- The average age for users is 37. That seems surprisingly low.
- Users are more likely to create an account on a date near their birthday but not on their birthday.
- User profile captions are pretty funny.
The average age for an Ashley Madison user is 37. That’s surprising given Ashley Madison has been around since 2001. Also interesting is the high number of members aged 38 and 51. My guess is those are fake accounts. There are 34 million accounts and some analysis puts the number of legit accounts at ~800,000.
Also, in a hypothetical situation where I had the Ashley Madison data, I would probably do something like this…
- Spin up a cheap Amazon cluster and upload data to the new instance.
- Write a script to convert a MySQL table dump to a tsv file.
- Spin up a cheap Redshift cluster and import tsv files.
Point being the Ashley Madison data is delivered as large MySQL dump files and loading large MySQL dump files is a chore. You would be better off converting the MySQL dump files into a more flexible format like tab delimited files then using Redshift or Hadoop.