Abstract: Certain aspects of the disclosure provide a method for detecting data collection errors by processing error data with a plurality of regression models to generate a plurality of predicted error rates over a plurality of time intervals. The method includes determining an error mode by applying a set of policy rules optimized for determining the error mode to the plurality of predicted error rates.

Abstract: At least one processor may receive a query response generated by a query machine learning (ML) model, wherein the query response is generated in response to a query from a client device. The at least one processor may generate an evaluated likelihood of the query response being found in a training data set comprising known valid data, wherein the generating is performed using an evaluation ML model. The at least one processor may determine that the evaluated likelihood indicates the query response is likely to include valid data. In response to the determining, the at least one processor may return the query response to the client device.

Abstract: A Large Language Model (LLM) for classifying documents by identifying indicators within the documents. A smart caching mechanism stores document classifications and associated indicators output from the LLM. The database contains document details, classifications, and associated indicators. A classification module classifies a new document by analyzing it for indicators, checking the cache for a match, and querying the database for the indicators if no match is found. The module applies a majority vote based on the classifications associated with the indicators.

Abstract: Methods and systems are presented for imputing missing data items within a first dataset based on data associated with a second dataset that is the nearest neighbor of the first dataset. A first mapping model is configured to map data subsets corresponding to a first data source to first positions in a multi-dimensional space. A second mapping model is configured to map data subsets corresponding to a second data source to second positions in the multi-dimensional space. The first and second mapping models are trained together to reduce a distance between positions mapped by the first and second mapping models based on corresponding data subsets that belong to the same entity. A nearest neighbor dataset to the first dataset is identified based on the first and second mapping models. Data associated with the nearest neighbor dataset is used to impute the missing data items of the first dataset.

Abstract: A system is configured to train a machine learning tree network using path based features, such as leaf nodes or connections between nodes. A first machine learning tree network model, for example, may be trained using a first set of training data, and used to generate predictions for a second set of training data. The path based features are determined from the first machine learning tree network model when generating the predictions for the second set of training data. The path based features may then be used to train a second machine learning tree network model, e.g., using logistic regression.

Abstract: A first schema accessed is associated with a plurality of entities that are participants of an electronic system. Each entity has a corresponding attribute. Each of a first subset of the entities has a respective attribute value below a threshold. Each of a second subset of the entities has a respective attribute value above the threshold. According to the first schema, it is determined that data and/or transactions associated with the first and second subsets of the entities are processed using a first and a second model, respectively. A second schema is generated by softening the predefined threshold such that according to the second schema, data and/or transactions associated with the first subset of the entities and data and/or transactions associated with the second subset of the entities are each processed using both the first model and the second model. The second schema is implemented in the electronic system.

Abstract: The present disclosure provides techniques for data retrieval using machine learning. One example method includes receiving a plurality of training episodes associated with different environments, wherein each training episode of the plurality of training episodes includes a sequence of states, computing, based on the plurality of training episodes, total counts of a plurality of values in the states, initializing, for each state of the sequence of states in each training episode of the plurality of training episodes, a reward based on the total counts of the plurality of values, and training a reinforcement learning agent using the rewards.

Abstract: There are provided systems and methods for adjustment of training data sets for fairness-aware artificial intelligence models. A service provider, such as an electronic transaction processor for digital transactions, may utilize different decision services that implement rules and/or artificial intelligence models for decision-making of data including data in production computing environment. Decision services may be used for data processing and decision-making, where multiple decision services may be invoked during run-time in order to complete a data processing request. When processing data, machine learning and other artificial intelligence models may be utilized by such decision services. These may be trained using a sampled training data set that takes into account data records' diversity and model attribution scores as providing valuable data points or observations for training and/or retraining the ML model. The sampled training data may be analyzed to determine these scores and generated for training.

Abstract: Systems and methods use hierarchical models to process conversations. A set of word vectors is processed using a sentence model, resulting in a sentence vector for the conversation message. The sentence vector is modified to include a time value. A set of sentence vectors, representing a time window, is processed using a window model, to generate a window vector for that time window. The window vector is updated to include a count value. A set of window vectors, corresponding to a set of time windows within the conversation, is processed using a conversation model to generate a conversation vector. A sentiment value indicating the sentiment of the conversation is presented, using a processor that generates the sentiment value from the conversation vector.

Abstract: Systems and methods for training machine learning models are disclosed. An example method includes receiving a semi-labeled set of training samples including a first set of training samples, where each training sample in the first set is assigned a known label, and a second set of training samples, where each training sample in the second set has an unknown label, determining a first loss component, the first loss component providing a loss associated with the first set, determining a second loss component, the second loss component having a value which increases based on a difference between a distribution of individually predicted values of at least the second set and an expected overall distribution of at least the second set, and training the machine learning model, based on the first loss component and the second loss component, to predict labels for unlabeled input data.

