Abstract: A method for detecting an anomaly in human behavior is provided. The method includes: receiving information that relates to a behavior of a person; determining at least one behavior trace based on the received information; classifying each behavior trace into a respective category from among a first category that corresponds to behaviors that indicate an intention to commit a crime, such as money laundering, and a second category that corresponds to behaviors that indicate standard non-criminal activity; and analyzing each behavior trace to determine a potential intended goal of the person. The behavior trace includes a sequence of behavioral states and actions performed by the person in response to each respective behavioral state.

Abstract: A method for heuristics-based link prediction in multiplex networks may include a link prediction computer program: receiving a model for a multiplex network; defining a property matrix that specifies feature for cross-layer correlation; constructing a cross-correlation matrix from the property matrix; applying a count and weight correlation heuristic to the cross-correlation matrix, wherein the count and weight correlation heuristic counts a number of layers that contain a link between two nodes, and weights that count according to cross-layer correlations; applying a correlation weighted heuristic to the cross-correlation matrix; applying a count correlation-weighted heuristic to the cross-correlation matrix that counts the number of layers that contain a link between two nodes and weights that count according to both cross-layer correlations and values resulting from evaluating a monoplex heuristic applied to each layer in the multiplex network, resulting in output values; and identifying a missing link ba

Abstract: Systems and methods for applying game theory for fraud detection. Rather than inspecting every transaction record, embodiments are directed to limiting incoming suspicious transaction records according to a schedule. The schedule may define time windows for various clients and transactions. These time windows may filter down the stream of incoming transaction records to a subset. As a result, fraud may be detected by strategically allocating resources in an optimal way rather than attempting to inspect each and every instance of transaction.

Abstract: Systems and methods for digital document generation using natural language interaction are disclosed. In one embodiment, in an information processing apparatus comprising at least one computer processor, a method for digital document generation using natural language interaction may include: (1) receiving from an electronic device, a natural language command comprising an action to generate digital content, an object, and a data source for the digital content; (2) processing the natural language command to identify the action, the type of digital content, and the data source; (3) identifying a skill in a skill library that is mapped to the action and the object; (4) retrieving data from the data source for the skill; and (5) generating the digital content according to the skill using the data.

Abstract: Systems and methods for risk-sensitive reinforcement learning are disclosed. In one embodiment, a method for a method for training a risk-sensitive reinforcement learning policy may include: (1) receiving, from a data source, a plurality of sets of training data for a plurality of time steps; (2) receiving a training budget comprising a plurality of episodes, a risk aversion coefficient, and an end state; and (3) calculating a correction factor using the training data. The correction factor may minimize stochasticity based on a risk aversion coefficient.

Abstract: Systems and methods for privacy-preserving inventory matching are disclosed. In one embodiment, in an information processing apparatus comprising at least one computer processor, a method for inventory matching may include: (1) receiving, from each of a plurality of clients, a masked submission comprising an identification of at least one security to buy or sell and a desired quantity to buy or sell; (2) aggregating the masked submissions resulting in a sum of the desired quantities to buy or sell; (3) matching at least two of the clients to conduct a transaction based on aggregation and their respective masked submissions; and (4) conducing the transaction between the matched clients.

Abstract: Systems and methods for privacy-preserving summarization of digital activity are disclosed. According to one embodiment in an information processing apparatus comprising at least one computer processor and at least one display, a privacy-preserving digital activity computer program performing the following: (1) capturing a blurred or pixelated screenshot of the at least one display; (2) identifying a plurality of computer application visible in the blurred or pixelated screenshot; (3) identifying a foreground or actively-used application out of the plurality computer applications in the blurred or pixelated screenshot; and (4) logging the visible computer applications and the foreground or actively-used application.

Abstract: A method for using images that represent time-series data to forecast future images depicting future values as pixelated information is provided. The method includes: receiving a first set of time-series data; converting the received first set of time-series data into a first image; and using the first image to forecast a future image depicting future values as pixelated information that corresponds to a future time interval Training sets of time-series data are used to generate historical data that provides input to a machine learning algorithm, which provides, as an output, a composite image that depicts the future values as pixelated information that reflects associated uncertainties in the value predictions.

Abstract: A method, comprising displaying an image to a first player, displaying a portion of the image to a second player wherein the portion of the image displayed to the second player is less than all of the image and wherein the portion of the image displayed to the second player is determined by an action of the first player, allowing the second player to submit a word, and determining whether the word submitted by the second player is related to the image. The present invention also includes apparatuses and systems.

Abstract: A classifier for signal classification based on a plurality of classification signals can be generated in three phases: a training phase, an orchestration phase, and a final classifier phase. In the training phase, genetic programming techniques are used to evolve a population of classification programs to produce a series of groups within the population, each of which is the best able to classify one type of input signal from all other signals. In the orchestration phase, the best programs from each group are selected and placed in a hierarchy of systems, wherein each system contains the best programs that are able to classify one type of input signal from all other signals. Default weights are assigned to each system and each program within a system. Training signals are input into the selected programs, output values for each program and system are generated, and the weights associated with the programs and systems are adjusted.