Amazon SageMaker for Financial Services

Prepare, build, train, and deploy high-quality machine learning models for financial services use cases

Today, hundreds of thousands of customers including top financial services organizations such as Intuit, Vanguard, Coinbase, NuData, and more, use Amazon SageMaker for machine learning (ML). The increasing growth in online transactions and the subsequent need to improve security, privacy, compliance, and governance is top of mind for financial services organizations. Financial services organizations use ML to address these needs and detect fraud, assess credit risk, and automate operational processes. SageMaker brings together a broad set of capabilities purpose-built for ML helping financial services organizations prepare, build, train, and deploy high quality ML models to support regulatory and compliance mandates and exceed the highest customer expectations.

Top use cases for Amazon SageMaker

Fraud detection

Fraud detection

Financial services companies are looking to automate detection of suspicious transactions and other anomalous behavior faster to strengthen customer trust. With Amazon SageMaker, you can build ML models to detect suspicious transactions before they occur and alert your customers in a timely fashion. SageMaker provides built-in ML algorithms, such as Random Cut Forrest and XGBoost, that you can use to train and deploy fraud detection models. In addition, SageMaker provides a set of solutions for fraud detection that can be deployed readily with a few clicks.  

Credit risk prediction
Credit risk prediction

 
A borrower's failure to make payments is a key source of risk for financial institutions granting loans. Amazon SageMaker helps financial companies build high quality ML models that forecast the likelihood of a loan default to maximize risk-adjusted returns. SageMaker provides capabilities to create automated workflows and pipelines, thereby accelerating model deployment. In addition, SageMaker gives you the capability to identify and limit bias, and offer explanations to risk reviewers and customers. With SageMaker, you can also deploy a credit risk prediction solution with a few clicks.
Claims automation
Claims automation

 
Financial services companies are looking to help agents make faster decisions and in turn minimize the time to provide claims to customers. With Amazon SageMaker, you can build ML models to automate the claims process, detect false claims, and accelerate processing claims at scale. You can use SageMaker to easily build a training dataset from unlabeled data, such as images related to vehicle damage. SageMaker also checks for bias on a specified feature, such as age, in your initial dataset or trained model, and you receive a detailed report that quantifies different types of possible bias.

Customers

NuData Security Mastercard

NuData Security uses Amazon SageMaker to improve detection of fraudulent attacks such as credential stuffing.

Learn more

Fannie Mae

With Amazon SageMaker, Fannie Mae can develop and improve ML models to assess loans and analyze property values so lenders can make the right decisions.

Learn more

Intuit

Intuit uses Amazon SageMaker as part of a centralized ML platform which reduced the time required to deploy ML models by 90%.

Learn more

 

Coinbase

Coinbase can recognize anomalies in sources of user identification using Amazon SageMaker, so they can quickly take action against potential fraud.

Learn more

Resources

Solution


Fraud detection in financial transactions

Get started »


Explain credit decisions with Amazon SageMaker

Get started »


Learn about best practices with ML in financial services

Read white paper »


Learn to build secure and compliant end to end ML workflows

Watch webinar »


Build a secure ML environment with Amazon SageMaker

Get started »


Machine learning best practices in financial services

Read blog »


Creating high-quality machine learning models for financial services using Amazon SageMaker Autopilot

Read blog »