Interest in spousal gifts: a data science project

Trying to think about whether husbands or wives are in general more romantic is difficult, simply because there are many different aspects of romance. So I have chosen to take “buying gifts” as a proxy for romance and, in particular, to look at worldwide Google searches for “gift for wife” and “gift for husband” in the last 12 months (June 2016 – June 2017).

A cursory examination of the Google Trends visualisation indicates that there is generally more interest in looking for a gift for one’s husband than looking for a gift for one’s wife, although there are specific points in the year when this is not true. Furthermore, the significant spikes in interest in spousal gifts in December and February – this is expected, as it coincides with Christmas and Valentine’s Day.

I analysed the CSV dataset, using R, and found that there were indeed 44 weeks in the last 12 months when interest in “gift for husband” is higher than “gift for wife”. From this one might make an initial conclusion that wives are thinking more about about buying gifts for their husbands than vice versa – and thus are more romantic.

What is interesting are the eight weeks where interest in “gift for wife” is higher than or equal to “gift for husband”:

  • Week commencing 18 December 2016
  • Week commencing 11 December 2016
  • Week commencing 4 December 2016
  • Week commencing 27 November 2016
  • Week commencing 16 October 2016
  • Week commencing 7 May 2017
  • Week commencing 30 April 2017
  • Week commencing 18 September 2016

The first four dates could probably be put down the Christmas season. But it is not clear from this particular dataset, why there should greater interest in “gift for wife” compared to “gift for husband” on any of those dates.

Another intriguing trend is that that the two dominant regions for these searches is India and the US, with more searches coming from India.

R code

#This dataset records the number of worldwide google searches for “gifts for husbands”
#and “gifts for wife” each week of the year
GiftsHusbandWife <- read.csv(“E:/Projects/Data Science/GiftsHusbandWife.csv”)

#There are 52 rows, one for each week of the year

#For 44 weeks of the year, the interest in “gifts for husband” is higher
#than interest in “gifts for wife”
table(GiftsHusbandWife$ForHusband > GiftsHusbandWife$ForWife)

#This is a subseat of only the eight weeks in the year where the interest in
#”gifts for wife” is greater than interest in “gifts for husband”
GiftsWife <- subset(GiftsHusbandWife, (GiftsHusbandWife$ForHusband > GiftsHusbandWife$ForWife) == “FALSE”)



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s