Soji Adeshina

Amazon Neptune is a fast, reliable, fully managed graph database service that makes it easy to build and run applications that work with highly connected datasets. Purpose-built to store and navigate relationships, graph databases can be used to store fraud graphs, which contain information on how actors, transactions, and other identifiers are related to each other.

Machine learning techniques can help find hidden correlations in graphs with billions of relationships. These correlations can be useful when recommending products, predicting creditworthiness, identifying fraud, and more.

Join this chalk talk to explore the Amazon SageMaker solutions designed to help you get started faster with machine learning (ML). Each of the 20 solutions accelerates your ML journey by offering a dataset and model for common ML use cases, such as predictive maintenance, churn prediction, and credit risk, so you can move quickly from concept to production.

Machine learning (ML) is helping to mitigate a universally expensive problem—fraud. This session is for data scientists and ML developers who want to dive deep and use prebuilt algorithms and models on Amazon SageMaker to help their organizations spot fraud sooner.

There are many practical applications for computer vision systems, and AWS AI services make it easy for developers to add visual recognition capabilities to their programs. In this builders session, you learn how to use AWS DeepLens and Amazon Rekognition to build an application that helps identify whether a person at a construction site is wearing the correct safety gear, in this case, a hard...