Graph mining assisted semi-supervised learning for fraudulent cash-out detection

Fraudulent cash-out is an increasingly serious problem in China, which costs financial facilities billions of dollars. Unlike most of the well-studied credit card fraud, where only one party illicitly seeks financial gain, fraudulent cash-out involves both parties of the transaction. When prior information, such as credit score and reputation score, about the majority of consumers and shops is available, the phenomenon can be readily analyzed by using the Markov random field models. In this paper, we investigate the detection of fraudulent cash-out under the circumstance where no prior information but only the labels of a small set of consumers and shops are available. The novelty of this work is building a semi-supervised learning algorithm that automatically tunes the prior and parameters in Markov random field while inferring labels for every node in the graph. We evaluate our algorithm with data from JD Finance.