Two weeks ago we put out a pre­dic­tion regard­ing US online spend­ing for Valentine’s Day: “You CAN Put a Price on Love” to the tune of $500 million.

Mar­keters inter­ested in the power and use­ful­ness of pre­dic­tive ana­lyt­ics will be inter­ested in see­ing the actual results vs. our pre­dic­tion (below). The model ended up being very accu­rate. Online spend­ing was within about 7% of the day-to-day prediction.


For­mu­lat­ing the model that drove this pre­dic­tion revealed some inter­est­ing behav­ioral pat­terns around Valentine’s shopping.

  • Valentine’s shop­pers wait until the last minute even for online shopping.
    • Mar­keters should expect this and not sell off inven­tory too soon.
  • Shop­ping pat­terns are highly depen­dent on the day of week that Valentine’s falls
    • 2013 lagged behind 2012 in total shop­ping the week prior to Valentine’s, but made up for it the week of Valentine’s because Valentine’s fell on a Thurs­day rather than a Tuesday.
  • Shop­ping starts 3 weeks before Valentine’s and that early shop­ping sets the tone for YoY growth.
    • Mar­keters don’t need to wait until the week of Valentine’s to see if their pro­mo­tions are working.

Does this jive with what you saw last week? Let me know @tyrwhite.