The identification of producer typologies is a crucial tool for understanding the heterogeneity of agroecosystems and designing targeted policies. Andean agroecosystems, particularly those in rapidly suburbanizing areas, have been understudied in this regard, creating a critical knowledge gap. This study addressed this void by determining the typologies of smallholder agroecosystems in the suburban periphery of Cuenca, Ecuador, by applying an unsupervised machine learning technique, Partitioning Around Medoids (PAM) Clustering, to survey data from 293 farmers. Our analysis revealed three distinct typologies, highlighting a socio-economic and productive gradient defined by income sources, market access, and agrochemical use. The typologies range from economically vulnerable households to more commercially oriented and environmentally sustainable ones, underscoring the complex interplay between livelihoods strategies and environmental management. This research provides one of the first empirical typologies of suburban Andean agroecosystems, demonstrating the value of unsupervised learning for capturing farm heterogeneity in data-scarce contexts. The findings offer a robust evidence base for moving beyond one-size-fits-all approaches, enabling the design of differentiated agricultural and territorial policies that enhance sustainability, equity, and resilience at the rural–urban interface.

Macleania rupestris is an underutilized wild fruit-bearing shrub native to the Ecuadorian Andes, with considerable ecological importance and potential for sustainable local development. However, information regarding its genetic, morphological, and phytochemical diversity remains scarce. This study aimed to characterize the genetic and morphological diversity and total phenolic content (TPC) of M. rupestris populations. A multilocus analysis was performed using three previously amplified concatenated sequences. Fruit characterization was conducted using quantitative morphological and physicochemical traits, while TPC was expressed as gallic acid equivalents and determined in fruits collected from the same individuals. Relationships among genetic, fruit, phytochemical, and environmental variables were also explored. The multilocus phylogenetic structure showed no clear geographic pattern, while most fruit traits exhibited limited differentiation among provinces. However, soluble solids content (°Brix), seed number, and pedicel length differed significantly among provinces. Fruit moisture content was moderately negatively correlated with soluble solids content (r = −0.45) and moderately positively correlated with seed number (r = 0.46). These correlations represent observational associations and do not demonstrate causal relationships. No significant correlation was detected between fruit traits and TPC. These findings provide important scientific basis for the conservation, selection of promising genotypes, and future domestication of this underutilized Andean fruit species.