Skip to main content
Figure 16 | EPJ Data Science

Figure 16

From: Does noise affect housing prices? A case study in the urban area of Thessaloniki

Figure 16

Scatter plot between the LIME weights and the daily (left) and nightly (right) noise in decibels for the best performing XGBoost model with the noise radius set to 100 meters in area B. A positive weight indicates that an increase in the feature value leads to a higher prediction (high property price). A negative weight implies that an increase in the feature value leads to a lower prediction (low property price)

Back to article page