Open Research Repository ORR
Not a member yet
2835 research outputs found
Sort by
A new approach to estimate neighborhood socioeconomic status using supermarket transactions and GNNs
No full textEnding poverty in all its forms everywhere remains the number one Sustainable Development Goal of the United Nations 2030 Agenda. Governments face challenges in measuring socioeconomic status with fine spatial resolution because traditional data collection methods, such as censuses and surveys, are time-consuming, labor-intensive, performed at long intervals, and cover only a limited population. This work is a data-driven study to analyze the digital traces left by humans in supermarket transactions and model the relationship between consumption behavior and the average per capita income, proposing a proxy to estimate socioeconomic status at the urban neighborhood level. We analyze more than 20 million supermarket shopping transactions in Guayaquil, the most populated city in Ecuador. Using customer consumption data, we created a basket graph and fed it into a graph neural network to predict neighborhood socioeconomic status. The model was trained with spectral and spatial convolutional filters using cross-validation to select the best approach for the prediction. The results show that the Chebyshev spectral convolutional filter has the highest predictive power to predict the socioeconomic status of the neighborhood, with R2=0.91. Our proposed approach contributes to measuring socioeconomic status at the neighborhood level to support policymakers in making informed decisions about resource allocation according to the needs of different geographical areas
The networks of ingredient combinations as culinary fingerprints of world cuisines
No full textInvestigating how different ingredients are combined in popular dishes is crucial to uncover the principles behind food preferences. Here, we use data from public food repositories and network analysis to characterize and compare worldwide cuisines. Ingredients are first grouped into broader types, and each cuisine is then represented as a network in which nodes correspond to ingredient types and weighted links describe how frequently pairs of types co-occur in recipes. Cuisines differ not only in the popularity of ingredient types and range of recipe sizes, but also in the structural organization of ingredient-type combinations. By analyzing these networks, we uncover distinctive patterns of type associations that serve as culinary fingerprints. For example, European cuisines typically distribute ingredients across different types, whereas certain Asian and South American traditions emphasize one dominant type, such as vegetables or spices. The essence of these patterns is well captured by the networks’ maximum spanning trees, which offer a simplified yet representative backbone for each cuisine. We demonstrate that both these full and simplified network representations enable machine learning models to identify cuisines from subsets of recipes with very high accuracy. Networks of ingredient combinations also cluster global cuisines into meaningful geo-cultural groups, reflecting shared patterns in culinary traditions. More broadly, our study offers novel insights into the structure of world cuisines, enabling data-driven approaches to their characterization, cross-cultural comparison, and potential adaptation
