Abstract: Systems and methods for using an artificial intelligence-based technique for automatic generation of travel and dining reviews are provided. The method includes: receiving a request for a review of an entity that provides a service to a user; applying a first artificial intelligence (AI) algorithm to the received request in order to generate the review of the entity; and outputting the review of the entity. The entity provides either or both of a travel-related service and a dining-related service, and as such, the entity may include a restaurant or a hotel. The AI algorithm may use a large language model and/or may be trained such that the review has a style and a tone of a Zagat review.

Abstract: Methods and systems for detecting and mitigating hallucinations in artificial intelligence (AI) summarizations of user-generated content are provided. The method includes: receiving an AI-generated content item; retrieving historical content items that have been generated by human beings; comparing the AI-generated content item with the historical content items in order to determine whether text string matches are present; when a determination is made that no match exists, performing a semantic matching operation to identify text strings included in the historical content items that are semantically similar to text strings in the AI-generated content item; and determining, based on the comparison and the semantic matching operation, whether the AI-generated content item is a hallucination. When a hallucination is detected, the hallucination may be mitigated by removing a textual perturbation and/or replacing the textual perturbation with text that accurately reflects the original content item.

Abstract: In some aspects, the techniques described herein relate to a method including: receiving, as input to a binary search process, a subject vector embedding and a class vector embedding, wherein the subject vector embedding is generated from a plurality of subject text strings and wherein the class vector embedding is generated from a class text string; generating a similarity score; determining that the similarity score is below a threshold value; splitting the plurality of subject text strings into a first new plurality of subject text strings and a second new plurality of subject text strings; receiving a new subject vector embedding, wherein the new subject vector embedding is generated from the first new plurality of subject text strings; and calling the binary search process recursively using the new subject vector embedding and the class vector embedding as input to the binary search process.

Abstract: In some aspects, the techniques described herein relate to a method including: receiving, as input to a binary search process, a subject vector embedding and a class vector embedding, wherein the subject vector embedding is generated from a plurality of subject text strings and wherein the class vector embedding is generated from a class text string; generating a similarity score; determining that the similarity score is below a threshold value; splitting the plurality of subject text strings into a first new plurality of subject text strings and a second new plurality of subject text strings; receiving a new subject vector embedding, wherein the new subject vector embedding is generated from the first new plurality of subject text strings; and calling the binary search process recursively using the new subject vector embedding and the class vector embedding as input to the binary search process.

Abstract: In some aspects, the techniques described herein relate to a method including: receiving, as input to a binary search process, a subject vector embedding and a class vector embedding, wherein the subject vector embedding is generated from a plurality of subject text strings and wherein the class vector embedding is generated from a class text string; generating a similarity score; determining that the similarity score is below a threshold value; splitting the plurality of subject text strings into a first new plurality of subject text strings and a second new plurality of subject text strings; receiving a new subject vector embedding, wherein the new subject vector embedding is generated from the first new plurality of subject text strings; and calling the binary search process recursively using the new subject vector embedding and the class vector embedding as input to the binary search process.

Abstract: Systems and methods for using an artificial intelligence-based technique for automatic generation of travel and dining reviews are provided. The method includes: receiving a request for a review of an entity that provides a service to a user; applying a first artificial intelligence (AI) algorithm to the received request in order to generate the review of the entity; and outputting the review of the entity. The entity provides either or both of a travel-related service and a dining-related service, and as such, the entity may include a restaurant or a hotel. The AI algorithm may use a large language model and/or may be trained such that the review has a style and a tone of a Zagat review.

Abstract: A method and a system for detecting abnormal and/or anomalous rejections of requests for quotes for foreign exchange transactions are provided. The method includes: receiving a request for quote (RFQ) that relates to a proposed foreign exchange (FX) transaction; retrieving first information that relates to a financial capability of the requester to conduct the proposed FX transaction; applying a first algorithm that is designed to make an initial determination as to whether the RFQ is acceptable, based on the RFQ and the first information; when the initial determination indicates that the RFQ is not acceptable, applying a second algorithm that uses an artificial intelligence (AI) technique to determine a potential reason that the initial determination has indicated that the RFQ is not acceptable; and generating a report that includes information that relates to the potential reason that the initial determination has indicated that the RFQ is not acceptable.

