Forecasting Univariate Time Series with an LSTM

Offered By
Coursera Community Project Network
In this Guided Project, you will:

compute statistics. Make visualization. Split the data for forecast validation. Define an LSTM. Forecast univariate time series with an LSTM.

ClockOne to two hours
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

Create a Jupyter Notebook in order to forecast a univariate time series (in our case new one family home sales) using an LSTM. You will also be able to tell when univariate time series have the appropriate structure to be forecasted with LSTM's or even using any other univariate forecasting techniques. This Guided Project was created by a Coursera community member.

Skills you will develop

Time Series ForecastingMachine LearningTime SeriesStatisticsLSTM's

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Define and Estimate the LSTM.

  2. Separating Data into Training and Validations Sets Format to Feed to LSTM

  3. Introduction to the Project and the Instructor.

  4. Load the data and Make Transformations.

  5. Descriptive Statistics and Visualizations the Data.

  6. Forecast the LSTM on the Validation Set and Assess Accuracy.

  7. Autocorrelations and Partial Autocorrelations Plots.

  8. Unit Root Test.

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.