Abstract: A method for using an artificial intelligence (AI) technique to forecast market activities by specific parties with respect to derivatives and other specific types of financial instruments is provided. The method includes: retrieving first information that relates to at least one form that corresponds to a government filing; generating, based on the first information, a first knowledge graph that relates to an entity, such as a commercial concern; retrieving second information that relates to historical actions performed by at least one person that is associated with the entity; and forecasting, based on the first knowledge graph and the second information, at least one proposed future transaction to be executed by the person with respect to the first entity. The forecasting is based on an application of an AI algorithm to the information retrieved from the government filing(s).

Abstract: A method for using an artificial intelligence (AI) technique to forecast trading behavior and thematic concepts for trade baskets with respect to derivatives and other specific types of financial instruments is provided. The method includes: retrieving, from an internet website, information that relates to at least one form that corresponds to a government filing; using the retrieved information to generate a knowledge graph that relates to a particular entity; generating at least one application programming interface (API) that is configured to analyze the retrieved information and the knowledge graph in order to provide insight into at least one financial instrument that relates to the particular entity; and forecasting, based on an output of the API(s) and by applying an AI algorithm to the knowledge graph, at least one proposed future transaction to be executed with respect to the financial instrument(s) that relate to the particular entity.

Abstract: A method and a system for generating domain-aware captions for time-series images that are capable of adapting to new domains without retraining are provided. The method includes: receiving information that relates to a first time-series image that is associated with a target domain; generating a generic caption for the first time-series image; extracting, from a memory based on the generic caption, a plurality of image-caption pairs; generating, for each respective one of the plurality of image-caption pairs, a corresponding domain-agnostic caption that includes information that describes a shape of the respective image; and adapting the generic caption into a domain-specific caption for the first time-series image that relates to the target domain. The generating of domain-agnostic captions and domain-specific captions may be performed by using models that are respectively trained based on synthetic time series images having captions that correspond to a set of parameters.

Abstract: A method and system for generating keywords that distinguish a group of selected documents from a larger corpus. The method includes: receiving a corpus that includes a plurality of documents; selecting from the corpus, based on at least one predetermined criterion, a group of the documents; determining a first Inverse Document Frequency (IDF) score for each word in a vocabulary of the group with respect to the corpus; determining a second IDF score for each word in the vocabulary of the group with respect to the group; generating based on the first IDF score and the second IDF score, a Group Frequency Inverse Document Frequency (GFIDF) score for each word in the vocabulary of the group; and assigning based on the generated GFIDF score for each word in the vocabulary of the group, at least one keyword.

Abstract: A method for using a large language model to generate executable code for workflow execution in a manner that integrates user feedback and adjusts the workflow as needed while preserving data privacy is provided. The method includes: receiving first information that relates to a workflow context, second information that relates to at least one application programming interface (API), and third information that relates to a code generation request; using the received information to generate a lecture, and transmitting the lecture to a language model; receiving a user query that relates to performing a task, and transmitting the query to the language model; receiving a workflow that is automatically generated by the language model based on the lecture and the query; and executing the workflow in order to generate an output that is responsive to the query.

Abstract: A method and system for generating keywords that distinguish a group of selected documents from a larger corpus. The method includes: receiving a corpus that includes a plurality of documents; selecting from the corpus, based on at least one predetermined criterion, a group of the documents; determining a first Inverse Document Frequency (IDF) score for each word in a vocabulary of the group with respect to the corpus; determining a second IDF score for each word in the vocabulary of the group with respect to the group; generating based on the first IDF score and the second IDF score, a Group Frequency Inverse Document Frequency (GFIDF) score for each word in the vocabulary of the group; and assigning based on the generated GFIDF score for each word in the vocabulary of the group, at least one keyword.

