Forecasting and Time Series Analysis in Tableau

Name: Forecasting and Time Series Analysis in Tableau
Rating: 4.5 (684 reviews)

Use Tableau to work with time series, generate forecasts and even add R functionality to enhance Tableau.

Created byR-Tutorials Training

Last updated 12/2018

English

English [Auto],Korean [Auto],

What you'll learn

visualize time series in Tableau
perform calculations with time series data in Tableau e.g. SMA calculations
use time series specific Tableau functions
use the Tableau forecasting tools for exponential smoothing models
understand the generated forecast models
integrate R into Tableau in order to enhance forecasting capabilities

Course content

4 sections • 27 lectures • 3h 54m total length

Introduction3:18
Master time series in Tableau with exponential smoothing forecasting, moving averages, and Arima models via R integration, while learning time-based data roles, functions, and practical exercises.
Orientation - Course Fundamentals3:00
Discover how the forecasting and time series analysis in Tableau course is organized into sections on general time series concepts, Tableau forecasting, and ARIMA with R integration for advanced models.

Which Data Role Do I choose?9:09
Master time series concepts in Tableau by distinguishing discrete and continuous date fields and their axis or header, including hierarchy and granularity. Visualize time series with line and area charts.
Tracking Changes in Time Series10:32
Build a three-year sales line graph in Tableau from a data extract and compare discrete versus continuous date levels while applying a percent-difference table calculation to show month-over-month changes.
How to get a Smoother10:22
Learn to create moving averages in Tableau, compare simple and exponential methods, adjust window sizes (10 vs 30 days), and refine visuals with dual axes and synchronized scales.
Coding a Smoother13:22
Create an interactive Tableau visualization by driving a moving average with a parameter and table calculations. Wire in start and end points with a case function for correct window sizing.
Moving Average - Exercise7:56
Learn to build a Tableau visualization of a 21-day moving average of sales over time, with start and end date controls, and a boolean date filter using table calculations.
Creating a Custom Forecasting Line9:12
Create a forecasting line in Tableau by combining a running total of sales with a reference line and a forecast parameter, using a calculated field and a shared axis.
The Discrete Data Role10:00
Explore how discrete and continuous data roles affect date fields in time series visualizations in Tableau, including handling weekdays, business days, and level of detail techniques for multi year data.
Time Series Differences - Excercise8:14
Explore time series differences in Tableau by building running totals for three years, visualizing year differences with area charts, and refining with table calculations, reference lines, and a month filter.
Relative Date Filtering12:37
Learn to create up-to-date visualizations in Tableau by applying relative date filtering with today, now, and date-part calculations, including last-month filters for consistent month-level comparisons.
Tableau Date and Time Functions7:39
Explore Tableau's date and time functions, from dynamic today and now values to date part, day, month, year, and date name, with date add and date diff calculations.
Another Case Of Relative Date Filtering12:10
Create a dynamic Tableau visualization showing the latest order per partner using a last table calculation, with a months to contact parameter and robust date-diff logic.
Combined Chart - Exercise5:39
Create a combination chart in Tableau showing monthly sales as tri-colored bars and a switchable running total or running average line, with a category filter.

Forecast Theory7:37
Explore forecasting theory in Tableau using exponential smoothing, trend and seasonality concepts. Learn about optional ARIMA with R, model selection, and practical data requirements.
Forecast Summary12:51
Learn to create a basic Tableau forecast using a date or integer dimension, with monthly data, applying exponential smoothing and a seasonal model to produce a 95% forecast interval.
Forecast Models5:39
Explore a seasonal additive forecast in Tableau using exponential smoothing, with initial level, seasonal components guided by alpha, beta, and gamma; assess accuracy via root mean square error.
Customizing The Forecast Plot12:47
Customize your forecast plot in Tableau by adjusting forecast length, data aggregation, missing data handling, and the forecast model type, then set the prediction interval and read the model summary.
Using The Row ID To Forecast4:13
Substitute a date with an integer row ID to forecast when no time variable exists; use an ordered integer dimension to generate forecasts with whisker intervals and diverse mark types.
Changing The Forecast Result7:18
Explore how to display and interpret forecast results in Tableau, including trend, precision (absolute and relative), quality, and prediction intervals, with guidance on additive versus multiplicative models and confidence levels.
Exercise - Passengers7:09
Forecast and analyze the passengers dataset in Tableau, exploring trend and seasonality and applying a multiplicative level, additive trend, and multiplicative seasonality model; extend forecast to two years.

