R 中的欺诈检测
Tim Verdonck
Professor Data Science at KU Leuven
$recency=exp(-\gamma\cdot t)=e^{-\gamma t}$
(2) 计算 $\gamma=-log(recency)/t$
示例：设定 $\gamma$ 使得 $t$ = 180 天后 recency = 0.01
gamma <- -log(0.01)/180 print(gamma)
0.02558428
recency_fun <- function(t, gamma, auth_cd, freq_auth) { n_t <- length(t) if (freq_auth[n_t] == 0) { recency <- 0 # recency = 0 when frequency = 0 } else { time_diff <- t[1] - max(t[2:n_t][auth_cd[(n_t-1):1] == auth_cd[n_t]]) # time-interval = current time - time of previous transfer with same auth_cd recency <- exp(-gamma * time_diff) } return(recency) }
recency_fun <- function(t, gamma, auth_cd, freq_auth) {
n_t <- length(t) if (freq_auth[n_t] == 0) { recency <- 0 # recency = 0 when frequency = 0
} else { time_diff <- t[1] - max(t[2:n_t][auth_cd[(n_t-1):1] == auth_cd[n_t]]) # time-interval = current time - time of previous transfer with same auth_cd
recency <- exp(-gamma * time_diff) } return(recency)
}
(1) 选择 $\gamma$ 值
gamma <- -log(0.01)/180 # = 0.0256
(2) 使用 rollapply()、group_by() 与 mutate()
rollapply()
group_by()
mutate()
library(dplyr) # needed for group_by() and mutate() library(zoo) # needed for rollapply() trans <- trans %>% group_by(account_name) %>% mutate(rec_auth = rollapply(timestamp, width = list(0:-length(transfer_id)), partial = TRUE, FUN = recency_fun, gamma, authentication_cd, freq_auth))
account_name timestamp authentication_cd rec_auth fraud_flag 1 Bob 44.25 AU02 0.000 0 2 Alice 54.12 AU03 0.000 0 3 Bob 57.45 AU04 0.000 0 4 Bob 64.29 AU02 0.599 0 5 Alice 64.29 AU03 0.771 0 6 Bob 64.29 AU02 1.000 0 7 Alice 70.25 AU03 0.859 0 8 Bob 70.25 AU02 0.859 0 9 Alice 74.08 AU01 0.000 0 ... ... ... ... ... ... 37 Bob 407.17 AU02 0.002 0 38 Alice 420.17 AU03 0.717 0 39 Bob 441.34 AU03 0.000 1 40 Alice 443.24 AU04 0.000 1
Preparing Video For Download...
