24We aimed to describe multiple dimensions of poverty according to the capability 25 approach theory by applying data mining approaches to the Cuatro Santos Health 26 and Demographic Surveillance databases, Nicaragua. Four municipalities in northern 27 Nicaragua constitute the Cuatro Santos area, with 25,893 inhabitants in 5,966 28 households (2014). A local process analyzing poverty-related problems and 29 prioritizing suggested actions, was initiated 1997 based on a community action plan 30 2002-2015. Priority interventions were school breakfasts, environmental protection, 31 water and sanitation, preventive healthcare, home gardening, micro credits, technical 32 training, stipends for university education, and the use of Internet. In 2004, a survey 33 of basic health and demographic information was performed in the whole population 34 followed by surveillance updates in 2007, 2009, and 2014 linking households and 35 individuals by unique identifiers. Information included the house (floor, walls) and 36 services (water, sanitation, electricity) as well as demographic data (birth, deaths, 37 migration). Data on participation in interventions, on food security, household assets, 38 and women's self-rated health were collected in 2014. A K-means algorithm were 39 used to cluster the household data (54 variables). The poverty ranking of household 40 clusters using the unsatisfied basic needs index (UBN) variables changed when 41 including variables describing basic capabilities. The households in the fairly rich 42 cluster, having assets as motorbikes and computers were described as modern. 43 Those in the fairly poor cluster, having different degrees of food insecurity were 44 labeled vulnerable. Poor and poorest clusters of households were traditional e.g. in 45 using horses for transport. Results displayed a society transforming from traditional 46 to a modern, where the forerunners were not the richest but educated, had more 47 working members of household, fewer children and were food secure. Those lagging 3 48 were the poor, traditional and food insecure. The approach and results may be useful 49 for an improved understanding of poverty and to direct local interventions. 50 51 Key words: multidimensional poverty, capability approach, health and demographic 52 surveillance, data mining, K-means clustering, poverty alleviation 53 54 Word count abstract: 299, main text incl., tables: 5,729 55 4 56