Get an outline of a blueprint for the real-time fraud detection use case by identifying individual modules, their responsibilities, and interactions with each other.
- [Instructor] We will outline the solution…for real-time fraud detection in this video.…We have our e-commerce system…that is used to collect orders from the customer.…The orders are pushed into a transactions database.…The database contains orders and customer details.…There is a separate fraud tracking system…that is used to track actual fraudulent transactions.…This system will mark transactions…in the transactions database as fraud,…so every record in this database…is marked as either fraud or not…based on investigations done later…after the order is placed.…
Your data science team…will then use the past historical data…in the transactions database…to build fraud detection models…from time to time.…The models are then persisted…in a model database…usually a file system.…Remember that this chain of process so far…is not real time,…it is a batch process where fraudulent transactions…get marked on a day-to-day basis…and models are built on a weekly…or monthly basis.…
Now we get to the real-time part of the architecture.…
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