Abstract: Systems and methods for forecasting data drift for model monitoring. In some aspects, the system receives a current explainability vector for a machine learning model and a data drift vector for historical data profiles. The machine learning model is trained on historical data including values for a first set of features. The system generates a projected synthetic dataset using the data drift vector and updates the machine learning model based on the projected synthetic dataset. Using the current explainability vector and a future explainability vector for the updated model, the system generates a second set of features and determines a drift threshold vector for the second set of features based on values in the explainability vectors. The system determines a discrepancy score for each feature of the second set of features. The system generates an alert including features in the second set of features and their associated discrepancy scores.

Abstract: Methods and systems are described herein for determining data quality using data reconstruction models. The system receives a dataset including entries and features and generates a machine learning model for each feature of the dataset. Each model may be trained to generate predictions for a corresponding feature based on other features of the dataset. The system may input, into each model, values of the other features to obtain prediction values for the corresponding feature. For a subset of entries for which a difference between the predicted and actual values of the corresponding feature satisfies a threshold, the system may determine relative impacts of the other features on the corresponding feature. The system may then transmit, to a user, a subset of the other features having relative impacts that meet a feature impact threshold.

Abstract: The invention relates to executing an action for a cryptographic storage application by comparing a movement dataset, which may contain positional and inertial datasets, with a user profile dataset. The system may receive a first cryptographic storage application address, retrieve a first movement dataset corresponding to a first time period, retrieve a user profile dataset, compare the first movement dataset with the user profile dataset, and execute an action for the first cryptographic storage application.

Abstract: Methods and systems are described herein for updating machine learning models based on the impact of features on predictions. The system inputs, into a machine learning model, a dataset including entries and features to obtain predictions. The machine learning model is trained to generate predictions for entries based on features. The system generates, for each entry, feature impact parameters indicating a relative impact of each feature on each prediction. The system determines a feature impact threshold for assessing which features have contributed to each prediction and generates, using the feature impact parameters and the feature impact threshold, a sparsity metric for each prediction. The sparsity metric indicates which features have relative impacts that meet the feature impact threshold for the prediction. The system generates a global sparsity metric for the machine learning model and updates the machine learning model based on the global sparsity metric.

Abstract: Methods and systems are described herein for updating machine learning models using weights. The system inputs, into a machine learning model, a dataset including entries and features to obtain a relative impact of each feature. The system generates, using the relative impacts, a sparsity metric for each entry, each sparsity metric indicating a measure of a number of features used to generate a corresponding prediction. The system retrieves a sparsity threshold for assigning weights to the plurality of entries. The system generates an updated dataset based on assigning, to each entry within the dataset, a corresponding weight. Each corresponding weight is determined based on a relation of the sparsity metric to the sparsity threshold. The system inputs, into the machine learning model, the updated dataset to update the machine learning model based on the corresponding weights, where the machine learning model relies more heavily on entries with higher corresponding weights.

Abstract: A method and related system operations include determining a predicted category by providing a prediction model with a set of input feature values and generating a plurality of conditionals based on the set of input feature values for a set of features and the predicted category. The method also includes filtering the plurality of conditionals based on a knowledge base to obtain a selected conditional by generating a set of sub-conditional paths by providing, as an input for a prompt generator model, a candidate conditional of the plurality of conditionals to the prompt generator model and selecting the candidate conditional as the selected conditional based on a determination that the set of sub-conditional paths satisfies a set of criteria associated with a set of sequences of the knowledge base. The method further includes storing the selected conditional in a data structure in association with the set of input feature values.

Abstract: Disclosed embodiments may include a system for fraud detection. The system may identify, using a web browser extension, that a user has navigated to a webpage on a user device. The system may receive, via the webpage, data associated with a transaction. Responsive to receiving the data, the system may retrieve search history data corresponding to a searching session associated with the data, and may identify a searching session path corresponding to the transaction. The system may determine, using a machine learning model (MLM) and based on the search history data and the searching session path, a likelihood of fraud associated with the data. The system may determine whether the likelihood exceeds a predetermined threshold. Responsive to determining the likelihood exceeds the predetermined threshold, the system may conduct one or more fraud prevention actions.

Abstract: In some implementations, a device may obtain a first document set associated with a first code repository. The device may generate a first embedding set of one or more embeddings for respective documents included in the first document set. The device may obtain a second embedding set of one or more embeddings for respective documents included in a second document set associated with a second code repository. The device may compare the first embedding set to the second embedding set. The device may generate a code repository similarity score that indicates a similarity between the first code repository and the second code repository. The device may perform, based on the code repository similarity score satisfying a threshold, an action associated with the first code repository and/or the second code repository.

Abstract: A method and related system of operations include providing a set of feature values to determine a first reward value to a prediction model configured with a set of model parameters and obtaining a set of feature weights for features of the set of feature values by performing a local explainability operation that comprises providing the prediction model with a set of test inputs to determine a set of feature weights. The method also includes selecting a subset of feature weights of the set of feature weights based on a feature subset of the features indicated by a policy parameter of the prediction model, determining a reward modification value based on the subset of feature weights, and determining a second reward value based on the first reward value and the reward modification value. The method also includes updating the set of model parameters based on the second reward value.

Abstract: Disclosed embodiments may include a system for providing automated bill splitting. The system may receive speech data. The system may identify, from the speech data and using natural language processing, one or more users. The system may determine, from the speech data and using natural language processing, orders of the one or more users. The system may determine, from the speech data and using natural language processing, rules for the orders of the one or more users. The system may process one or more payments for the orders based on the rules and one or more credentials associated with the one or more users.

