Cohort analysis

28 sec read

Cohort analysis is a good metric on how users engage to an application. To do this, you:

  1. Break the users into cohorts according to when they register (bin size usually a month)
  2. Count the number of users in each cohort who login in over time
  3. Plot it

What you can get:

  1. the number of users currently using the program (read the height of period 5)
  2. retention rate over time
  3. growth rate

EverNote ECO Phil Libin used this analysis to attract investors.


How to make the cohort analysis plot?

It’s actually simple. Use Excel. Prepare a table where each row is one cohort over time, and each column is a time point. Then click “insert” and “Stacked Area”.

cohort plot using Excel
cohort plot using Excel


Want to receive new post notification? 有新文章通知我


该文章可以通过该链接完整阅读(包括图片。这些图片有时微信禁止转载)。 我们印象当中,发文章需要做大量的实验和分析。实验对象可以是原子、病毒,可以是疾病、人群,也可以是恒星、宇宙。可是,如果分析的对象是
Xu Cui
14 sec read

Google Chrome takes too much CPU

I have been noticing for a while that Chrome takes too much of my CPU. It constantly consumes about ~30% or even more CPU even if I have only a blank page opened. As a consequence, my CPU fan is always running, making some noise which can be annoying
Xu Cui
32 sec read

Functional Near Infrared Spectroscopy (fNIRS): List of manufactures

Contents Company Products Artinis Brite, OxyMon, OctaMon, PortaMon, PortaLite BIOPAC fNIR 100, fNIR2000M Series CORTIVISION PHOTONCAP Huichuang Medical NirScan-900X, NirSmartⅡ- Pro GOWERLABS NTS fNIRS system, LUMO HAMAMATSU NIRO-200NX HITACHI ETG-410
Xiaodan Feng
14 min read

One Reply to “Cohort analysis”

Leave a Reply

Your email address will not be published. Required fields are marked *