Abstract: Systems and methods for training machine learning models are disclosed. An example method includes receiving a semi-labeled set of training samples including a first set of training samples, where each training sample in the first set is assigned a known label, and a second set of training samples, where each training sample in the second set has an unknown label, determining a first loss component, the first loss component providing a loss associated with the first set, determining a second loss component, the second loss component having a value which increases based on a difference between a distribution of individually predicted values of at least the second set and an expected overall distribution of at least the second set, and training the machine learning model, based on the first loss component and the second loss component, to predict labels for unlabeled input data.

Abstract: A processor may identify a plurality of data sets subject to upcoming update processing in a next update cycle. For each of the plurality of data sets, the processor may determine a probability that data included in the data set has changed since a most recent update processing. The processor may exclude a first subset of the plurality of data sets having respective probabilities below a threshold value from the upcoming update processing until the respective probabilities are determined again in a subsequent update cycle. The processor may perform the upcoming update processing on the plurality of the data sets not included in the first subset, where the upcoming update processing may include obtaining updated data from at least one external data source.

Abstract: A method and system that proactively generate alerts for updating a scraping script to avoid scraping script errors. A predetermined number of webpages targeted by the scraping script are randomly sampled. The scraping script is appended to each webpage in the sample. A structured list of text fragments across the webpages with the appended script is generated. At predetermined time intervals, a fresh set of webpages is sampled, the scraping script is appended to the webpages, and a new structured list is generated. If the new structured list and the previous structured list do not match, the webpages may have been changed and the scraping script may have to be updated. An alert is generated indicating that such update is required and may include a location of the mismatch. Therefore, scraping script errors are proactively detected and can be rectified before an actual error occurs and propagates.

Abstract: Certain aspects of the present disclosure provide techniques for medoid-based data compression. One example method generally includes receiving item data indicative of one or more items, determining one or more medoids based on the item data, determining, for each item of the one or more items, a corresponding medoid based on the one or more medoids, identifying, for each item of the one or more items, a difference between the item and the corresponding medoid for the item, storing the one or more medoids, and storing, for each item of the one or more items, the identified difference between the item and the corresponding medoid.

Abstract: Methods and systems are presented for imputing missing data items within a first dataset based on data associated with a second dataset that is the nearest neighbor of the first dataset. A first mapping model is configured to map data subsets corresponding to a first data source to first positions in a multi-dimensional space. A second mapping model is configured to map data subsets corresponding to a second data source to second positions in the multi-dimensional space. The first and second mapping models are trained together to reduce a distance between positions mapped by the first and second mapping models based on corresponding data subsets that belong to the same entity. A nearest neighbor dataset to the first dataset is identified based on the first and second mapping models. Data associated with the nearest neighbor dataset is used to impute the missing data items of the first dataset.

Abstract: Certain aspects of the present disclosure provide techniques for medoid-based data compression. One example method generally includes receiving item data indicative of one or more items, determining one or more medoids based on the item data, determining, for each item of the one or more items, a corresponding medoid based on the one or more medoids, identifying, for each item of the one or more items, a difference between the item and the corresponding medoid for the item, storing the one or more medoids, and storing, for each item of the one or more items, the identified difference between the item and the corresponding medoid.

Abstract: Computer system security and efficiency of processing operations may be improved using techniques that are described relating to analyzing user actions based on time of day of occurrence, and using time of a day as a factor in determining whether a particular action should be allowed or disallowed. Past action times can be transformed to a two-dimensional representation using a radial time schema that avoids discontinuity. A probability distribution can indicate a likelihood of whether a new action fits a previous pattern. If a new user action is relatively unlikely due to time of day, the new user action might be denied/prevented from completing, thus enhancing computer system security and avoiding unnecessary computational processing costs.

Abstract: Systems and methods for generating a contextually adaptable classifier model are disclosed. An example method is performed by one or more processors of a system and includes obtaining a dataset, feature values, and labels, transforming each datapoint into a natural language statement (NLS) associating the datapoint's feature values and label with feature identifiers and a label identifier, generating a feature matrix for each NLS, transforming the feature matrix into a global feature vector, generating a target vector for each NLS, transforming the target vector into a global target vector having a same shape, and generating, using the vectors, a similarity measurement operation, and a loss function, a classifier model trained to generate a compatibility score predictive of an accuracy at which the classifier model can classify given data based on at least one of a different feature characterizing the given data or a different label for classifying the given data.

Abstract: Techniques are disclosed relating to weakly supervised machine learning, which may be employed when there is a limited amount of labeled data available. A computer system may generate respective sets of synthetic labels for unlabeled data for a classification problem, where a given set of synthetic labels is produced by a corresponding one of a plurality of different label models. The computer system may then fit a set of supervised models, where each supervised model is fitted with one of the respective sets of synthetic labels to produce a respective set of predictions. The computer system may then evaluate the set of supervised models based on their respective set of predictions and using a set of labeled data for the classification problem. The evaluation may be used to select a particular supervised model and its corresponding label model.

Abstract: A system deploying a machine learning technique that utilizes known code graph and abstract syntax tree pairs for known JSON objects to learn a function for predicting a corresponding abstract syntax tree from a new JSON object. The predicted abstract syntax tree is used to generate code for formatting the new JSON object into a standardized data structure.