Abstract: A system, method and computer program product for processing event records. The present invention includes a detection layer, an analysis layer, an expert systems layer and a presentation layer. The layered system includes a core infrastructure and a configurable, domain-specific implementation. The detection layer employs one or more detection engines, such as, for example, a rules-based thresholding engine and a profiling engine. The detection layer can include an AI-based pattern recognition engine for analyzing data records, for detecting new and interesting patterns and for updating the detection engines to insure that the detection engines can detect the new patterns. In one embodiment, the present invention is implemented as a telecommunications fraud detection system. When fraud is detected, the detection layer generates alarms which are sent to the analysis layer. The analysis layer filters and consolidates the alarms to generate fraud cases.

Abstract: A system, method and computer program product for processing event records. The present invention includes a detection layer, an analysis layer, an expert systems layer and a presentation layer. The layered system includes a core infrastructure and a configurable, domain-specific implementation. The detection layer employs one or more detection engines, such as, for example, a rules-based thresholding engine and a profiling engine. The detection layer can include an AI-based pattern recognition engine for analyzing data records, for detecting new and interesting patterns and for updating the detection engines to insure that the detection engines can detect the new patterns. In one embodiment, the present invention is implemented as a telecommunications fraud detection system. When fraud is detected, the detection layer generates alarms which are sent to the analysis layer. The analysis layer filters and consolidates the alarms to generate fraud cases.

Abstract: A system, method and computer program product for processing event records. The present invention includes a detection layer, an analysis layer, an expert systems layer and a presentation layer. The layered system includes a core infrastructure and a configurable, domain-specific implementation. The detection layer employs one or more detection engines, such as, for example, a rules-based thresholding engine and a profiling engine. The detection layer can include an AI-based pattern recognition engine for analyzing data records, for detecting new and interesting patterns and for updating the detection engines to insure that the detection engines can detect the new patterns. In one embodiment, the present invention is implemented as a telecommunications fraud detection system. When fraud is detected, the detection layer generates alarms which are sent to the analysis layer. The analysis layer filters and consolidates the alarms to generate fraud cases.

Abstract: An approach provides detection of unauthorized use of data services. A fraud case is created for a data call that is determined to be potentially fraudulent based on a fraud alert. A fraud score is determined for the case according to the fraud alert. The fraud score is adjusted according to adjustment criteria including an intermediate network involved with the data call, and an originating country of the data call.

Abstract: An approach provides detection of unauthorized use of data services. A determination is made as to whether connections supporting remote access to a data network are completed. The number of completed connections associated with a selected attribute is tracked over a time period. It is then determined whether the number of completed connections satisfies a connection frequency threshold. A fraud alert is generated if the connection frequency threshold is satisfied.

Abstract: An approach provides detection of unauthorized use of data services. The number of data calls for access to a data network is tracked over a predetermined time period, and the cumulative duration of the data calls is determined. Thereafter, a determination is made as to whether the number of the data calls and the cumulative duration satisfy, respectively, a first threshold and a second threshold. A potential fraudulent use of the account is determined, if the thresholds are satisfied.

Abstract: An approach provides fraud detection in support of data communication services. A threshold corresponding to a geographic location is set. The threshold corresponds to duration of a call supporting data communications. It is determined whether the call duration exceeds the threshold. A fraud alert is generated if the monitored call duration exceeds the threshold.

Abstract: An approach provides fraud detection in support of data communication services. A list of single-event attributes (e.g., hot or cold attributes) is generated and includes a network address of an end user host originating a data call or a calling party identification (e.g., Automatic Number Identification (ANI) or an originating Calling Line Identification (CLI)) for network access, wherein entries of the list specify values of the hot attributes. An attribute value associated with the data call is compared with the entries. A fraud alert is generated if the attribute value matches one of the entries.

Abstract: A system, method and computer program product for processing event records. The present invention includes a detection layer, an analysis layer, an expert systems layer and a presentation layer. The layered system includes a core infrastructure and a configurable, domain-specific implementation. The detection layer employs one or more detection engines, such as a rules-based thresholding engine and a profiling engine. The detection layer can include an Artificial Intelligence based pattern recognition engine for analyzing data records, for detecting new and interesting patterns and for updating the detection engines to insure that the detection engines can detect the new patterns. In one embodiment, the present invention is implemented as a telecommunications fraud detection system. When fraud is detected, the detection layer generates alarms which are sent to the analysis layer. The analysis layer filters and consolidates the alarms to generate fraud cases.

Abstract: A system, method and computer program product for processing event records. The present invention includes a detection layer, an analysis layer, an expert systems layer and a presentation layer. The layered system includes a core infrastructure and a configurable, domain-specific implementation. The detection layer employs one or more detection engines, such as, for example, a rules-based thresholding engine and a profiling engine. The detection layer can include an AI-based pattern recognition engine for analyzing data records, for detecting new and interesting patterns and for updating the detection engines to insure that the detection engines can detect the new patterns. In one embodiment, the present invention is implemented as a telecommunications fraud detection system. When fraud is detected, the detection layer generates alarms which are sent to the analysis layer. The analysis layer filters and consolidates the alarms to generate fraud cases.

Abstract: A system, method and computer program product for processing event records. The present invention includes a detection layer, an analysis layer, an expert systems layer and a presentation layer. The layered system includes a core infrastructure and a configurable, domain-specific implementation. The detection layer employs one or more detection engines, such as, for example, a rules-based thresholding engine and a profiling engine. The detection layer can include an AI-based pattern recognition engine for analyzing data records, for detecting new and interesting patterns and for updating the detection engines to insure that the detection engines can detect the new patterns. In one embodiment, the present invention is implemented as a telecommunications fraud detection system. When fraud is detected, the detection layer generates alarms which are sent to the analysis layer. The analysis layer filters and consolidates the alarms to generate fraud cases.

Abstract: A configurable and scalable rules-based thresholding system, method and computer program product for processing event records includes a core infrastructure and a configurable domain-specific implementation. The core infrastructure is generically employed regardless of the actual type of network being monitored. The domain-specific implementation is provided with user specific data and rules. The core infrastructure includes an event record enhancer which enhances events with additional data and a threshold detector which determines whether an enhanced event record, alone or in light of prior event records, exceeds one or more thresholds. The enhancer can access external databases for additional information related to an event record. In one embodiment, the enhancer generates feature vectors to represent enhanced event records. The threshold detector receives enhanced event records from the event record enhancer.