This data is randomly generated. It resembles raw data from a customer
satisfaction survey using CSAT (Customer Satisfaction Score) for a
contract-based product. The first three variables are given, all other
variables come from a survey tool and are only named "item1" etc.
A recoded version of this data set can be found here <csat>.
csatraw
A tibble with 150 rows and 15 variables:
Customer identification number
Type of customer: "new", "existing" or "reactive"
The type of product: "basic", "advanced" or "premium"
The overall Customer Satisfaction Score
Scale: Ranging from 1 =
"Very unsatisfied" to 5 = "Very satisfied"
Follow-up question why the respondent gave this specific Customer Satisfaction rating. The open-ended answers have been coded into six categories: 11 = "great product", 12 = "good service", 13 = "friendly staff", 21 = "too expensive", 22 = "unfriendly", 23 = "no response" (multiple answers possible).
When did the customer have last
contact via postal mail (item2a), phone (item3a), email (item4a), website
(item5a), a retail shop (item6a) ?
Scale: 0 = "no contact", 1 = "more
than 3 years ago", 2 = "within 1 to 3 years", 3 = "within the last year"
If customer had contact
via postal mail (item2b), phone (item3b), email (item4b), website (item5b),
a retail shop (item6b): How satisfied was he?
Scale: Ranging from 1 = "Very unsatisfied", to 5 = "Very satisfied"
csatraw#> # A tibble: 150 × 15 #> cust_id type product item1 item1_open item2a item2b item3a item3b item4a #> <chr> <chr> <chr> <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> #> 1 61297 existing advanc… 3 12 2 3 2 2 0 #> 2 07545 existing advanc… 2 22 2 2 3 4 2 #> 3 03822 existing premium 2 21, 22, 23 2 5 3 5 0 #> 4 88219 reactivate basic 4 12, 13, 11 3 5 2 3 0 #> 5 31831 new basic 4 12, 13, 11 3 2 3 5 3 #> 6 63646 new basic 3 21 0 NA 2 3 3 #> 7 63600 existing advanc… 1 23, 22, 21 3 3 3 4 3 #> 8 82048 reactivate advanc… 3 11, 23 2 3 3 2 2 #> 9 41142 reactivate advanc… 3 21, 23, 13 2 4 0 NA 2 #> 10 00803 new premium 2 21, 23 0 NA 1 2 2 #> # … with 140 more rows, and 5 more variables: item4b <dbl>, item5a <dbl>, #> # item5b <dbl>, item6a <dbl>, item6b <dbl>