Abstract: Systems, methods and products for quantitative translation of design requirements into a machine learning framework for training a classification model. A plurality of auxiliary tasks associated with a plurality of auxiliary task models are specified. The plurality of auxiliary task models are concurrently trained on the auxiliary tasks to generate one or more latent features learned by the plurality of auxiliary task models. The one or more latent features may be transferred from the plurality of auxiliary task models to augment a latent feature space of a target task for the classification model. Contribution levels of the transferred one or more latent features are adjusted based on design requirements for the target task for the classification model. First and second contribution levels are specified for respective first and second sets of auxiliary task latent features being quantified and enforced.

Abstract: Computer-implemented method and systems to improve training and performance of artificial intelligence (AI) systems having one or more machine learning models stored in one or more data storage mediums connected in at least one computing network is provided. The method comprises receiving student machine scores, generated by a student machine learning model stored in a data storage medium, the student machine learning model having a primary loss function; receiving teacher scores provided by one or more analytic resources, the teacher scores being provided based on known results and behavior of pre-existing machine learning models used for accomplishing a first series of classification objectives; transforming the teacher scores into transformed teacher scores.

Abstract: Systems, methods, and products for detection of selective omissions in an open data sharing computing platform comprises monitoring a plurality of events associated with a first digital record stored in a database of digital records, the first digital record uniquely identifying a first entity; associating a first detected event with a first set of words at least partially descriptive of the first detected event; associating a second detected event with a second set of words at least partially descriptive of the second detected event, the first event and the second event being detected, in response to digital records associated with the first event and the second event being shared over an open data sharing computing platform with express authorization provided by the first entity.

Abstract: Computer-implemented systems and methods for selecting a first neural network model from a set of neural network models for a first dataset, the first neural network model having a set of predictor variables and a second dataset comprising a plurality of datapoints mapped into a multi-dimensional grid that defines one or more neighborhood data regions; applying the first neural network model on the first dataset to generate a model score for one or more datapoints in the second dataset, the model score representing an optimal fit of input predictor variables to a target variable for the set of variables of the first neural network model.

Abstract: Computer-implemented systems and methods for selecting a first neural network model from a set of neural network models for a first dataset, the first neural network model having a set of predictor variables and a second dataset comprising a plurality of datapoints mapped into a multi-dimensional grid that defines one or more neighborhood data regions; applying the first neural network model on the first dataset to generate a model score for one or more datapoints in the second dataset, the model score representing an optimal fit of input predictor variables to a target variable for the set of variables of the first neural network model.

Abstract: A method for detecting fraud and non-fraud pattern changes can be based on transaction pathway transversal analysis. A decision tree can be built based on a training dataset from a reference dataset. Pathway transversal information can be recorded along each pathway for the reference dataset. A first mean and a first variance of a class probability can be calculated of all samples over each pathway. A pathway distribution for a new transaction dataset under investigation and a second mean and a second variance of all samples of the new transaction dataset can be obtained. The second mean and the second variance can represent a fraud probability. The deviation metrics between one or more feature statistics of a feature along each pathway for the reference dataset and the new dataset can be determined on a local level. Feature contributors to pattern changes can be determined by analyzing the deviation metrics.

Abstract: A computer-based fraud detection system stores extracts of the payment and other activity of the payer as well as the payee by efficiently profiling their accounts, and also stores extracts of the overall global or segmented payment activities. This profile information is then used to effectively capture fraudulent activity. The fraud detection system accepts messages from the payment processing system or from the associated financial institution, and depending on the nature of the message will update its databases, or assess fraud risk by computing a score, or both. If a score is computed, the higher the score, the greater the likelihood that the transaction is fraudulent. Said score is based on automatically determined risky values of variables and is also be automatically scaled using self-calibrating analytics using the captured profile information.

Abstract: A system and method for learning and associating reliability and confidence corresponding to a model's predictions by examining the support associated with datapoints in the variable phase space in terms of data coverage, and their impact on the weights distribution. The approach disclosed herein examines the impact of minor perturbations on a small fraction of the training exemplars in the variable phase space on the weights to understand whether the weights remain unperturbed or change significantly.

Abstract: A system and method for learning and associating reliability and confidence corresponding to a model's predictions by examining the support associated with datapoints in the variable phase space in terms of data coverage, and their impact on the weights distribution. The approach disclosed herein examines the impact of minor perturbations on a small fraction of the training exemplars in the variable phase space on the weights to understand whether the weights remain unperturbed or change significantly.

Abstract: A system and method for detecting compromise of financial transaction instruments associated with a merchant or automated teller machine (ATM) are disclosed. Historical data representing a historical aggregate financial transaction instrument behavior history is stored in a computer memory. The historical data is received at the computer from one or more merchants and ATMs via a communications network. Authorization data representing authorization behavior of a plurality of financial transaction cards related to corresponding financial transactions at the same or a different one or more merchants and ATMs is received by the computer. Abnormal activity data representing an abnormal aggregate financial transaction instrument activity based on the authorization data is determined, and the historical data is compared with the abnormal activity data to generate a compromise profile for the plurality of financial transaction instruments.

Abstract: The subject matter disclosed herein provides methods for detecting fraud and non-fraud pattern changes based on transaction pathway transversal analysis. A decision tree can be built based on a training dataset from a reference dataset. Pathway transversal information can be recorded along each pathway for the reference dataset. A first mean and a first variance of a class probability can be calculated of all samples over each pathway. A pathway distribution for a new transaction dataset under investigation and a second mean and a second variance of all samples of the new transaction dataset can be obtained. The second mean and the second variance can represent a fraud probability. A first pathway density distribution can be retrieved for the reference dataset. A second pathway density distribution can be generated for the new transaction dataset.

