Time series is all around us; from the post you’ve made on Twitter, to the daily fluctuations in the financial markets - these are all examples of time-series data points that need to be analyzed. In this course, you’ll learn to classify, treat and analyze time series; an absolute must, if you’re serious about stepping up as an analytics professional.
Discover the power of time seriesYou’ll start with the basics where you’ll learn the different types of time series that exist, as well as the analytical methodologies to analyze this. Once you’ve got the fundamentals down, you’ll learn how to reformat time series data in preparation for univariate and multivariate visualizations.
Data Preparation & Time seriesEveryone wants to analyze data, but it’s important we clean this up as well. We’ll learn how to clean up time-series data using Tableau’s date functions where we’ll reshape our data based on the different time context we’re interested in. Additionally, we’ll learn the ins and outs of using LODs to automate these calculations for us!
Analyzing Time series DataIn the final parts of this course, you’ll learn about statistical techniques like Z-Values, where you’ll your very own Anomaly detection fields in Tableau to identify optimal arbitrage opportunities for a trading company! You’d have learnt what time series is, how to treat it, and more importantly, how to use statistical measures to tell an impactful story. Let’s get started!
Introduction to Time Series Analysis in TableauFree
In this chapter, we’ll begin our journey by understanding the different types of time series that exist, as well as the analytical methodologies to analyze this. Once you’ve understood the fundamental concepts, you’ll learn how to reformat time series data in preparation for univariate and multivariate visualizations.An introduction to time series50 xpTime series classification100 xpDate time formatting in Tableau50 xpReformatting with datename100 xpPartitioning with datepart100 xpDate transformations and visualizations50 xpDate time knowledge check50 xpReformatting dates in Tableau50 xpTruncating dates100 xpCalculating durations from date timestamps100 xpClassifying time series data100 xpAnalyzing ridership behaviour100 xp
Data Preparation for Time Series Analysis
Everyone wants to analyze data, but it’s important the data is clean. In this chapter, we’ll learn how to clean up time series data using Tableau’s inbuilt date functions where we’ll reshape, split and rejoin our data based on the different time context we’re interested in. Beyond this, we’ll dive into the concepts of seasonality, trend analysis and anomaly detection!Date string manipulation and reformation50 xpValid or not?50 xpReforming dates in practice50 xpParsing the date100 xpWeekly truncations100 xpSeasonality and anomalies in time series data50 xpAnomalous techniques50 xpVisualizing seasonality and percentiles50 xpChanging the seasons100 xpTrending matters100 xpSeasonal variance with box plots100 xpAnalyzing avocado pricing discrepencies100 xp
Windowing Functions and Moving Averages in Tableau
In this final chapter, you’ll learn all about the powers of window functions and statistical techniques like Z-Values, where you’ll create your very own anomaly classifiers to identify optimal pricing arbitrage opportunities for a trading company! In the second part of this chapter, we’ll compare multiple anomaly detection techniques, equipping you with a broad range of approaches to treating and analyzing time series!Window functions in Tableau50 xpUnderstanding window functions50 xpCalculations with window functions50 xpSmoothing data with moving averages100 xpSelecting moving average time windows100 xpIdentifying relationships with window correlations100 xpAnomaly detection with window functions50 xpMuscle memory with Z-scores and standard deviation100 xpA deep dive into window calculations50 xpUnpacking volatility100 xpSetting upper boundaries100 xpAnomaly detection with Z-scores100 xpCongratulations!50 xp
Chris HuiSee More
VP at Tracked
Chris currently works as the VP of Product & Analytics at Tracked, an analytics edtech startup. He oversees data science and data engineering teams spanning the US, Australia, and Southeast Asia. Prior to Tracked, Chris created and spearheaded the course creation of the Microsoft, Amazon, and Walmart Data Analytics Career Tracks; educational initiatives aimed at those coming from non-technical backgrounds. Prior to this, Chris excelled in various data scientist roles specializing in time series analysis where he leveraged machine learning to predict asset failure and commodity movements across energy markets. Beyond his professional commitments, Chris mentors aspiring data scientists in the Tracked and Springboard analytics programs.