Checklist: 6 Must-Haves for Your Advanced Analytics
Overview
Your data holds the key to everyday business opportunities and eureka moments alike. It’s your job to uncover them. And it’s the job of your visual analytics tool to facilitate the exploration that leads you there. It should augment your intellect and curiosity. It should equip you with the ability to ask deeper questions of your data—to go beyond the standard KPIs and unearth new meaningful insights.
To empower users to ask deeper questions, a visual analytics tool should make powerful analytic techniques addictive. You should be inspired to ask sophisticated questions of your data with advanced analytics that are both accessible and mature.
To uncover the power of advanced analytics—with or without coding—here’s what your visual analytics tool should allow you to do:
1. Stay in the Flow
A visual analytics tool should allow you to ask deeper questions while staying in the flow of your analysis. When you leave your analysis to work in a wizard, write code in another application, or painstakingly connect to a new data source, you lose the magic of your train of thought. You stop exploring. Our brains don’t deal well with interruptions, so you want to select a tool that minimizes them.
Your visual analytics tool should have advanced analytics built in seamlessly, with drag-and-drop ease, so you stay in the flow. Asking the next question should be a natural part of your data exploration.
Learn more about Show Me in the Tableau Help.
Change your perspective
Stay in the flow with Tableau's intuitive interface. Features like Show Me instantaneously reveal the rich analytical stories in your data. Here, we visualize tourism by country as side-by-side and stacked bar charts, dual lines, and more. Dig deeper into the tourism data in an interactive analytics game:
2. Segment with Ease
Groups, sets, and cohorts can shed new light on data. Do customers who were acquired through a direct mail campaign spend more over time than customers who were acquired through a Google ad? How do graduation rates trend by major? What if you look at the data by major and the year they started school? Your visual analytics tool should allow you to ask these types of questions to create groups, define sets with logic, and adjust cohorts—without needing to modify the underlying data.
This kind of slice-and-dice visual analysis allows people to explore data and test hypotheses while staying in the analytical flow. Segmenting should be intuitive, simple, and accessible, while remaining powerful.
Groups, sets, and cohorts should update seamlessly along with the underlying data, without manually running scripts or data refreshes.
Learn more about segmentation in Advanced Analytics with Tableau.
Group it up
Creating groups in Tableau adds incredible value to your viz's ability to highlight the right data points, and they're just one click away. Here, we highlight the top-performing countries in terms of tourism expenditure by grouping them and sorting. Dig deeper into the tourism data in an interactive analytics game:
3. Ask "What If?"
When you’re exploring data, you want it to be easy to change the inputs of your analysis. For instance, you may want to change a click-through rate while assessing the performance of a Facebook ad campaign, the price basis in a cost-benefit analysis, or the commission percentage in a sales model. These “what if” analyses shed light on key business questions.
Changing the parameters for what variables are displayed allows you to conduct and share more types of analyses in one visualization or dashboard easily. Your visual analytics tool should offer a flexible set of input controls that allow you and your audience to adjust numbers, text and dates to see how they influence results.
Learn more about what-if analysis in Advanced Analytics with Tableau.
Give me the parameters
By using fields from your data set as parameters in Tableau, you empower everyone to find the angle they're looking for with rapid data comparisons. Here, we create two views—one for tourist arrivals and one for departures—on the same map, so it's immediately obvious how tourism compares by country. Dig deeper into the tourism data in an interactive analytics game:
4. Dive Deeper with Calculations
Your data source doesn’t always contain exactly the fields you need to do your analysis. You’ll want to be able to apply calculations and logic to your source data to create new fields—while staying in the flow of your analysis, of course. Your visual analysis tool should make this easy, providing a built-in language that’s expressive and flexible.
Rather than writing complex SQL group-by statements, choose a tool that makes level-of-detail calculations simple. You’ll also want the built-in calculations to work well with relative data in a table, making it easy to create running sums, rankings and weighted averages.
