Sign in
Sign in
or
Create a new account
Categories
Your Saved List Partners Sell in AWS Marketplace Amazon Web Services Home Help
Amazon SageMaker ×

Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.

Autoencoder for Fraud Detection
Free Trial

By: FraudML Latest Version: v1

The algorithm trains a sparse autoencoder model to predict on classification datasets directly from CSV data.

Product Overview

This deep autoencoder is trained using TensorFlow and seeks to provide greater performance when compared to traditional anomaly detection techniques. The deep autoencoder returns a probability score, which corresponds to the probability that the customer/transaction is fraudulent. The algorithm trains a deep autoencoder model to predict on classification datasets directly from CSV data. The algorithm can save time by automating time-consuming manual steps such as feature engineering and feature selection. It can detect anomalies in highly-imbalanced data sets. The algorithm is ideally used to detect anomalies in transactional data

Key Data

Version
By FraudML
Categories
Type Algorithm
Fulfillment Methods Amazon SageMaker

Usage Information

Fulfillment Methods

Amazon SageMaker

For large datasets with > 100,000 rows or > 1,000 columns, use larger instance type. For best results, provide all your data to Deep Autoencoder as train_data rather than splitting a validation set yourself. The algorithm handles missing data, manual feature transformations, data splitting, model selection, algorithm selection, hyperparameter selection and tuning, and repeating the process when data changes.

The first line of your CSV file should contain names for each column. Columns in your CSV file can be strings/text-fields/Numeric.

Deep Autoencoder requires no manual data preprocessing as long as your data is a valid CSV table. Your data must contain the column that you identify as 'label' in your hyperparameter configuration.

The model returns a probability score as output, which is the likelihood that the record is an anomaly.

Additional Resources

End User License Agreement

By subscribing to this product you agree to terms and conditions outlined in the product End User License Agreement (EULA)

Support Information

Autoencoder for Fraud Detection

For any issues please feel free to contact us at info@fraudml.com

www.fraudml.com

AWS Infrastructure

AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services. Learn more

Refund Policy

N/A

Customer Reviews