A spam call prevention apparatus 11 includes: a response unit 111 configured to convey, to a phone terminal of a sender of a call, a response that, in a case where the call from the sender is evaluated as a spam or a fraud by a receiver of the call, the sender is billed a sum of money corresponding to a probability of being evaluated as the spam or the fraud; a notification unit 112 configured to notify, when the sender has requested, in responding to the response, the call to the receiver, a phone terminal of the receiver of a request for returning an evaluation result of evaluating the call from the sender after the call between the sender and the receiver has ended; and a determination unit 114 configured to determine, when the call from the sender has been evaluated as the spam or the fraud in the evaluation result, the sum of money corresponding to the probability of being evaluated as the spam or the fraud, as a sum of billing.

Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

Embodiments are described for a pattern-based control system that learns and applies device usage patterns for identifying and disabling devices exhibiting abnormal usage patterns. The system can learn a user's normal usage pattern or can learn abnormal usage patterns, such as a typical usage pattern for a stolen device. This learning can include human or algorithmic identification of particular sets of usage conditions (e.g., locations, changes in settings, personal data access events, application events, IMU data, etc.) or training a machine learning model to identify usage condition combinations or sequences. Constraints (e.g., particular times or locations) can specify circumstances where abnormal pattern matching is enabled or disabled. Upon identifying an abnormal usage pattern, the system can disable the device, e.g., by permanently destroying a physical component, semi-permanently disabling a component, or through a software lock or data encryption.

Methods and systems are presented for generating a machine learning model using enhanced gradient boosting techniques. The machine learning model is configured to receive inputs corresponding to a set of features and to produce an output based on the inputs. The machine learning model includes multiple layers, wherein each layer includes multiple models. To generate the machine learning model, multiple models are built and trained in parallel for each layer of the machine learning model. The multiple models use different subsets of features to produce corresponding output values. After a layer in built and trained, a collective error may be determined for the layer based on the output values from the different models in the layer. An additional layer of models may be added to the machine learning model to reduce the collective error of a previous layer.

A method and system are described for enhancing the security of calls made by a member of a controlled environment to an outside party, particularly when the outside party communicates via a cellular phone. An application is provided for the cellular device, which must communicate and register with a calling platform of the controlled environment. Certain elements of personal verification data are obtained by the user of the cellular device and stored at the calling platform for later reference. Calls from the inmate to the cellular device cause the calling platform to issue a notification to the user via the application. The user verifies his/her identity using the application, after which the call can be connected. As a further security measure, certain conditions can be required and periodically checked during the call to ensure the user remains verified.

A method for identifying a fraudulent phone number is provided. The method includes receiving a user report dataset indicating fraudulent activity corresponding to a phone number, and responsive to receiving the user report dataset, identifying a record in a database corresponding to the phone number. The method further includes tagging the record to identify the phone number as being associated with fraudulent activity.

A method and system are described for enhancing the security of calls made by a member of a controlled environment to an outside party, particularly when the outside party communicates via a cellular phone. An application is provided for the cellular device, which must communicate and register with a calling platform of the controlled environment. Certain elements of personal verification data are obtained by the user of the cellular device and stored at the calling platform for later reference. Calls from the inmate to the cellular device cause the calling platform to issue a notification to the user via the application. The user verifies his/her identity using the application, after which the call can be connected. As a further security measure, certain conditions can be required and periodically checked during the call to ensure the user remains verified.

A method for predicting fraudulent call activity is provided. The method includes receiving one or more datasets indicating call activity corresponding to a phone number, and analyzing the one or more datasets to identify unusual call activity. The method further includes generating a fraud prediction, based at least in part on the identified unusual call activity, that the phone number will be used for fraud.

Systems and methods for managing a set of electronic assets from a single location are disclosed. The method includes providing a portal with a network security access control. The method includes determining that login credentials input to the access control are associated with a set of electronic assets corresponding to a plurality of third-party computing systems with application programming interface (API) gateways configured to accept API calls directed to changes in functionality of the electronic assets. The method includes presenting, via the portal, a virtual icon to identify a coordinated action with respect to the set of electronic assets and, in response to a selection of the virtual icon, executing a set of API calls that include an asset-specific API call to each third-party computing system in the plurality of third-party computing systems to implement the coordinated action on all electronic assets in the set of electronic assets.

In some embodiments, a method includes: generating, by a session controlling Internet platform, a personalized Universal Resource Locator link (PURL), including: where the PURL is: communicatively coupled to the permission controlling schema and configured to be utilized to establish a peer-to-peer communication session between a sender computing device and a recipient computing device; where the PURL includes: a domain name associated with the session controlling Internet platform hosting a permission controlling schema, and at least one first identity linked to the recipient computing device; transmitting, by the session controlling Internet platform, the PURL to the recipient computing device; receiving, by the session controlling Internet platform, after the transmitting the PURL to the recipient computing device, a mobile originating communication, having data including: a multi-part multi-functional address signaling sequence, including: a MICRO band part, corresponding to a MICRO band parameter and a MACRO band part.