Machine Learning for Time Series Forecasting @ data2day

An introduction to forecasting time series with machine learning by

This is an advanced course that builds on practical experience in Python programming, data analysis, and machine learning. While we recapitulate some of the foundations, they are covered in much more detail in the following modules of Data Science 101:

  • 📓 Data Analysis with Python
  • 📓 Machine Learning with Python
  • 📓 Deep Learning with TensorFlow

Table of Contents

Curriculum

  1. Overview
    An overview over machine learning on time series.

  2. Handling Time Series with pandas
    Working with time series data as dataframes.

  3. Time Series Forecasting
    About predicting a time series several steps into the future.

    1. Forecasting with Prophet
      An easy-to-use model from our colleagues at a social media company.

    2. Forecasting with Shallow Learning
      How to apply any supervised ML regression algorithm for forecasting.

    3. Forecasting with Deep Learning
      Using recurrent neural networks to forecast a time series.

Exercise

  1. Challenge: Forecasting Taxi Demand

Additional Resources

  • Python Test Notebook
    Verify that your Python stack is working.

  • TensorFlow Test Notebook
    Verify that your TensorFlow stack is working.

  • Jupyter Cheat Sheet
    Some useful commands for Jupyter Notebook, mostly optional.


This notebook is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Copyright © 2019 Point 8 GmbH