Fraud Detection and prevention is a collection of machine learning techniques designed to identify, monitor, and prevent fraud. There are many different ways of committing fraud including stolen credit cards, identity theft, phishing, chargebacks, etc. Machine Learning algorithms can allow early detection and prevention of fraudulent behavior in online institutions.  

Potential Applications: Identity Theft, Chargebacks, Credit Card Frauds, Chargebacks

Customer segmentation is the process of dividing the customer base into different sub-groups based on some type of shared characteristics.  The aim is to identify high yield segments that are likely to be the most profitable, or have the highest growth potential, so that these can be targeted with special marketing.

Potential Applications: Ad targeting, User Engagement, Targeted Messaging

Targeted marketing uses machine learning models to personalize and tailor online advertising intended for specific customer segments. Targeted marketing allows online businesses to attract promising leads, and increase customer loyalty.  

Potential Applications: User Engagement, Ad Revenue, Increased Sales

Uses econometrics and machine learning models to determine the risk of default that may arise from a borrower failing to make required payments. Optimal credit risk models allows lending institutes to maximize returns while minimizing risk

Potential Applications: Loan Approvals