Purchases post installing app

purchasepostinstall <- purchase_value %>% group_by(uuid) %>% 
                         summarise(number_of_items = n()) %>% left_join(purchase_value_customerwise, by = "uuid") %>% 
                         left_join(cycles3, by = "uuid") %>% 
                         select(uuid, number_of_items, total_value, cycle1) %>% 
                         filter(cycle1 == 1) 


purchasepostinstall <-  purchasepostinstall %>% arrange(number_of_items) 



purchasepostinstall <- purchasepostinstall %>% group_by(number_of_items) %>% 
                        summarise(purchase.value = sum(total_value))

purchasepostinstall$number_of_items <- as.factor(purchasepostinstall$number_of_items)


purchasepostinstall <- purchasepostinstall %>% mutate(items_number = recode(number_of_items, "1" = "One Item",
                                                                      "2" = "Two Items",
                                                                      "3" = "Three Items",
                                                                      "4" = "Four Items"))

ggplot(purchasepostinstall, aes(x = items_number, y = purchase.value, fill = items_number)) +
       geom_bar(stat="identity", position = "dodge") +
       geom_text(aes(label= purchase.value), vjust= -0.3, size=3.5, color="black") +
       theme_economist() + 
       scale_color_economist()+
       ggtitle("Purchase value for items purchased post installing app") +
       theme(plot.title = element_text(hjust = 0.5))

Purchases in 2nd, 3rd…weeks if retention is greater than one week

d <- cycles %>% mutate(week_no = strftime(creation_date, format = "%V") %>% unlist() %>% as.numeric()) # get week numbers

dif <- d %>% 
       group_by(uuid) %>% 
       mutate(week = week_no - lag(week_no)) %>% 
       filter(creation_date == max(creation_date)) %>% select(uuid, week) # get week difference

dif <- dif %>% filter(!is.na(week)) # remove missing values


purchase_after_oneweek <- left_join(dif, purchase_value, by = "uuid") %>% filter(!is.na(total) & week > 0)  # get purchases for retention greater than one week



purchase_after_oneweek <- purchase_after_oneweek %>% group_by(week) %>% 
                            summarise(purchase.value = sum(total))

purchase_after_oneweek$week <- as.factor(purchase_after_oneweek$week)


purchase_after_oneweek <- purchase_after_oneweek %>% mutate(Week = recode(week, "1" = "Week1",
                                                      "2" = "Week2",
                                                      "3" = "Week3",
                                                      "4" = "Week4"))

knitr::kable(purchase_after_oneweek)

ggplot(purchase_after_oneweek, aes(x = Week, y = purchase.value, fill = Week)) +
  geom_bar(stat="identity") +
  geom_text(aes(label= purchase.value), vjust=-0.3, size=3.5, color="black") +
  theme_economist() + 
  scale_color_economist()+
  ggtitle("Purchase value for customers retained for one week and more") +
  theme(plot.title = element_text(hjust = 0.5)) 

Is there a steady inflow of revenue for customers with high retention?

prop_revenue <- prop.table(purchase_after_oneweek$purchase.value) %>% as.data.frame()

prop_revenue$week <- c(1,2,3,4)

colnames(prop_revenue)[1] <- "Prop.revenue"

prop_revenue

##   Prop.revenue week
## 1   0.67171507    1
## 2   0.14985696    2
## 3   0.15318598    3
## 4   0.02524199    4

ggplot(prop_revenue, aes(x = week, y = Prop.revenue, label = week)) +
  geom_point() +
  geom_line() +
  geom_text(aes(label=week),hjust=0, vjust=0) +
  ggtitle("Proportion of revenue from retained customers week wise") +
  theme(plot.title = element_text(hjust = 0.5))

Purchasing customers

purchase_cust_events <- cust_events %>% filter(event %in% purchase1) %>% arrange(uuid, event_timestamp) %>% 
  group_by(uuid) %>%  mutate(Rank = order(as.POSIXct(event_timestamp, format = "%Y-%m-%d %H:%M:%S", tz = 'CET'))) %>% 
  select(-rank) 
  
purchase_cust_events <- purchase_cust_events %>% group_by(uuid) %>% 
                summarise(activity = max(Rank)) 


purchase_cust_events <- left_join(purchase_cust_events, cycles3, by = "uuid")



purchase_cust_events <- purchase_cust_events %>% select(uuid, activity, rentention_trend) %>% 
                   filter(rentention_trend == 1) 


knitr::kable(purchase_cust_events)

ggplot(purchase_cust_events, aes(x = activity)) +
  geom_histogram(bins = 10, color="black", fill="green", position="identity") + # purchase values customerwise
  theme_economist() + 
  scale_color_economist()+
  ggtitle("Activity of purchasing customers in one lifecylce") +
  theme(plot.title = element_text(hjust = 0.5))

Non-purchasing customers

nonpurchase_cust_events <- cust_events %>% filter(!event %in% purchase1) %>% arrange(uuid, event_timestamp) %>% 
  group_by(uuid) %>%  mutate(Rank = order(as.POSIXct(event_timestamp, format = "%Y-%m-%d %H:%M:%S", tz = 'CET'))) %>% 
  select(-rank)

nonpurchase_cust_events <- nonpurchase_cust_events %>% group_by(uuid) %>% 
  summarise(activity = max(Rank))


nonpurchase_cust_events <- left_join(nonpurchase_cust_events, cycles3, by = "uuid")


nonpurchase_cust_events <- nonpurchase_cust_events %>% select(uuid, activity, rentention_trend) %>% 
  filter(rentention_trend == 1) 

knitr::kable(nonpurchase_cust_events)