This course is ideal for data analysts, data scientists, researchers, and business professionals who want to learn how to forecast time-based data using Facebook Prophet. It’s well-suited for those with basic Python knowledge who are interested in predicting trends, seasonality, and future values in areas such as sales, finance, marketing, or operations. Whether you’re an aspiring data professional, a researcher working with time series data, or a business decision-maker aiming to leverage predictive analytics, this course will equip you with practical skills in time series forecasting using Prophet.
What you will learn
- Prepare your data (a Pandas dataframe) for Facebook Prophet
- Learn how to fit a Prophet model to a time series
- Plot the components of the fitted model
- Model holidays and exogenous regressors
- Evaluate your model with forecasting metrics
- Learn how to do changepoint detection with Prophet
Course Outline
Welcome
- Introduction
- Outline
Time Series Basics
- Time Series Basics Section Introduction
- Forecasting Metrics
- The Naive Forecast and the Importance of Baselines
- Walk-Forward Validation
- Suggestion Box
Facebook Prophet
- How Does Prophet Work?
- Prophet: Code Preparation
- Prophet in Code: Data Preparation
- Prophet in Code: Fit, Forecast, Plot
- Prophet in Code: Holidays and Exogenous Regressors
- Prophet in Code: Cross-Validation
- Prophet in Code: Changepoint Detection
- Prophet: Multiplicative Seasonality, Outliers, Non-Daily Data
- (The Dangers of) Prophet for Stock Price Prediction
- Prophet Section Summary