Machine learning algorithms for document clustering and fraud detection

Machine Learning plays very important role in processing of large amounts of structured and unstructured data. A set of algorithms can be used to get meaningful insights into the data that are helpful in making effective business decisions. Document clustering is one of the popular machine learning technique used to group unstructured data (text documents) based on its content and further analyze the data to understand the patterns in it. The unstructured data gets transformed into semi-structured data and structured data in stages by using text mining and clustering (k-means) techniques. Classification is another machine learning technique that can be implemented for use cases like "fraud detection and cross-sell & up-sell opportunity identification" in banking, financial services and insurance industry. This paper focuses on the implementation of both document clustering algorithm and a set of classification algorithms (Decision Tree, Random Forest and Naïve Bayes), along with appropriate industry use cases. Also, the performance of three classification algorithms will be compared by calculation of "Confusion Matrix" which in turn helps us to calculate performance measures such as, "accuracy", "precision", and "recall".