Fraud Detection

Highlights

Fraud Detection is designed to help organizations reducing costs connected to frauds. The APP focus his predictive capabilities on combination of different techniques, mixing in a single risk score business user experience with predictive modeling techniques and anomaly detection models.

Risk scores produced by the APP may relate to individual customers or other actors in the chain, such as branch offices, agents and liquidators in the case of insurance. The APP identifies fraud by analyzing real-time data that are produced every day through transactions and customer interactions with the company. The APP is able to handle big data as in the case of data from the “black boxes” installed in cars from insurance companies.

The APP does not only propose to a central user a risk score, but interacts with company core processes through alerts and reports or triggers that can activate and / or modify the behavior of business users involved in the process, such as bank counter operator or insurance liquidator. In this way advanced analytics benefit spread to all levels of users, even those without skills needed for using complex analytical tools.

Business Context

Alongside increased risk associated with lending, banks have witnessed growing fraudulent behavior. This behavior may be internal (by undisciplined staff) or external (by fraudulent customers). In the insurance market, the incidence of fraudulent events has grown, especially in certain geographical areas. Overt fraud is known to be low, but suspect cases and claims that are resolved, for example, by settlement between the counterparties, are significantly higher. Lack of control over such events can lead to, over time, and (sometimes sizeable) losses in any case this  means businesses do not have the right information needed to tackle different situations.  It is therefore crucial for fraud managers to have as much information as possible at their disposal to spot fraudulent and new abnormal behavior early on and to identify possible fraudulent networks of people among counterparties, dealers, and other parties involved in the business.

ì4C Application

The i4C advanced analytics application for Fraud Detection screens all claims procedures, loans applications and product purchase procedures allocating a risk score to each which enables the fraud manager to set up alert logics for receiving signals based on its control objectives. The application allows users to assess all procedures based on certain business rules that are specific to individual industries (insurance, consumer credit, lending products), i.e. not only the standard rules of the market, but also those contained within the company’s business practices. Through predictive analytics users can also define fraud prediction models based on past cases of overt fraud and, even more so, on cases deemed suspect, thereby capitalizing on the value of all available information. Finally, the Fraud Detection application offers SNA (social network analysis) in order to perform exploratory analyses of dealers and counterparties and enable those in charge of fraud to investigate and recognise abnormal or fraudulent networks.

Business Pain – Key Features

  • Manage Fraud detection as a core business process
  • Real-time checking and scoring
  • Alerts for claims investigators
  • Alert, e-mail, and report management based on deterministic rules
  • Mapping of actions (initiation of disputes, inspections..)
  • Overview and breakdown features for anomalies detected / risk level
  • Detect internal and external fraud
  • Deterministic rules to identify fraudulent behavior, false claims and risky subjects (customers, employees, companies, 3rd parties)
  • Predictive Fraud Detection algorithms to improve accuracy in each risk scoring activity
  • Specific rules based on process, branch  and claim type
  • Risk score based on Risk Matrix: best of predictive, best of industry knowledge
  • Fraud analysts can start off on the existing business rules library for insurance (250+) and add new or fine tune during time
  • Use all available information to fight fraud
  • Mapping business processes, corporate procedures and all relevant policy and claims entities
  • Processing of information from central risk database across companies of the group (e.g.: traditional, on line etc)
  • Detect abnormal behavior not known a priori
  • Anomaly detection for potentially fraudulent patterns
  • Predictive models for customers or transaction risk score
  • Profiling of the types of actions and relationships between subjects via Social Network Analysis
  • Analysis of relationships between counterparties to identify fraudulent networks and collusions