Time Series Forecasting in R: A Down-to-Earth Approach

High-performance forecasting tools made easy to understand and apply

Created by: Bogdan Anastasiei
University Teacher and Consultant

What Will I Learn?

• Know the time series forecasting steps
• Know the essential time series components
• Know the most important forecasting accuracy metrics
• Use the moving averages and the simple exponential smoothing techniques
• Use the advanced exponential smoothing techniques: Holt and Holt-Winters
• Use extended exponential smoothing models: TBATS and STLM
• Build regression models with trend only
• Build regression models with trend and seasonality
• Understand important concepts like autocorrelation, stationarity and integration
• Use the augmented Dickey-Fuller test for stationarity
• Build autoregressive integrated moving average models (ARIMA)
• Build neural networks for time series forecasting

Requirements

• Basic R programming notions
• Basic statistics notions

Target audience

• Students in any field that requires quantitative forecasts
• Data analysts
• Wanna be data analysts
• Doctoral students
• Any person who wants to develop their skills in time series analysis and forecasting