Abstract: Systems and methods for triggering token alerts. In some aspects, the system, after determining that the probability that an authentication request from an authentication token is associated with a malicious activity is above a threshold, determines whether a user device associated with the authentication token is within a threshold distance of the authentication token. In response to determining that the authentication token is not within the threshold distance of the user device, the system declines the authentication request and transmits an alert request to the authentication token to emit an audio signal from a speaker included in the authentication token.

Abstract: Systems and methods for using hash tables generating textual prediction explanations. In some aspects, the system receives a first plurality of user profiles and a corresponding plurality of resource availability values. Each user profile includes values for a first set of features. The system processes a first machine learning model to extract an explainability vector. The first machine learning model receives as input the first set of features and outputs a resource availability value. The system, using the explainability vector, selects a subset of features having corresponding values in the explainability vector above a threshold. The system generates a set of categories based on the subset of features and a hash table including the set of categories. The hash table is indexable using a hash value generated based on values for the subset of features. The system transmits to a user system corresponding a user profile a textual prediction explanation.

Abstract: Disclosed embodiments may include a system for executing programmable macros based on external device interactions. The system may include one or more processors, and a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to execute programmable macros based on external device interactions. The system may receive a device identification of an external device. The system may receive a rule associated with the external device, wherein the rule comprises a triggering event and transfer instructions. The system may receive, from the external device, device data. Responsive to determining, from the device data, that the triggering event has occurred, the system may execute the transfer instructions.

Abstract: Disclosed embodiments may include a method and system for automated incremental payments. The system may identify recurring charges from historical account data. Based on the recurring charges and an incremental period, the system may calculate an incremental amount and expected amount. At each iteration of the incremental period, the incremental amount may be assigned to a savings bucket. The value of the savings bucket may be subtracted from an actual account balance to calculate a reduced account balance. The system may generate and transmit a graphical user interface to a user device showing the reduced account balance. The system may receive current data containing a charge that corresponds to the recurring charges. The system may reduce the value of the savings bucket by the amount of the current data charge. If the current data charge is different from the expected amount, the system may adjust the incremental amount accordingly.

Abstract: In some implementations, a server may receive, from a user device, one or more credentials associated with a user. Accordingly, the server may transmit, to the user device, instructions for generating a user interface including a plurality of visual components based on authenticating the user with the one or more credentials. The server may detect, during a first interval, a lack of interaction with the user interface. Accordingly, the server may remove one of the plurality of visual components from the user interface based on the lack of interaction. Additionally, the server may detect, during a second interval, one or more interactions with the user interface and may update a similarity score associated with the user based on properties associated with the one or more interactions. Accordingly, the server may restore the visual component to the user interface based on the updated similarity score satisfying a similarity threshold.

Abstract: Methods and systems are described herein for novel uses and/or improvements to artificial intelligence applications. As one example, methods and systems are described herein related to adapting explainable artificial intelligence (XAI) to non-differentiable models (e.g., as used in intent prediction, fraud detection, and/or cyber incident detection). The systems and methods achieve this through the use of integrated gradients. For example, the systems and methods generate numerical approximations to gradients and integrals for non-differentiable models. These integrated gradients may then be used to apply XAI to non-differentiable models.

Abstract: In some aspects, a computing system obtain a first dataset including a set of original data samples. The computing system may generate a key that indicates a location within the first dataset where spurious data should be stored. The computing system may determine a modified value associated with a first data sample of the set of original data samples, where the modified value causes a machine learning model to generate output that does not match a label associated with the first data sample. Based on the first data sample, the computer system may generate a spurious data sample comprising the modified value. Based on the key, the computer system may add the spurious data sample to the first dataset. In some aspects, based on a request for the first dataset, the computing system may remove the spurious data sample from the first dataset.

Abstract: In some aspects, a computing system obtain a first dataset including a set of original data samples and a first set of spurious data samples. Based on a time period expiring, the computing system may replace the first set of spurious data samples in the first dataset with a second set of spurious data samples. The computing system may obtain an indication that a second dataset is available via a third-party computing device. Based on a determination that a subset of samples of the second dataset correspond to the first set of spurious data samples, the computing system may determine a time window in which an incident occurred. As an example, the time window may be determined to correspond to a time before the first set of spurious data samples were replaced with the second set of spurious data samples.

Abstract: In some aspects, a computing system may generate uninformative features that may be added to a dataset of real features to use as a baseline for determining the quality of an explanation of model output. The uninformative features may be features that do not correlate with what a model is tasked with predicting (e.g., the uninformative features may be random values), and the real features may be informative and correlate with what the model is tasked with predicting (e.g., variables of a dataset sample). A machine learning model may be trained on a dataset that includes both the real features and the uninformative features. The computing system may generate feature attributions for model output, which may include feature attributions for the uninformative features and the real features in the dataset.

Abstract: In some aspects, a computing system may iterate between adding spurious data to the dataset and training a model on the dataset. If the model's performance has not dropped by more than a threshold amount, then additional spurious data may be added to the dataset until the desired amount of performance decrease has been achieved. the computing system may determine the amount of impact each feature has on a model's output. The computing system may generate a spurious data sample by modifying values of features that are more impactful than other features. The computing system may repeatedly modify the spurious data that is stored in a dataset. If a cybersecurity incident occurs (e.g., the dataset is stolen or leaked), the system may identify when the cybersecurity incident took place based on the spurious data that is stored in the dataset.