Time Series Forecasting with LSTM Neural Network Python

Time Series Forecasting with LSTM Neural Network Python

Deep Learning Project- Learn to apply deep learning paradigm to forecast univariate time series data.

Videos

Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

What will you learn

Understanding the problem statement
Importing the problem statement
Installing Keras and LSTM
Importing the necessary libraries for applying Neural Networks
Performing basic EDA and checking for the null values
Imputing the null values using appropriate method
Plotting a Time Series plot
Creating a Dataset matrix for applying LSTM
Sequentially initializing a Neural Networks
Defining the error function
Understanding solver used "Adam"
Applying LSTM as training model
Visualizing the loss and accuracy with each epoch
Tuning the final model and using it to make predictions
Saving the predictions made in CSV format

Project Description

Deep learning is an upcoming field, where we are seeing a lot of implementations in the day to day business operations, including segmentation, clustering, forecasting, prediction or recommendation etc. Deep learning architecture has many branches and one of them is the recurrent neural network (RNN), the method that we are going to analyze in this deep learning project is about Long Short Term Memory Network (LSTM) to perform time series forecasting for univariate time series data.

Similar Projects

In this deep learning project, we will predict customer churn using Artificial Neural Networks and learn how to model an ANN in R with the keras deep learning package.

In this machine learning resume parser example we use the popular Spacy NLP python library for OCR and text classification.

In this project, we are going to talk about insurance forecast by using regression techniques.

Curriculum For This Mini Project

Deep Learning Architectures
06m
DNN - Deep Neural Network
00m
CNN - Convolutional Neural Network
01m
RNN - Recurrent Neural Network
02m
Deep Belief & Boltzman Network
01m
Deep Neural Network - Graphical Representation
20m
Activation Functions
02m
Perceptron and Bias
02m
Convolutional Neural Network - Graphical Representation
08m
Recurrent Neural Network - Graphical Representation
07m
Deep Belief & Boltzman Network - Graphical Representation
00m
Problem Statement
01m
Data Set
05m
Setting up Libraries
15m
Setting Theano as backend
01m
Import Libraries
02m
Create Seed function
01m
Normalize the dataset
04m
Split dataset into training and testing
06m
Create Dataset Matrix
07m
Reshape Dataset
05m
Create RNN or LSTM Model
04m
Make Predictions
08m
Calculate Mean Squared Error
03m
Conclusion
05m