Analyze the problem statement for the real-time fraud detection use case and learn about the goals to achieve while architecting the solution.
- [Instructor] We now get to our next use case,…real-time fraud detection.…Let us look at a problem to solve.…We are going to focus on using big data…and predictive analytics in preventing…e-commerce payment fraud.…A detailed description of how payment fraud works…is provided in the linked research paper.…Your business is losing money…because of online e-commerce payment fraud…and wants to take steps…to identify and prevent them.…
When a customer buys online…and places an order,…your business wants to determine…if this is a fraudulent transaction…before it starts processing the order.…Given that customers order next-day deliveries,…your business wants to identify this…in a matter of minutes after the order is placed.…Given the volume of transactions,…your business cannot manually review…each transaction for fraud,…hence it has initiated a data science project…that will come up with a model…to predict fraudulent transactions…and stop their processing and shipping.…
Transactions identified as fraudulent…will then be taken up for manual review.…
There is no coding involved. Instead you will see how big data tools can help solve some of the most complex challenges for businesses that generate, store, and analyze large amounts of data. The use cases are drawn from a variety of industries, including ecommerce and IT. Instructor Kumaran Ponnambalam shows how to analyze a problem, draw an architectural outline, choose the right technologies, and finalize the solution. After each use case, he reviews related best practices for real-time streaming, predictive analytics, parallel processing, and pipeline management. Each lesson is rich in practical techniques and insights from a developer who has experienced the benefits and shortcomings of these technologies firsthand.
- Components of a big data application
- Big data app development strategies
- Use cases: fraud detection and product recommendations
- Technology options
- Designing solutions
- Best practices