Multivariate Time Series Prediction with LSTM and Multiple features (Predict Google Stock Price)

Build a Artificial Neural Network (ANN) with Long-Short Term Memory (LSTM) to predict value which can be impacted by multiple different features.

In this video I demonstrate how to use LSTM to predict Google Stock price (you can use any other case) by taking into consideration multiple predictors (features). Let’s say, the final stock price can be predicted by finding importance of such features as historical low price, high price, volume, adj. price, etc.

Link to github notebook: https://github.com/vb100/multivariate-lstm/blob/master/LSTM_model_stocks.ipynb

The video has 3 parts:
– Part 01. Data pre-processing (4:11)
| Step 01: Read data.
| Step 02: Data pre-processing (shaping and transformations).

– Part 02. Create a LSTM model and train it. (10:39)
| Step 03: Building-up the LSTM based Neural Network.
| Step 04: Start training.

– Part 03. Make future predictions. (13:50)
| Step 05: Make predictions for future date.
| Step 06: Visualize the predictions.

In this tutorial I used Tensorflow 1.15.0 and Keras 2.3.1

Download data from: https://finance.yahoo.com/quote/GOOG/history (check 1:59 in video).

This is real life Python code example for demonstration purposes, so the model is not very accuracy and of course could be improved or tuned.

My goal of this Python tutorial is to demonstrate how to perform LSTM predictions with multiple features (complex dataset).

Hoping it will help to undersant the way it could be implemented in real Data Science or Data Analysis projects. TIme Series forecasting with LSTM is the good choice if you want to manipulate with multiple different data features and see which ones has impact to predictions and which ones do not.

If you are interested how to run Tensorboard on this LSTM Keras model, check this tutorial: https://youtu.be/-9-Hy5dWKLE

Sorry for video quality. There were some unexpected issues with resolution.
Video Rating: / 5

Time Series Analysis (Georgia Tech) – 5.2.2 – State Space Modelling – Prediction and Estimation

Time Series Analysis
PLAYLIST: https://tinyurl.com/TimeSeriesAnalysis-GeorgiaTech
Unit 5: Other Time Series Methods
Part 2: Multivariate Time Series Modelling
Lesson: 2 – State Space Modelling – Prediction and Estimation
Notes, Code, Data: https://tinyurl.com/Time-Series-Analysis-NotesData

Creating a time series forecast when the series has a trend. Use excel’s „slope“ and „intercept“ commands to estimate the equation for a line and use it to forecast future values. Create a historical forecast using the line and compare it to actual data to evaluate the likely precision of your forecast.

Modern Time Assortment Interpretation | SciPy existing Tutorial | Aileen Nielsen

Modern Time Series Analysis | SciPy 2019 Tutorial | Aileen Nielsen

This tutorial will cover the newest and most successful methods of time series analysis. 1. Bayesian methods for time series 2. Adapting common machine learning methods for time series 3. Deep learning for time series These methods are producing state-of-the-art results in a variety of disciplines, and attendees will learn both the underlying concepts and the Python implementations and uses of these analytical approaches to generate forecasts and estimate uncertainty for a variety of scientific time series.
Tutorial information may be found at https://www.scipy2019.scipy.org/tutorial-participant-instructions
See the full SciPy 2019 playlist at https://www.youtube.com/playlist?list=PLYx7XA2nY5GcDQblpQ_M1V3PQPoLWiDAC
Connect with us!
*****************

https://www.facebook.com/Enthought/
https://www.linkedin.com/company/enthought

time series prediction