Skip to content

Anomaly detection in multivalent financial time series using RNNs and TensorFlow

License

Notifications You must be signed in to change notification settings

frouhi/anomaly_detection_RNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Anomaly Detection Using RNNs and TensorFlow

Author

  • Farhang Rouhi

Introduction

This program is for anomaly detection in any financial data that includes [open,high,low,close,volume] fields. First, we create a Recurrent Neural Network (RNN) to forecast [open,high,low,close] fields in the financial times series. Note that the financial data used in this program is multivariate time series in order to increase accuracy of anomaly detection step. After training the model, it is used to predict [open,high,low,close] fields. If error of all four fields pass a threshold, that data point is marked as anomalous. At the end, a plot visualizes the anomalies.

About

Anomaly detection in multivalent financial time series using RNNs and TensorFlow

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages