Explore the fundamentals of Time Series Analysis using the KNIME Analytics Platform in this comprehensive tutorial. Learn essential concepts including preprocessing, alignment, missing value imputation, forecasting, and evaluation. Build a practical demand prediction application using both (S)ARIMA models and machine learning approaches. Gain hands-on experience with KNIME's Time Series components for preprocessing, transforming, aggregating, forecasting, and inspecting time series data. Discover techniques for time aggregation, trend cycle analysis, and seasonality modeling. Dive into ARIMA modeling, autocorrelation, and model identification. Explore advanced topics like seasonal ARIMA and stream learning. Access example workflows to apply these concepts in your own projects.
Time Series Analysis with the KNIME Analytics Platform - Preprocessing, Alignment, Imputation
Overview
Syllabus
Introduction
Introductions
Agenda
What is Time Series Analysis
Time Series Data
Forecasting
Preprocessing
Time aggregation
Trend cycle
Seasonality
Modeling
KNIME Prediction
Other Considerations
Motivation
Arima Model
Autocorrelation Partial Autocorrelation
Model Identification
Seasonal Arena
Seasonal lags
Recap
Stream Learner
Time Series Components
Taught by
Data Science Dojo