Abstract: A method for preserving privacy with respect to modeling event sequence data is provided. The method includes: receiving information about a sequence of events; modeling the event sequence by a Hawkes process that has an intensity that includes an exogenous base intensity rate and an indigenous component that has an excitation rate and a decay rate; analyzing the received information; and determining estimated values of the exogenous base intensity rate and the excitation rate, such that an accuracy of the estimates corresponds to a length of time over which the sequence of events is observed. Differential privacy is introduced by adding noise to the sequence of events in order to preserve the privacy of individuals associated with the events, and a cost of the differential privacy is expressible as an additional length of observation time required to ensure the accuracy of the estimates.

Abstract: In some aspects, the techniques described herein relate to a method including: receiving, at a forecasting platform, a time series; partitioning the time series into a plurality of partitions; processing the time series with a convolutional neural network machine learning model; generating, by the convolutional neural network machine learning model, a plurality of tokens, wherein the plurality of tokens are based on the time series; processing the plurality of tokens with a transformer machine learning model; generating, by the transformer machine learning model, a transformer vector, wherein the transformer vector is based on relationships among the plurality of tokens determined by the transformer machine learning model; and assigning, by a multilayer perceptron classifier, a classification to the transformer vector.

Abstract: A method for providing a domain-specific language model to facilitate natural language data analytics is disclosed. The method includes aggregating documents from various sources, each of the documents including natural language data; ingesting each of the documents to generate structured data sets that are organized according to a contextual hierarchy; determining prompts that provide domain-specific information for a language model, the domain-specific information including instructions to access the structured data sets; receiving a request via a graphical user interface, the request relating to questions in a natural language format; generating, by using the language model, software codes for the request based on the prompts; and executing each of the software codes to identify results for the request from the structured data sets.

Abstract: A method for using multidimensional Hawkes processes for modeling and generating sequential events data in order to improve accuracy with respect to parameter estimation for various domains such as finance, epidemiology, and personalized recommendations is provided. The method includes: receiving information that relates to a sequence of events; modeling, based on the received information, the sequence of events by a multidimensional Hawkes process that relates to a conditional density function that includes a base intensity component and a cross-activation matrix component; defining, based on the conditional density function, a log-likelihood function that is dimensionally separable; and determining a maximum-likelihood estimation of a solution to the log-likelihood function along at least one dimension.

Abstract: A method and a system for using differential privacy techniques to provide axe obfuscation with respect to information included in an inventory axe list of available securities is provided. The method includes: obtaining first information to be included in a first inventory axe list to be published on a particular day; retrieving second information included in a second inventory axe list that was published on the previous day and/or several previous days; obfuscating the obtained first information by applying an algorithm based on the difference between the first information and the second information; and publishing the first inventory axe list by transmitting the obfuscated first information to a plurality of intended recipients. The quality of obfuscation may be measured and controlled as a function of desired privacy level and potential cost.

Abstract: A method and a system for detecting an anomalous sequence of events in stream data are provided. The method includes: receiving a first set of raw data; analyzing the first set of raw data in order to determine a first event sequence; applying a first Hidden Markov Model (HMM) to the first event sequence in order to generate a first output; and determining, based on the first output, whether the first event sequence is classifiable as being an anomalous event sequence. The HMM is trained by using known sequences of normal events and event sequences that are known to be anomalous.

Abstract: A method and a system for obtaining conditional demographic parity in the construction of a data-driven model are provided. The method includes: identifying features associated with the model; determining a first joint distribution of model outputs and a feature based on a first level of a particular one of the features and a second joint distribution of model outputs and a feature based on a second level of the particular feature; computing a bi-causal transport distance between the first joint distribution and the second joint distribution; computing a regularizer based on the bi-causal transport distance; and applying the regularizer to the model.

