This project is used to detect a credit card fraud detection in an unsupervised manner. An autoencoder- based. an autoencoder with two hidden layer clustering model is build. an autoencoder with two hidden layer and K-means clustering unsupervised machine learning algorithm is used. The data has been taken from Kaggle.
Credit Card Fraud detction using Autoencoders in H2O
Machine Learning PLatform used in here is H2O, which is a Fast, Scalable, Open source application for machine/deep learning.The speciality of H2O is that it is using in-memory compression to handles billions of data rows in memory, even in a small cluster. It is easy to use APIs with R, Python, Scala, Java, JSON as well as a built in web interface. For using H2O framework, first install Java Kit.