TFD-IIS-CRMCB: Telecom Fraud Detection for Incomplete Information Systems Based on Correlated Relation and Maximal Consistent Block

. 2023 Jan 5;25(1):112. doi: 10.3390/e25010112

Algorithm 2:MCIR-RGAD algorithm

Input: Information system $(U, C ⋃ D)$ , an attribute reduction set $B$ , threshold $ϵ > 0$ .

Output: A decision tree T

1:
compute $B$ $▹ U s i n g A l g o r i t h m$
2:
compute $M C B (B) = {B_{1}, \dots, B_{k}}$ , $M C B (D) = {D_{1}, \dots, D_{m}}$ . $▹ U s i n g D e f i n i t i o n$
3:
if $(U, C ⋃ D)$ is incomplete then
4:
$g \Leftarrow 1$ , $R G (D, B) \Leftarrow R_{r} (D, B)$ (Equation (14))
5:
else
6:
$0 < g < 1$ , $R G (D, B) \Leftarrow g \cdot R_{r} (D, B) + (1 - g) \cdot \frac{1}{G_{r} (D, B)}$ (Equation (14))
7:
end if $▹ R e c u r s i o n P o i n t$
8:
for $a_{j} \in B$ do
9:
$a_{j} \Leftarrow \underset{a_{j} \in B}{arg} min R G (D, a_{j})$
10:
$B \Leftarrow B - a_{j}$
11:
if $R G (D, a_{j}) > ϵ$ then
12:
$L a b e l_{T} \Leftarrow \underset{f (U, D_{i})}{arg} max ∣ D_{i} ∣$
13:
else
14:
$M C B (a_{j}) \Leftarrow {X_{1}, \dots, X_{s}}$
15:
for $X_{i} \in M C B (a_{j})$ do
16:
$(U, C ⋃ D) \Leftarrow (X_{i}, B ⋃ D)$
17:
if $∣ M C B (D) ∣ = 1$ then
18:
$L a b e l_{T} \Leftarrow f (U, D)$ $B = ϕ$
19:
$L a b e l_{T} \Leftarrow \underset{f (U, D_{i})}{arg} max ∣ D_{i} ∣$
20:
else
21:
return Step 8
22:
end if
23:
end for
24:
end if
25:
end for
26:
return T