UD.Mak Kembar is a shop engaged in the sale of cakes and bread, located in Rambung Merah. Until now, UD. Mak Kembar only uses a simple system in marketing information and recording, causing delays in marketing information and in recording sales calculations. Based on the problems above, the authors design and create a system at UD.Mak Kembar. This system applies predictions in its sales, and is built using an artificial neural network with the Backprogation algorithm. The results obtained with the best architecture 4-5-1 with an iterative process (epoch) during training with an epoch value = 75% and SSE achievement at the time of testing with SSE = 0.23950.