Abstract: A method and system distinguish between anomalous members of a majority group and members of a target group. The system and method utilize a neural network architecture that attends to each level of a classification hierarchy. The system and method chain a semi-supervised autoencoder with a supervised classifier neural network. The autoencoder is trained in a semi-supervised manner with a machine learning process to identify user profile data that are typical of a majority class. The classifier neural network is trained in a supervised manner with a machine learning process to distinguish between user profile data that are anomalous members of the majority class and user profile data that are members of the target class.

Abstract: A method includes establishing a network connection with a source computing device and an application services computing device, receiving, via the network connection, a source event stream at the application services computing device, and extracting a sample of the source event stream. The method further includes partitioning the sample of the source event stream into fields, identifying a field data type of a field of the multiple fields in the sample, identifying a distribution of values of the field in the sample, and extrapolating, from the sample of the source event stream, extrapolated functions for the fields. Extrapolating an extrapolated function is dependent on the field data type and the distribution of the field. The method further includes transforming, based on the plurality of extrapolated functions in the configuration file, the source event stream to obtain a transformed event stream, and analyzing, by a target machine learning model, the transformed event stream.

Abstract: A method includes establishing a network connection with a source computing device and an application services computing device, receiving, via the network connection, a source event stream at the application services computing device, and extracting a sample of the source event stream. The method further includes partitioning the sample of the source event stream into fields, identifying a field data type of a field of the multiple fields in the sample, identifying a distribution of values of the field in the sample, and extrapolating, from the sample of the source event stream, extrapolated functions for the fields. Extrapolating an extrapolated function is dependent on the field data type and the distribution of the field. The method further includes transforming, based on the plurality of extrapolated functions in the configuration file, the source event stream to obtain a transformed event stream, and analyzing, by a target machine learning model, the transformed event stream.

Abstract: A method includes establishing a network connection with a source computing device and an application services computing device, receiving, via the network connection, a source event stream at the application services computing device, and extracting a sample of the source event stream. The method further includes partitioning the sample of the source event stream into fields, identifying a field data type of a field of the multiple fields in the sample, identifying a distribution of values of the field in the sample, and extrapolating, from the sample of the source event stream, extrapolated functions for the fields. Extrapolating an extrapolated function is dependent on the field data type and the distribution of the field. The method further includes transforming, based on the plurality of extrapolated functions in the configuration file, the source event stream to obtain a transformed event stream, and analyzing, by a target machine learning model, the transformed event stream.

Abstract: Methods and systems of the present disclosure include identifying and addressing potential healthcare-based fraud, according to one embodiment. The methods and systems identify potential healthcare-based fraud associated with potentially suspicious healthcare providers, patients, and/or claim submissions, in one embodiment. According to one embodiment, the methods and systems acquire data associated with a healthcare provider, patient, and/or claim submission; apply the data to one or more predictive models to generate one or more risk scores to identify potential healthcare-based fraud, and perform one or more risk reduction actions based on the one or more risk scores, according to one embodiment.

Abstract: Methods and systems of the present disclosure include identifying and addressing potential fictitious business entity-based fraud, according to one embodiment. The methods and systems identify fictitious business entities associated with fraudulent tax return filings, in one embodiment. According to one embodiment, the methods and systems acquire data associated with an employer identification number (EIN), apply the data to one or more predictive models to generate one or more risk scores to identify potentially suspicious EIN data, and perform one or more risk reduction actions based on the one or more risk scores, according to one embodiment.

Abstract: Account takeover is one of a number of types of Internet-centric crime (i.e., cybercrime) that includes the unauthorized access/use of a user's account with the user's identity or credentials (e.g., username and/or password). Because fraudsters acquire user credentials through phishing, spyware, or malware scams, it can be difficult to detect unauthorized access of a user's account. Methods and systems of the present disclosure identify and address potential account takeover activity, according to one embodiment. The methods and systems acquire system access data, apply the system access data to one or more predictive models to generate one or more risk scores, and perform one or more risk reduction actions based on the one or more risk scores, according to one embodiment. The financial system is a tax return preparation system according to one embodiment.

Abstract: Account takeover and stolen identity refund fraud are types of Internet-centric crime (i.e., cybercrime) that include the unauthorized access or use of a user account or identity information to file a tax return in order to obtain a tax refund and/or tax credit from, for example, a state or federal revenue service. Because fraudsters access legitimate user accounts or use legitimate identity information to create user accounts, it can be difficult to detect fraudulent activity in user accounts. Methods and systems of the present disclosure facilitate the identification and prevention of potential fraudulent activity in a financial system, according to one embodiment. The methods and systems automate fraud claim receipt, predictive model training, risk score threshold improvement/optimization, and/or investigation of potentially affected user accounts, according to one embodiment.

Abstract: A system for determining a canonical title includes an interface and a processor. The interface is to receive a new title. The processor is to generate a set of n-grams based on the new title; look up n-grams in canonical database to assign one or more labels; and map the new title to a canonical title based on the one or more labels.

Abstract: A system for determining a canonical title includes an interface and a processor. The interface is to receive a new title. The processor is to generate a set of n-grams based on the new title; look up n-grams in canonical database to assign one or more labels; and map the new title to a canonical title based on the one or more labels.

Abstract: A method for normalizing raw titles to canonical titles is described. The method includes designating a set of canonical titles, generating a set of n-grams for each canonical title, assigning a set of attributes to each n-gram, assigning a set of labels to each of the attributes, and storing the labeled canonical title and labeled n-grams in a database. In some examples, a new title may be mapped to an existing canonical title in the database by generating a set of n-grams for the new title, looking up the n-grams in the database of canonical titles, retrieving the set of labels assigned to n-grams in the database that match n-grams from the new title, and assigning those labels to the corresponding attributes of the new title. The new title may then be mapped to a canonical title on the basis of similarly labeled attributes.

Abstract: Systems and methods for the manipulation of particles within channels such as microfluidic channels are provided. In one set of embodiments, magnets are positioned around a channel. As a fluid containing magnetic and non-magnetic particles flows through the channel, the magnetic field created by the magnets can be used to transport the magnetic and/or non-magnetic particles to desired locations within the channel, which may useful in some cases for causing some separation of the particles. For example, the magnetic field may be used to transport magnetic or non-magnetic particles from a core fluid to a surrounding sheath fluid. In some cases, the magnetic field is used to transport non-magnetic particles to a small volume within the channel (e.g., a single-file row within the channel).

Abstract: Provided herein are systems and related methods comprising (i) short stretches (e.g., 9 to 24 bases) of single-stranded nucleic acid (e.g., DNA) capture probes coated with RecA and, in some instances, bound to a solid substrate, and (ii) double-stranded nucleic acid (e.g., DNA or RNA) target(s).

Abstract: Systems and methods for the manipulation of particles within channels such as microfluidic channels are provided. In one set of embodiments, magnets are positioned around a channel. As a fluid containing magnetic and non-magnetic particles flows through the channel, the magnetic field created by the magnets can be used to transport the magnetic and/or non-magnetic particles to desired locations within the channel, which may useful in some cases for causing some separation of the particles. For example, the magnetic field may be used to transport magnetic or non-magnetic particles from a core fluid to a surrounding sheath fluid. In some cases, the magnetic field is used to transport non-magnetic particles to a small volume within the channel (e.g., a single-file row within the channel).