Prices Up, Customers Down

Recall our paid search scenario from yesterday.Spend = $100,000.Clicks = 200,000.Cost per Click = $0.50.Conversion Rate = 1.8%.Orders = 3,600.Average Order Value = $100.Profit Factor = 30%.Profit = (3,600*100)*0.30 – $100,000 = $8,000.Profit per Order = (8,000 / 3,600) = $2.22.The following year your merchandising team increases prices via introducing new items at higher price points.

Read Full Story

Rakuten Marketing Data Breaks down Consumer Habits During the First Holiday Shopping Events of the Season

Larger Purchases Made on Single’s Day and a Higher Frequency of Orders During Click Frenzy
Rakuten Marketing have released findings from data collected on Single’s Day and Click Frenzy which for the first time ever, fell over three consecutive days (Nov 11 – 13).

Read Full Story

Using scikit-learn Pipelines and FeatureUnions

Since I posted a postmortem of my entry to Kaggle’s See Click Fix competition, I’ve meant to keep sharing things that I learn as I improve my machine learning skills. One that I’ve been meaning to share is scikit-learn’s pipeline module. The following is a moderately detailed explanation and a few examples of how I use pipelining when I work on competitions.

Read Full Story