Abstract: Methods and systems for automatically identifying umbrella sub-funds from within an umbrella investment fund are provided. The method includes: receiving a first data set that includes entity-specific records; retrieving, for each respective entity-specific record, a corresponding set of entity-specific reference data; extracting, from each respective set of reference data, a corresponding umbrella name; determining, based on the corresponding umbrella name, whether the respective entity is associated with a particular sub-fund; and associating the respective entity with other entities that have previously been determined as being associated with the particular sub-fund. The determination may be made by applying an artificial intelligence (AI) algorithm that uses a machine learning technique to determine a probability with respect to whether the respective entity is associated with the particular sub-fund.

Abstract: A method for identifying, contracting, evaluating, bounding, and filtering out uncertainty in survey data is provided. The method includes: receiving survey responses with respect to a customer survey; constructing a simulated numerical model that replicates the structure of the original survey by using responses that are generated randomly from distribution of responses with constraint variability that specifically account for the uncertainty that arises from the subjective nature of sampling response from an ordinal range of possible options; matching between the original survey and the numerical model using a machine learning algorithm; and evaluating and filtering out the uncertainty of the original survey. In addition, a method is offered to constrain and contract the uncertainty by assigning survey responses to corresponding evenly distributed bins and by calibrating the survey responses by attaching a short textual description to each of the ordinal values in the original survey.

Abstract: A method and a system for generating an interpretable embedding that corresponds to a sequence of events is provided. The method includes: receiving information that corresponds to a sequence of events that respectively correspond to interactions between a customer and an organization; determining, for each respective event, a respective product associated with the organization and a respective channel via which the event has occurred; assigning a respective sentiment to each event; computing a respective weight for each event; aggregating the computed weights with respect to the products and the channels; and using the aggregated weights to generate the interpretable embedding for the customer. The interpretable embedding is then usable for generating targeted offers to the customer, handling complaints, and preventing subsequent complaints.

Abstract: A method and a system for using an online learning framework for mixture of multivariate Hawkes processes to model sequences of events are provided. The method includes: receiving data that corresponds to a group of event sequences; generating a mixture of multivariate Hawkes processes model based on the group of event sequences; and adjusting the model by applying an online learning algorithm to the generated model. The online learning algorithm includes an E-step that corresponds to updating a set of responsibilities that relates to the group of event sequences and an M-step that corresponds to updating Hawkes processes parameters that relate to the group of event sequences.

Abstract: A method for identifying, contracting, evaluating, bounding, and filtering out uncertainty in survey data is provided. The method includes: receiving survey responses with respect to a customer survey; constructing a simulated numerical model that replicates the structure of the original survey by using responses that are generated randomly from distribution of responses with constraint variability that specifically account for the uncertainty that arises from the subjective nature of sampling response from an ordinal range of possible options; matching between the original survey and the numerical model using a machine learning algorithm; and evaluating and filtering out the uncertainty of the original survey. In addition, a method is offered to constrain and contract the uncertainty by assigning survey responses to corresponding evenly distributed bins and by calibrating the survey responses by attaching a short textual description to each of the ordinal values in the original survey.

Abstract: A method for identifying, contracting, evaluating, bounding, and filtering out uncertainty in survey data is provided. The method includes: receiving survey responses with respect to a customer survey; constructing a simulated numerical model that replicates the structure of the original survey by using responses that are generated randomly from distribution of responses with constraint variability that specifically account for the uncertainty that arises from the subjective nature of sampling response from an ordinal range of possible options; matching between the original survey and the numerical model using a machine learning algorithm; and evaluating and filtering out the uncertainty of the original survey. In addition, a method is offered to constrain and contract the uncertainty by assigning survey responses to corresponding evenly distributed bins and by calibrating the survey responses by attaching a short textual description to each of the ordinal values in the original survey.

Abstract: A method for identifying, contracting, evaluating, bounding, and filtering out uncertainty in survey data is provided. The method includes: receiving survey responses with respect to a customer survey; constructing a simulated numerical model that replicates the structure of the original survey by using responses that are generated randomly from distribution of responses with constraint variability that specifically account for the uncertainty that arises from the subjective nature of sampling response from an ordinal range of possible options; matching between the original survey and the numerical model using a machine learning algorithm; and evaluating and filtering out the uncertainty of the original survey. In addition, a method is offered to constrain and contract the uncertainty by assigning survey responses to corresponding evenly distributed bins and by calibrating the survey responses by attaching a short textual description to each of the ordinal values in the original survey.