Product

Learn about our time series algorithms

Forecasting exchange rates is a critical task for traders, investors, and financial institutions. Even though different machine learning models have been studied for this purpose, Long Short-Term Memory (LSTM) networks have become the most widely adopted…

Forecasting

August 11, 2024

Forecasting exchange rates with long short-term memory networks using the RNN SageMaker algorithm

Stock return forecasting has been extensively studied by both academic researchers and industry practitioners. Numerous machine learning models have been proposed for this purpose, ranging from simple linear regressions to complex deep learning models. In this post, we examine the performance of liquid neural networks (LNNs), a new neural network architecture for sequential data.

Forecasting

June 29, 2024

Forecasting stock returns with liquid neural networks using the LNN SageMaker algorithm

Anomaly detection in financial time series plays a crucial role in identifying unusual market conditions that could affect trading strategies and pose risks to investors. Anomaly detection can help identify abnormal price movements or trading volumes associated with specific events, such as earnings announcements, release of economic indicators, or geopolitical tensions…

Anomaly Detection

January 2, 2024

Detecting anomalies in financial time series with the LSTM-AE SageMaker algorithm

Detecting anomalies in electrocardiogram (ECG) signals is critical for the diagnosis and treatment of cardiovascular diseases. The introduction of wearable ECG sensors enables long-term continuous remote monitoring of patients’ cardiac activity. However, it is unfeasible for cardiologists to manually review the large amount of data generated by real-time ECG sensors. Machine learning algorithms can automate the process of ECG analysis, reducing the need for manual inspection by healthcare providers…

Anomaly Detection

December 12, 2023

ECG anomaly detection with the LSTM-AD SageMaker algorithm

Arrhythmia classification based on electrocardiogram (ECG) data involves identifying and categorizing atypical patterns of cardiac electrical activity detected in the ECG signal. Arrhythmia classification is important for diagnosing cardiac abnormalities, assessing the risk of adverse cardiovascular events and guiding appropriate treatment strategies…

Classification

December 5, 2023

Arrhythmia classification with the LSTM-FCN SageMaker algorithm

Real-time monitoring of epileptic patients can prevent injuries and complications by alerting caregivers or medical personnel during a seizure, ensuring prompt assistance and reducing the risk of accidents or unexpected death. Continuous remote patient monitoring also allows healthcare providers to collect more accurate and detailed data on seizure frequency and duration, which enables them to tailor treatment plans more effectively…

Classification

November 17, 2023

Epileptic seizure detection with the InceptionTime SageMaker algorithm

Time series clustering is the task of partitioning a set of time series into homogeneous groups. Traditional clustering algorithms based on the Euclidean distance, such as K-Means clustering, are not directly applicable to time series data, as time series with similar patterns can have large Euclidean distance due to misalignments and offsets along the time axis…

Clustering

October 16, 2023

Clustering ECG signals with the CNN-KMeans SageMaker algorithm