High level of blood glucose is a key indicator of diabetes mellitus, with 90% of the worldwide cases attributed to Type 2 diabetes. This illness requires constant attention, putting a huge monetary toll on patients and their families. Research has shown a worldwide presence of diabetes, which has affected 10.5% of the adult population in the age group of 20–79 years. Projections suggest a stunning raise to 783 million cases by 2045. Diabetes increases the risk and complications of other diseases and may even cause untimely death. Existing literature has shown the implemented machine learning and deep learning approach on traditional datasets. Local and current datasets based on the Indian population are unavailable. The aim of this research is to create an optimized model to predicts the occurrence or non-occurrence of diabetes mellitus, on the Pima Indian diabetes (PID) dataset. The proposed Artificial Neural Network (ANN) model employs several hidden layers in an ANN with RMSprop and Adam optimizers. This study focuses on training the model using epochs, and studying its behavior on the performance of the model. Three hidden layers in an ANN showed a maximum accuracy of 84.42%, using the Adam optimizer. This study demonstrated that, in some scenarios, larger epochs did not reduce the validation loss, and hence did not improve the model’s performance. The model was validated through various performance metrics. Further studies would include evaluating the accuracy of predictions with a higher number of hidden layers. Our research would augment the continual worldwide effort to fight diabetes mellitus, by advancing the computational models for optimized prediction of the disease.