Aim: The Objective of the work is to predict the Accuracy of Breast Cancer using a Novel Multi Layer Perceptron comparative with Cart Algorithm. Materials and Methods: The accuracy and loss are performed with the dataset from the Github library. The total sample size is 48. The two groups of Novel Multi Layer Perceptron (N=10) and Cart Algorithm (N=10) were proposed by predicting the accuracy of 93.50% Breast Cancer prediction compared with Cart Algorithm 89.60%. Results: The results proved that Novel Multi Layer Perceptron achieves better accuracy than the Cart Algorithm. The Cart Algorithm appears significantly better than Feature Selection. The Statistical insignificance difference between the Novel Multi Layer Perceptron and Cart algorithm is found to be p=0.523 (p<0.05). Conclusion: The Results proved that Novel Multi Layer Perceptron helps to predict Breast Cancer Prediction and gives more accuracy