Solutions to “Just KNIME It!” Challenge 24 - Season 3

:sun_with_face: Happy Wednesday, folks! We just posted a new Just KNIME It! challenge. :boom:

:handshake: Cohort analysis is widely used by businesses when they want to track customer retention (a proxy for loyalty) over time. :pushpin: Don’t miss out on this challenge if you want to hone your business analytics skills over some real-world purchase data!

Here is the challenge. Let’s use this thread to post our solutions to it, which should be uploaded to your public KNIME Hub spaces with tag JKISeason3-24 .

:sos: Need help with tags? To add tag JKISeason3-24 to your workflow, go to the description panel in KNIME Analytics Platform, click the pencil to edit it, and you will see the option for adding tags right there. :blush: Let us know if you have any problems!

2 Likes

Hi, this is my solution.

3 Likes

Here’s my solution:

Component contains two charts:

  1. Overall Monthly Development vs. Marketing spent. It allows to select between different KPIs for the line (customer numbers, retention rate) and spent categories for the bars (Total, SEA…): Overall there seems to be a correlation between increasing SEA spent and improving overall rentetion:

  2. Line chart showing re-purchases in future months for Cohorts (i.e. if 10 customers made their first purchase in Jan, the 2016-01-01 Cohort line show how many of these purchased again in future month). Overall the first cohort seems to be doing best and any further cohort drops of just a bit more it seems:

Link to solution:

2 Likes

Heatmaps for cohort retention rate & spend.
Would be nice to be able to control the coloring in this node.
Plot shows behavior of individual customers in a cohort.

4 Likes

Hi all,
Here is my solution.

I calculated the CRR for each year (2016) and each month.
Additionally, I created a heatmap to visualize the retention rates of different cohorts over time.

4 Likes

Here’s my solution. Both the month sets for CCR and Cohorts are hard coded but can be easily changed. Report includes:
Annual CCR
Cohorts (Apr-Jul)
Monthly Revenue
Monthly Revenue per Client
Clients per Month
Monthly Multiple Purchases (Normalized for Client Count)

3 Likes

Hi all,
This is my solution. Combination of Generic ECharts view and K-AI is really usefull, as it does’t require me to code myself.


3 Likes

My solution to the challenge:

It was really interesting to read about cohort analysis as I didn’t know about this topic before. Great to know one additional puzzle piece we can do with KNIME :slight_smile:

2 Likes

Hi all,
Here is my soution.

The workflow was relatively complex, but was very easy to visualise thanks to the Generic ECharts View node with K-AI :+1:

2 Likes

Trying my bit… new topic to learn and understand and learning .
Not viz though.

2 Likes

:sun_with_face: Happy Tuesday, folks! We just posted our solution to last week’s Just KNIME It! challenge, as usual.

:brain: When I was working on this challenge, I learned a bunch of new concepts! Glad to see that some of you also experienced this. :slight_smile:

:us: See you tomorrow for a challenge on the US elections – which are quickly approaching!

1 Like

Hello, I had to do a corrected version as my first solution actually was no cohort analysis.

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.