|Metrics groups for evaluate the recommender systems|
TPR = (ORDERS_REC/ORDERS) * 100 % = (250/1400) * 100% = 17.9%
TIR = (NIRP/NIP) * 100% = (1.7/4.5) * 100% = 37.8%
ATM = (ATR - AT) / (AT) * 100% = (315-268/268) = 17,5%
- Technnique 2: Only Most popular Ranking
In the table 2 we can see that the average interaction is between 6.9% and 14.8% with the recommendations approaches implemented at the store. It means that, at least 6,9% of the recommended items presented were clicked. About the conversion metrics, we can observe that the recommendations are promoting new sales, which it wouldn't exist if there was no recommendations. The conversion rates are between 4,5 % to 13,5% at those stores. The best recommendation approach tested was the third one with 14,4% of increase at the profit. It is important to notice that this rate is calculated in average, so during the period analyzed there was some peaks in the increase of the profit, for instance sometimes 30% , and 4%.
PS: This article is based on the brazilian article at E-commerceBrazil Magazine June/2012 Edition. I recommend a lot if you are a brazilian to read it either.