Orientation9:48
Explore how to extend Tableau forecasts with R by integrating ARIMA and exponential smoothing models through calculated fields, addressing data length limits, and preparing your environment with the forecast package.
Connecting Tableau and R3:36
Activate the Rserve library and start Rserve to establish a local Tableau–R connection, then configure Tableau to localhost:6311 and test the link for R calculations.
R Code in Tableau - Exponential Smoothing14:23
Learn to integrate R code within Tableau to forecast time series data using the forecast package, auto.arima, and a flexible table-calculation workflow with yearly visitor data.
ARIMA in Tableau10:59
Set forecast periods with a parameter in tableau and apply an arima model to forecast ten periods, differentiating actual and forecast values with calculated fields.
Comparing Plots11:57
Compare multiple forecasting models in Tableau by plotting exponential smoothing and Arima forecasts side by side or via interactive switches, using parameters and calculated fields in dashboards.
Conclusion3:08
Conclude with a practical tour of Tableau time series handling, building forecasts with parameters, reading forecast descriptions, and using Tableau with R for advanced models.

Requirements

A prior general understanding of Tableau is recommended
NO skills of R are required to follow along
you should have a computer with Tableau ready

Description

Do you want to know how to handle time series in Tableau?

Do you want to use Tableaus forecasting feature to get great visualizations?

Or you probably want to know how to add extra forecasting features like ARIMA models to Tableau?

Time based data has its own rules and implications. We will discuss these in Tableau. Quite often time series data is used to look into the future. Forecasting is the name of the game here. Luckily Tableau offers an exponential smoothing forecasting tool, which we will of course explore.

Sometimes you might find that Tableau's internal forecasting tools are too limited. Well, for these instances I will show you how to integrate the R forecast package into Tableau to do ARIMA modeling. This whole process is so well implemented that it can be done without prior R knowledge. In one of the last sections I will show you how it’s done, step by step.

So what are you going to learn in the course?

We start with the general knowledge you need to work with time series data. Especially data roles. We will then discuss moving averages which are widely used in time series analysis. And we will do some time based filtering. We will of course write our own functions, we will create parameters and you will also learn about the time based functions Tableau has to offer. Each of these things will be enforced with exercises.

That is the first section, after that we will be forecasting with Tableau, that means exponential smoothing. I will show you how to read the results you get and how to manually modify the forecast settings.

That is one way of forecasting in Tableau, but there is an advanced alternative. You can use R from within Tableau to perform advanced forecast modeling as we will learn in the last section of the course.

So how do you best prepare for this course?

Well, I built the course for people who already know a bit about Tableau. You should be able to get data into Tableau and to orient yourself in the interface. You should know the basics already. That way we can focus on time series and forecasting and we do not waste precious time on basic things you might already know.

You do not need R skills, although it is an advantage. The methods outlined in the last section are explained in a way so that you can follow along easily.

I hope you will enjoy this course - do not forget to add it to your CV, so that human resources knows that you train yourself on the latest technologies. Valuable skills are definitely a career booster.

Who this course is for:

Data science professionals
Business intelligence staff
People working in data visualization related positions
Everybody interested in data visualization of time series and forecasts

Forecasting and Time Series Analysis in Tableau

What you'll learn

Explore related topics

Course content

Introduction2 lectures • 6min

Working with Time Series in Tableau12 lectures • 1hr 57min

Creating a Forecast Using Tableau's Internal Toolbox7 lectures • 58min

Custom Forecasting Using R Integration in Tableau6 lectures • 54min

Requirements

Description

Who this course is for: