Anamoly-Detection-in-Time-Series Data using LSTM in Keras

This project is to build a model for Anomaly Detection in Time Series data for detecting Anomalies in the S&P500 index dataset, which is a popular stock market index for the top 500 US companies, using Deep Neural Network LSTM in Keras with Python code. You must be familiar with Deep Learning which is a sub-field of Machine Learning. Specifically, we’ll be designing and training an LSTM Autoencoder using Keras API, and Tensorflow2 as back-end. Along with this you will also create interactive charts and plots with plotly python and seaborn for data visualization and displaying results within Jupyter Notebook.

Pre-requisites

Python Artificial Neural Networks Machine Learning Data Visualization

To read and understand full coding implementation

---**#-----#---------->>>>>>> Article Link : https://valueml.com/anomaly-detection-in-time-series-data-using-keras/ <<--#*--#$--

Algorithmic Overview

For overview of algorithm, this project si implemented in followind steps: Import Libraries

Load and Inspect the S&P 500 Index Data

Data Preprocessing

Temporalize Data and Create Training and Test Splits

Build an LSTM Autoencoder

Train the Autoencoder

Plot Metrics and Evaluate the Model

Detect Anomalies in the S&P 500 Index Data