According to data from the Health Profile Book of Sidoarjo Regency in 2018 where in Sidoarjo regency, including in the Sukodono sub-district, Jumput Rejo village in 2018, the number of toddlers is 175,393 with toddlers weighing 118,464. From the weighing results, it can be seen that under-five under the red line (BGM) status is 733 (0.6%) with details of 344 boys under five and 388 girls. This indicates that there are still toddlers with poor nutritional status. Monitoring the physical growth of children is carried out using parameters including anthropometric measurements. In general, the anthropometric indices used are body weight for age (BW / U), height for age (TB / U). The purpose of this study was to group the anthropometric data of toddlers in determining their nutritional status in the Jumput Rejo Village, Sukodono District, Sidoarjo Regency. The method used is using data mining techniques with the K-Means algorithm. This research resulted in 5 clusters where the number of children under five in cluster1 = 37 under five where the toddlers at the ivory image posyandu need special attention because there are 11 toddlers who suffer from malnutrition. In cluster2, the number of children under five who suffer from malnutrition is 30 under five, especially those at the posyandu puri Sejahtera 3, which is 7 children under five. In cluster3 there are 28 children under five, where this cluster is included in the good nutrition cluster, especially for children under five at Posyandu Surya Asri 2 B, totaling 7 people. Whereas in cluster 4 which is included in the over nutrition cluster there are 33 toddlers where underfives who experience more nutrition, namely toddlers at the Kedung 1 posyandu. And in cluster 5 which is a cluster of toddlers with obesity there are 22 toddlers, especially at the posyandu jumput rejo indah a number of 3 toddlers. The results of grouping the anthropometric data for toddlers in the village of Jumput Rejo Sukodono show that there are 37 infants with malnutrition status, 30 under-fives with poor nutrition, 28 under-fives with good nutrition, 33 under-fives and 22 under-fives who are obese from a total of 150 under-five anthropometric data. Keywords : Clustering, algorithms, K-Means, Data Mining, Nutritional Status