As a crucial aspect of vitality, the economic facets of vitality at the store level have yet to be investigated in greater detail, and its relationship with micro-level perceived landscape qualities in the public realm requires further examination. The recent advancements in big data and Machine Learning (ML) have presented an exceptional opportunity to empirically investigate vitality and its association with the urban built environment. This research aims to comprehensively gather various dimensions of economic vitality for retail coffee chain, using Starbucks stores in Hong Kong as a case study. The study incorporates the previously under-researched dimension of customer sentiment, which is interpreted through the Natural Language Processing (NLP) model. Additionally, the study collects both subjectively measured landscape perceptions and objectively extracted visual features from street view imagery (SVI) using ML algorithms and crowdsourced surveys. Results indicate that micro-level perceived landscape qualities, such as scale and signage, have a greater impact on economic vitality than conventional macro-level planning characteristics. The findings of this research have the potential to inform and support a successful and economically dynamic retail model at the neighbourhood scale, further emphasizing the economic significance of human-scale landscape design in the public realm.