COD_Ecom

Om Joy Halder
25-11-2017

What is the average price paid with/without COD?

ecom<- read.csv(paste("PromotionDataV4.csv", sep= " "))
Has_COD = subset(ecom, ecom$COD == 1 )
Not_COD = subset(ecom, ecom$COD == 0)
# Average price paid with COD
mean(Has_COD$FinalTotalPrice)

[1] 774.6938

# Average price paid without COD
mean(Not_COD$FinalTotalPrice)

[1] 723.248

Does payment method has an impact on total price?


Call:
lm(formula = ecom$FinalTotalPrice ~ ecom$COD, data = ecom)

Residuals:
   Min     1Q Median     3Q    Max 
-774.7 -208.7  -94.3  143.0 6203.3 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  723.248      2.572  281.19   <2e-16 ***
ecom$COD      51.446      3.285   15.66   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 342.7 on 45896 degrees of freedom
Multiple R-squared:  0.005317,  Adjusted R-squared:  0.005295 
F-statistic: 245.3 on 1 and 45896 DF,  p-value: < 2.2e-16

Here, we see there is a significant relation between payment method and total price as the p value is less than 0.05. As stated in the data description payment through COD comes with an extra charge, this regression corroborates that that mode of payment influence the final price.

Do consumers prefer COD? (analysing impact of COD on Demand in units sold and revenue generated)

# Units sold
nrow(Has_COD)

[1] 28144

nrow(Not_COD)

[1] 17754

#  Total Revenue
mytable <- aggregate(ecom$FinalTotalPrice ~ ecom$COD, FUN = sum)
mytable

  ecom$COD ecom$FinalTotalPrice
1        0             12840545
2        1             21802982

```

Here, we see that more number of units have been sold through COD than through elctronic payment. Consequently, more revenue has been accrued through cash payment. So, we can presume that COD is more popular method of payment.