Abstract: A system and method of detecting command and control behavior of malware on a client computer is disclosed. One or more DNS messages are monitored from one or more client computers to a DNS server to determine a risk that one or more client computers is communicating with a botnet. Real-time entity profiles are generated for at least one of each of the one or more client computers, DNS domain query names, resolved IP addresses of query domain names, client computer-query domain name pairs, pairs of query domain name and corresponding resolved IP address, or query domain name-IP address cliques based on each of the one or more DNS messages. Using the real-time entity profiles, a risk that any of the one or more client computers is infected by malware that utilizes DNS messages for command and control or illegitimate data transmission purposes is determined. One or more scores are generated representing probabilities that one or more client computers is infected by malware.

Abstract: A system and method of detecting command and control behavior of malware on a client computer is disclosed. One or more DNS messages are monitored from one or more client computers to a DNS server to determine a risk that one or more client computers is communicating with a botnet. Real-time entity profiles are generated for at least one of each of the one or more client computers, DNS domain query names, resolved IP addresses of query domain names, client computer-query domain name pairs, pairs of query domain name and corresponding resolved IP address, or query domain name-IP address cliques based on each of the one or more DNS messages. Using the real-time entity profiles, a risk that any of the one or more client computers is infected by malware that utilizes DNS messages for command and control or illegitimate data transmission purposes is determined. One or more scores are generated representing probabilities that one or more client computers is infected by malware.

Abstract: A computer-implemented method and system for automated entity identification for efficient profiling in an event probability prediction system. A first subset of entities belonging to one or more entity classes is defined. At least one historical profile is constructed for each entity in the subset of entities based on a set of possible outcomes of transaction behavior of each entity in the first subset of entities. Based on the historical profiles, a second subset of entities having transaction behavior associated with a transaction is selected, the transaction behavior being predictive of at least one targeted outcome from the set of possible outcomes. The first subset of entities is redefined with the second subset of entities.

Abstract: A computer-implemented method and system for automated entity identification for efficient profiling in an event probability prediction system. A first subset of entities belonging to one or more entity classes is defined. At least one historical profile is constructed for each entity in the subset of entities based on a set of possible outcomes of transaction behavior of each entity in the first subset of entities. Based on the historical profiles, a second subset of entities having transaction behavior associated with a transaction is selected, the transaction behavior being predictive of at least one targeted outcome from the set of possible outcomes. The first subset of entities is redefined with the second subset of entities.

Abstract: A computer-implemented method and system for automated entity identification for efficient profiling in an event probability prediction system. A first subset of entities belonging to one or more entity classes is defined. At least one historical profile is constructed for each entity in the subset of entities based on a set of possible outcomes of transaction behavior of each entity in the first subset of entities. Based on the historical profiles, a second subset of entities having transaction behavior associated with a transaction is selected, the transaction behavior being predictive of at least one targeted outcome from the set of possible outcomes. The first subset of entities is redefined with the second subset of entities.

Abstract: A computer-implemented method and system for automated entity identification for efficient profiling in an event probability prediction system. A first subset of entities belonging to one or more entity classes is defined. At least one historical profile is constructed for each entity in the subset of entities based on a set of possible outcomes of transaction behavior of each entity in the first subset of entities. Based on the historical profiles, a second subset of entities having transaction behavior associated with a transaction is selected, the transaction behavior being predictive of at least one targeted outcome from the set of possible outcomes. The first subset of entities is redefined with the second subset of entities.

Abstract: A system and method for detecting compromise of financial transaction instruments associated with a merchant or automated teller machine (ATM) are disclosed. Historical data representing a historical aggregate financial transaction instrument behavior history is stored in a computer memory. The historical data is received at the computer from one or more merchants and ATMs via a communications network. Authorization data representing authorization behavior of a plurality of financial transaction cards related to corresponding financial transactions at the same or a different one or more merchants and ATMs is received by the computer. Abnormal activity data representing an abnormal aggregate financial transaction instrument activity based on the authorization data is determined, and the historical data is compared with the abnormal activity data to generate a compromise profile for the plurality of financial transaction instruments.

Abstract: A computer-implemented method for reconciling records from a plurality of data sets includes receiving a first data set from a left data source, retrieving data from the first data set, and placing the retrieved data from the first data set into a first abstract record from the left data source. The method also includes receiving a second data set from a right data source, retrieving data from the second data set, and placing the retrieved data from the second data set into a second abstract record from the right data source. The computer-implemented method also includes comparing the first abstract record and the second abstract record.

Abstract: Entity disambiguation resolves which names, words, or phrases in text correspond to distinct persons, organizations, locations, or other entities in the context of an entire corpus. The invention is based largely on language-independent algorithms. Thus, it is applicable not only to unstructured text from arbitrary human languages, but also to semi-structured data, such as citation databases and the disambiguation of named entities mentioned in wire transfer transaction records for the purpose of detecting money-laundering activity. The system uses multiple types of context as evidence for determining whether two mentions correspond to the same entity and it automatically learns the weight of evidence of each context item via corpus statistics. The invention uses multiple search keys to efficiently find pairs of mentions that correspond to the same entity, while skipping billions of unnecessary comparisons, yielding a system with very high throughput that can be applied to truly massive data.