With the rapid iteration of mobile internet technologies and the continuous development of social media ecosystems, social commerce has emerged as the fastest-growing sub-sector in the global e-commerce domain. However, against the backdrop of fragmented user attention and intensifying platform competition, how to effectively enhance users’ online purchase conversion rates remains a shared challenge for both academia and industry. Existing research predominantly employs single-factor analyses based on traditional technology acceptance models or the theory of planned behavior, lacking systematic exploration of multi-factor synergistic effects. This study, based on the AISAS (Attention-Interest-Search-Action-Share) consumer behavior model, integrates grounded theory and fuzzy-set qualitative comparative analysis (fsQCA) to reveal the multidimensional driving mechanisms of user purchase decisions in social commerce contexts and provide theoretical support for platform operation optimization. This research adopts a mixed-methods approach to construct its theoretical framework. First, grounded theory is applied to conduct in-depth interviews with 60 active users from representative platforms, including Douyin Mall, Xiaohongshu, and Pinduoduo, extracting core categories through three-stage coding. Subsequently, fsQCA is employed to perform configurational analysis on 363 valid questionnaires, exploring the synergistic effects of antecedent conditions. The study selects the AISAS model as its theoretical framework, particularly focusing on users’ complete behavioral chain from attention triggering to sharing diffusion. In terms of methodological innovation, it transcends the linear thinking of traditional regression analysis by adopting a set-theoretic perspective to deconstruct the multiple concurrent causal relationships in user decision-making. Through in-depth interviews with active users, this study first identifies seven core elements influencing user purchasing behavior: (1) online advertising effectiveness; (2) stimulating online reviews; (3) recommendation engines; (4) platform image; (5) perceived risk; (6) social sharing; and (7) social support. fsQCA analysis reveals five equivalent pathways leading to high online purchasing behavior: (1) Impulsive type: Core drivers include advertising effectiveness, recommendation engines, and social support; (2) Browsing type: Key drivers encompass online advertising effectiveness, recommendation engines, and social support; (3) Dependent type: Principal factors involve online advertising effectiveness, platform image, social sharing, and social support; (4) Autonomous type: Core determinants consist of platform image and social sharing; (5) Stable type: Fundamental drivers include online advertising effectiveness, platform image, and social support. Two equivalent pathways lead to non-high online purchasing behavior: (1) Independent type: Missing core conditions include online advertising effectiveness, recommendation engines, and social support; (2) Cautious type: Absent critical factors comprise online advertising effectiveness, recommendation engines, and platform image. Compared with existing literature, the marginal contributions of this paper are threefold: First, it pioneers the application of the AISAS model as the foundational theoretical framework for investigating online purchasing behaviors on social commerce platforms. Second, in factor identification, it combines semi-structured interviews with theoretically-oriented interviews, conducting a three-stage coding analysis based on grounded theory to explore determinants of user purchasing behavior. Third, in analyzing interactive effects, it adopts fsQCA to examine the synergistic effects of antecedents from a configurational perspective, revealing differentiated driving pathways and multiple concurrent causal characteristics underlying high/non-high purchasing behaviors. Therefore, this study not only extends theoretical research on the AISAS model, grounded theory, and fsQCA applications, but also provides practical insights for users and social commerce platform management.