This article is about how to perform Tableau Cohort Analysis to evaluate the performance of your marketing retention and acquisition efforts. One approach is to use Average Revenue per User (ARPU), dividing the revenue by the number of customers for that period. However, ARPU poses two problems:
- It doesn’t account for the age of customers
- New customer acquisition can mask a retention problem
Tableau Cohort analysis is customer centric, it enables you to compare customers in the same stage of the customer lifecycle, since their cohort is defined by their acquisition date. Cohort analysis is a part of behavioral analytics that takes the data from a given dataset and rather than looking at all users as one unit, it breaks them into related groups for analysis.
Tableau Cohort Analysis is used to study the outcomes or behavior associated with a group of people over time. Tableau you can perform cohort analyses and explore different groupings to understand consumer preferences, effect and cause relationships, and what is likely to happen to members of a particular cohort over time.
- Tableau Cohort analysis allows a company to “see patterns clearly across the life-cycle of a customer (or user), rather than slicing across all customers blindly without accounting for the natural cycle that a customer undergoes.
- While cohort analysis is sometimes associated with a cohort study, they are different and should not be seen as one and the same.
- Tableau Cohort analysis is specifically the analysis of cohorts in regards to big data and business analytics, while in cohort study, data is broken down into similar groups.
Tableau Cohort Analytics Common Use
In business, cohort analysis is most often that is used to study customer relation. A cohort is a group of subjects or customers that have a common characteristic. Cohorts can be determined by the date at which they joined a website or became a customer, by their demographic, by their age, or any other attribute that could be used to group a set of individuals.
Tableau Cohort Analytics Popular Study
A popular subject area for cohort analysis is tracking the user engagement on social network websites over the months following signup. A cohort can be based on the year and month in which a user joins the site. A metric could be the scale of users in cohort that visited the site each month after joining.
Connect to Date- or Time-Based Data
The data which you connected should consists of a date or a time based list of events per individual. These events should record behavior you want to track sign-in date, purchase date, message posting date, and so on. It can include more than one event type, and in that case you would need a unique row per individual, date, and time, event, along with any other attributes you need to form your cohorts.
Define the Cohort
Determine how you will define a cohort. If the cohort is not created as a dimension in the data, you can create calculated fields or sets.
Step 1: Collecting the data
To develop a cohort analysis, you will first need sales or website visit data over time with one metric and a unique identifier for each customer. The following fields are required:
Step 2: Data Modeling for Cohort Analysis
Events or Sales Table – The events table is the main table for our cohort analysis and it contains the mandatory fields like user_id, date, and revenue.
Step 3: Using Tableau for Cohort Analysis
Then download the Tableau Public workbook, Select it in Tableau Desktop and replace the cohort_retention_by_month_first_touch data source with your SQL server preview (cohort_retention_by_month_first_purchase).
Cohort analysis is a simple, yet effective way to understand the performance of your acquisition efforts and marketing retention. We at Locus IT provide Tableau Cohort Analytics training, Tableau Cohort Analytics support and Tableau Cohort Analytics implementation services. For more information please contact us.