A tool that offers sophisticated built-in calculations will save you hours of writing SQL code—and it can open up a world of advanced analytics to people who aren’t familiar with SQL or other coding languages.
Learn more about LOD calculations in our blog post Top 15 Level of Detail expressions.
Write a calc
Tableau's robust built-in calculation language means you can always find a path forward in your analytic journey. Here, we write a calc for percent of total tourism expenditure by country, and visualize the results in a filled map. Dig deeper into the tourism data in an interactive analytics game:
5. Track a Trend and Predict the Future
Choose a visual analytics tool that allows you to analyze the history of a time series and predict what will happen moving forward. Whether you’re tracking sales trends, graduation rates, or temperature patterns, trend lines and forecasts provide meaningful insight into your data.
You should be able to break down time and date fields intuitively and visually, and to create groups and cohorts that make sense for trends that interest you. It should be natural to explore seasonality and patterns. You should be able to aggregate and disaggregate data with a click—as well as change aggregation frequencies, allowing you to explore trends by month, quarter, year and more. Plus, relative date filters should allow you to answer questions like, “How has the cost of goods changed in the past year?”
Your visual analytics tool should go beyond linear trend lines, allowing users to explore logarithmic, polynomial, and exponential fits. And it should be easy for anyone to determine whether the trend line is a good fit, with p-values and R-squared available with a click. If you want to apply running total or running average calculations to your time series, you should be able to do that, too, to get even deeper insights.
Discover all Tableau's methods for trend and predictive analyses in Advanced Analytics with Tableau.
So trendy
In Tableau, trend lines are right where you need them, so you can verify that your p-value is statistically significant and get to next steps. Here, we perform trend analysis on in-country tourist spend to understand the trajectory for the tourism industry by region. Dig deeper into the tourism data in an interactive analytics game:
6. Integrate with R and Python
While a good visual analytics tool makes sophisticated analytics accessible to an everyday user, it’s worth noting that many organizations also invest in advanced statistics platforms like R, SAS and SPSS. These create their own analytical value—and since they’ve been around many organizations for years, they can contain valuable existing work. Your visual analytics tool should be able to leverage these investments.
Integration with R provides access to advancements in the wider statistical community, and it also creates a wider audience for work done in R. When you select a tool that can quickly visualize the output of advanced statistical tools, you create an environment in which non-technical users can make decisions and leverage the work done by data scientists and statisticians.
Learn how to Leverage the power of Python in Tableau or what Using R and Tableau looks like.
R u into Python?
Integrate with R and Python directly in Tableau so you can leverage preexisting models or script in-app. Here, we perform multiple linear regression to discover how many tourists are required to reach a specific income goal. Dig deeper into the tourism data in an interactive analytics game:
Get to the Good Stuff with Tableau
Standard KPIs and metrics answer some of your questions, but in a fast-changing world you need a tool that inspires deeper exploration of data. Look for one that empowers users to go beyond the first question and ask the next one, and then the one after that, inspiring “a-ha!” moments again and again. You want a solution that is both sophisticated enough for a data scientist and accessible and intuitive for a business user, so everyone can stay in the flow of their analysis, moving with their questions at the speed of thought.
In many ways, Tableau stands alone among analytics platforms. Because of our mission to augment human intelligence, we designed Tableau with both the business user and data scientist in mind. By staying focused on our mission to empower users to ask interesting questions of their data as quickly as possible, we built a platform that has valuable functionality for users of all levels.
Tableau’s flexible front-end allows analysts to ask questions of varying complexity. By leveraging sophisticated calculations, R and Python integration, rapid cohort analysis, and predictive capabilities, data scientists can complete complex analyses in Tableau and easily share the visual results. Whether you use Tableau for data exploration and quality control, or model design and testing, the interactive nature of the platform saves countless hours across the lifetime of a project. By making analysis more accessible and faster to complete at all levels, Tableau drives critical collaboration and better decision-making throughout the enterprise.