Abstract: A method for privacy-preserving inventory matching may include: (1) receiving a plurality of axe submissions; (2) arranging the parties into data structures based on a direction in the party's axe submission; (3) sending each party's commitment to the other party; (4) receiving, from each party, output secret-shares of an arithmetized comparison circuit; (5) verifying that the output secret-shares of the arithmetized comparison circuit received from the parties match commitments to the output secret-shares sent by the respective opposite party; (6) identifying a minimal party based on the outputs of the arithmetized comparison circuit; (7) generating and sending a proof of the minimal party identification to the minimal party; (8) receiving a minimal quantity integer from the minimal party; (9) revealing the minimal quantity integer to the first party and the second party; and (10) executing the trade for the minimal quantity integer.

Abstract: Systems and methods for generation of a synthetic dataset that simultaneously represents the original data and preserves privacy are provided. The objective of answering statistical queries in a differentially-private manner is addressed by providing data-independent and data-dependent algorithms based on space partitioning for differentially private dataset release. These algorithms are intuitive and transparent, resulting in theoretical results on the utility-privacy tradeoffs where utility is measured with respect to kernel density preservation. The data-dependent approach overcomes the curse of dimensionality and leads to a scalable algorithm.

Abstract: A method for privacy-preserving inventory matching may include: (1) receiving a plurality of axe submissions; (2) arranging the parties into data structures based on a direction in the party's axe submission; (3) sending each party's commitment to the other party; (4) receiving, from each party, output secret-shares of an arithmetized comparison circuit; (5) verifying that the output secret-shares of the arithmetized comparison circuit received from the parties match commitments to the output secret-shares sent by the respective opposite party; (6) identifying a minimal party based on the outputs of the arithmetized comparison circuit; (7) generating and sending a proof of the minimal party identification to the minimal party; (8) receiving a minimal quantity integer from the minimal party; (9) revealing the minimal quantity integer to the first party and the second party; and (10) executing the trade for the minimal quantity integer.

Abstract: A method for preserving privacy with respect to modeling event sequence data is provided. The method includes: receiving information about a sequence of events; modeling the event sequence by a Hawkes process that has an intensity that includes an exogenous base intensity rate and an indigenous component that has an excitation rate and a decay rate; analyzing the received information; and determining estimated values of the exogenous base intensity rate and the excitation rate, such that an accuracy of the estimates corresponds to a length of time over which the sequence of events is observed. Differential privacy is introduced by adding noise to the sequence of events in order to preserve the privacy of individuals associated with the events, and a cost of the differential privacy is expressible as an additional length of observation time required to ensure the accuracy of the estimates.

Abstract: A method for using a Gaussian Process-based algorithm to approximate an optimal stopping of a time series that corresponds to a sequence of events is provided. The method includes: receiving information that relates to an event sequence; estimating, based on the received information, a first potential reward that is obtained by stopping the event sequence at a first time, and a set of respective second potential rewards that are obtained by stopping the event sequence at corresponding times; and determining, based on the estimated first and second potential rewards, an optimal time for stopping the event sequence. The event sequence may include a numerical sequence that is modeled as a statistical learning method via a Gaussian Process (GP) function and/or a deep GP function that indicates a probability density distribution of the items in the numerical sequence over a predetermined time interval.

Abstract: A method for using an artificial intelligence (AI) model to simulate a limit order book market in order to facilitate study and evaluation of trading strategies is provided. The method includes: receiving information that relates to a state of the market at a particular time; and determining, based on the information, a potential market action that is expected to occur. The determination is made by applying an AI algorithm that implements a machine learning technique to determine the potential market action. The AI algorithm is trained by using historical data that relates to the market.

Abstract: Methods and systems for using images that represent time-series data to forecast corresponding images depicting future values of the time-series data are provided. The method includes: receiving a set of time-series data; converting the set of time-series data into a partial first image that includes a blank region to which future data to be included in the first set of time-series data corresponds; and performing an inpainting operation with respect to the partial first image by generating pixels for filling in the blank region in order to produce an augmented version of the first image. A machine learning algorithm that is trained by using historical time-series data may be used to perform the inpainting operation.