Machine Learning is the practice of using algorithms from extracted data and learns from it then makes a decision. We use subroutines on software with a specific set of instructions to accomplish a particular task. The machine is trained using large amounts of data and algorithms that give the ability to learn how to perform a specific task. One of the most common techniques for processing large amount of data is machine learning. Machine learning employs to detect an occurrence for fraud in the system. The computational algorithm built in computer model will process all transactions happening on the digital platform. Deep learning a subset of machine learning, utilizes an ANN to carry out the process of machine learning. The ANNs are built like the human brain, with neuron nodes connected together. Traditional methods programs build analysis with data in a linear way, the deep learning system activated machines to process data with a non linear approach. Deep Learning is still an extension of traditional neural network. It is type of machine learning technique that employs the deep neural network. Deep neural network is the multilayer neural network that contains two or more hidden layers. ConvNet is a technique that uses deep learning approach that is used for image recognition. ConvNet has conquered most computer vision techniques and is growing at a rapid place. ConvNet is deep neural network that has many hidden layers. It intimates how the visual cortex of human brain processes and recognizes images. Neural networks have a hard time understanding this concept on first encounter. ConvNet differs in concept and operation from previous neural networks. The deep neural network learning rule becomes the algorithm that generates the model from the training data. The deep neural network learning rule becomes the algorithm that generates the model from the training data. Deep Learning allows the development, training and use of neural networks.