Research Article
Facilitating User Authorization from Imbalanced Data Logs of Credit Cards Using Artificial Intelligence
Algorithm 1
CtRUSBoost (customized RUSBoost).
(i) | Input: , , (with ) | (ii) | Output: maximum of [(maximum of value), (maximum of value)] | | Begin | (1) | Initialization of for all | (2) | Do for | (a) | Create temporary training dataset with weight distribution by using random undersampling | (b) | Call decision tree, considering the sample set as and distribution of weight | (c) | Compute a hypothesis | (d) | Call support vector machine considering the sample set as and distribution of weight as | (e) | Compute a hypothesis | (f) | Compute the pseudo loss for SEG and | | | (g) | Compute the parameter to update the weighing factor: | | | (h) | Update | | | (i) | Normalize: Let | | | (3) | Find the values for and | (a) | For each value of , find out the maximum value of | (b) | For each value of , apply bagging either by performing voting or averaging among all the values of hypothesis obtained | (4) | Compute the final hypothesis as the maximum value between and | | End |
|