very narrow near 0, showing a slightly positive SHAP value with a high feature value. In the “N N Model” plot, the horizontal axis ranges from negative 0.2 to 0.6 in increments of 0.2 units. “Thermal Satisfaction” is the most influential feature, with a distribution concentrated in positive SHAP values (up to 0.6), primarily colored red. “Air Quality” and “Thermal Sensation” are also significant, with distributions extending into both positive and negative SHAP ranges, indicating that both low and high feature values influence the model output. Note: All numerical values are approximate.Violin plots of SHAP values illustrating each feature's contribution to the predicted IE satisfaction in Offices ML models. Source: Authors' own work