Evaluating pedestrian comfort in high-density cities requires methods integrating subjective experience with urban morphology. This study develops an integrated framework combining pairwise comparison scoring, semantic segmentation (DeepLabv3+), ensemble learning (Random Forest), and SHAP-based interpretability. EfficientNet-B7 is used to expand pairwise datasets and derive continuous comfort scores across Macau’s street network. Four experiential street types are identified: historical–cultural districts, urban lifestyle areas, natural corridors, and leisure zones. SHAP analysis illustrates stable associations between predicted comfort scores and multi-layered spatial configurations, including cultural legibility and sequencing in historic cores, moderate greenery with functional anchoring in residential areas, and scene coherence in tourism zones. Semantic features serve as effective morphological proxies within the modeling framework. Methodologically, the framework demonstrates how explainable machine learning can be applied to dense Asian cities under observational conditions. Design implications emphasize interface continuity, microclimate adaptation, and functional enrichment, suggesting that pedestrian comfort is closely related to coherent spatial–experiential structures rather than isolated environmental upgrades.

Urban nighttime lightscapes shape the tourist experience, urban image, and commercial identity, yet existing evaluation methods trade off objective measurement, real-scene coverage, and the interpretation of subjective perception. This study examines the nighttime facades of six representative commercial complexes in Macao and constructs a multisource computational framework for nighttime lightscape perception evaluation. Objective features such as luminance, color, light-element composition, and visual saliency are extracted from 1800 user-generated content (UGC) images; affect, atmosphere, aesthetics, comfort, and behavioral intention are measured through 300 online questionnaires; and affective responses expressed in natural language are characterized using 6208 Chinese and English public reviews. A structural equation model (SEM) shows that all six categories of subjective psychological perception—atmosphere, aesthetics, pleasure, comfort, arousal, and dominance—exert significant positive effects on behavioral intention, with atmosphere, aesthetics, and pleasure being the most prominent. Cross-source ranking comparisons further show that the objective light-element proportion is strongly consistent with predicted visual attention, whereas greater attention capture does not necessarily translate into higher aesthetic, comfort, or behavioral-intention ratings. At the case level, Grand Lisboa and Wynn Palace exemplify two contrasting nightscape configurations based on iconic light elements and holistic illumination, respectively. This study thus provides a reproducible data pipeline for commercial nightscape lighting evaluation and offers an analytical perspective for nighttime destination management that jointly weighs visual evidence and human-centered perception.