Research of customer behavior anomalies in big financial data

Abstract

The amount of data in financial institutions is growing rapidly and the subject of "big data" has become an urgent trend. The "big data" phenomenon brings challenge to empower analytical methods for enhanced scope. At the same time the big data composed from various sources opens new possibilities to capitalize data research. The article investigates the anomalies in big data used by financial institutions. It proposes the model designed for exploring dynamics and detecting anomalous behavior of bank customers. The experimental screening on bank customers' big data shows significant time and necessary calculation steps reduction for detecting suspicious operations.

Value creation with big data analytics for enterprises: a survey

“…BDA provides beneficial information allowing managers to make considerably effective decisions according to the conditions of the market [8]. Nowadays, BDA has been used in diverse areas of business such as customer analysis [9][10][11][12][13], product and service invention [14][15][16][17], market prediction [18][19][20], supply chain and performance management [21][22][23][24], risk management, and fraud detection [14,15].…”

Graph Structure Based Anomaly Behavior Detection

“…Existing anomaly behavior detection include content based method [1], behavior feature based method [2] and graph based method [3].Content based suspicious detection technology generally based on the user's personal information and the content of the message they published. Malicious users may publish spam ads, malicious links or illegal content but normal user won't.…”

“…However there are lots of risk behind the convenience of social medium-fake review, fake followers, phishing website, telecommunications fraud. The complex behavior of user makes it had to predict people's behavior and anomaly detection.Existing anomaly behavior detection include content based method [1], behavior feature based method [2] and graph based method [3].Content based suspicious detection technology generally based on the user's personal information and the content of the message they published. Malicious users may publish spam ads, malicious links or illegal content but normal user won't.…”