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: A method for automating a process of generating messages that are responsive to client inquiries by using an AI algorithm that implements a machine learning technique to ensure accuracy and timeliness in the responses is provided. The method includes: receiving a first message that includes an inquiry that relates to an account associated with a user; applying an AI algorithm for analyzing the first message in order to extract information that relates to the inquiry; determining, based on a result of the analysis, whether generating a response to the inquiry requires human intervention; when human intervention is not required, retrieving information that is responsive to the inquiry from a memory; generating a second message that includes the information that is responsive to the inquiry; and transmitting the second message to the user.

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: A method for automating a process of generating messages that are responsive to client inquiries by using an AI algorithm that implements a machine learning technique to ensure accuracy and timeliness in the responses is provided. The method includes: receiving a first message that includes an inquiry that relates to an account associated with a user; applying an AI algorithm for analyzing the first message in order to extract information that relates to the inquiry; determining, based on a result of the analysis, whether generating a response to the inquiry requires human intervention; when human intervention is not required, retrieving information that is responsive to the inquiry from a memory; generating a second message that includes the information that is responsive to the inquiry; and transmitting the second message to the user.

Abstract: Methods and systems for generating a counterfactual explanation that is robust with respect to a machine learning model and changes in the model are provided. The method includes: receiving raw data and training a model by using the raw data; perturbing the model by modifying the raw data; computing a first counterfactual explanation that relates to the model; computing a first counterfactual stability metric that relates to the original version of the first model and a second counterfactual stability metric that relates to the perturbed version of the first model; retrieving unstable counterfactual factors that relates to original and perturbed versions of the model; deleting data points that include any such unstable counterfactual factor; and reconstructing the model based on data that does not include the deleted data points.

Abstract: Methods and systems for generating a model to be used for evaluating credit and loan applications are provided. The method includes: training a first model by using all features included in a universe of candidate features; measuring a first metric that relates to an accuracy of the first model and a second metric that relates to a disparity of the first model; constructing a graph based on pairwise correlations of the features; clustering the features into feature sets; estimating a respective disparity contribution associated with each feature set; selecting feature sets to be included in a second model; training, the second model; measuring the first metric and the second metric with respect to the second model; and determining whether the second model satisfies a predetermined accuracy level and a predetermined disparity reduction with respect to the first model.