<![CDATA[Data Mining simplifies and accelerates the process of distributing social assistance funds, namely direct cash assistance from village funds and has a significant impact. One of the causes of the problem is due to inappropriate and inaccurate data, so that assistance is often not on target and also the lack of limited access to technology to manage population data updates which causes social assistance not to reach groups of people who really need it. The purpose of this study is to apply Data Mining for the distribution of social assistance funds to the community in the Rancaekek Kulon Village Area and to find out the accuracy of the results of the application of data mining using Rapidminer Tools and also to increase the efficiency and speed in the process of distributing social assistance funds in Rancaekek Kulon Village. Data analysis and implementation with the K-Means Clustering algorithm was carried out by manual calculation using Microsoft Excel and then tested using RapidMiner software. The data used in this study is 526 data. The application of data mining using the K-Means Clustering algorithm can be used to group people who are eligible and unworthy of receiving assistance by producing 2 clusters, namely C0 (Not Feasible) and C1 (Feasible). The results obtained from the RapidMiner test were unfeasible community groups, namely C0 (Not Feasible) as many as 206 data and C1 (Feasible) as many as 320 data. Where the Davice Bouldin Index (DBI) was obtained from the formation of the cluster as much as 0.701 which means that the cluster is quite good because it is close to 0. Based on the calculation of data using Microsoft Excel, namely the Unfit Community group (C0) as many as 232 data and the Decent Community group (C1) as many as 294 data with the accuracy results obtained from the validation that has been carried out through the Davies Bouldin Index (DBI) validation on Microsoft Excel, which is 0.378]]>
