algorithms for deriving and analyzing retroreflectivity influence factors through regression analysis. METHODS : An experimental road lane was created to examine the trends of retroreflectivity and LiDAR intensity values, and a controlled indoor experiment was conducted to identify influencing factors. The optimal algorithm was developed by regression analysis of the experimental data. RESULTS : The significance probability (P-value) through SPSS linear regression analysis was 0.000 for measured height, 0.001 for perpendicular angle, 0.157 for vertical angle, and 0.000 for LiDAR intensity, indicating that measured height, vertical angle, and LiDAR intensity are significant factors because the significance probability is less than 0.05, and vertical angle is not significant. The NNR regression model performed the best, so the measurement data with height (1.2m, 2m, 2.2m) and vertical angle (11.3°, 12.3°, 13.5°) were analyzed to derive the optimal LiDAR Intensity measurement height and vertical angle. CONCLUSIONS : For each LiDAR measurement height and vertical angle, the highest correlation between LiDAR Intensity and retroreflectivity was found at a measurement height of 1.2 meters and a vertical angle of 12.3°, where the model learning accuracy (R2) was the highest.