Abstract: Systems and methods are provided to perform context-aware text extraction.

Abstract: Systems and methods for monitoring items in publicly available inventories, such as websites, are disclosed. Items to be monitored in the publicly available inventories are identified based on embeddings obtained for the inventory items. For example, matching inventory items may be identified based on proximity of the embeddings, such as the cosine distance between embeddings, or a classification machine learning model may be trained to infer matches, e.g., based the embeddings as well as information related to the user and source of the publicly available inventories. The inventory items in the publicly available inventories may be monitored to detect changes which may be reported. Feedback related to the match between inventory items may be used to adjust one or more parameters used for matching.

Abstract: Systems and methods for identifying suspected anomalies in time series data are disclosed. An example method may receiving time series data for at least one quantity, the time series data including values of the at least one quantity at each of a plurality of times, determining a list of gradients for the time series data, each gradient in the list of gradients based on two or more values of the time series data separated by a specified number of values of the time series data, deriving a plurality of statistics based on the determined list of gradients, and performing a supervised machine learning process based on the derived plurality of statistics to generate a trained machine learning model for identifying one or more suspected anomalies in the time series data.

Abstract: Systems and methods may be used to generate and use a merchant community graph generated based on merchant financial transaction data. Connections between merchants and other data within the merchant community graph can be used to detect fraud, target product offerings and or other advertisements, detect similar communities, generate dynamic attributes that may be used to develop machine learning models, and develop new user interfaces (UIs) and other features of an information service.

Abstract: Certain aspects of the present disclosure provide techniques for generating a metric, include receiving a rule defining one or more text strings; determining a set of transactions based on a user attribute; determining a first subset of transactions; determining a second subset of transactions; generating a first categorical distribution based on each transaction of the first subset of transactions being associated with a transaction description containing at least one text string of the one or more text strings; calculating a first unity metric based on the first categorical distribution; generating a second categorical distribution based on each transaction of the second subset of transactions being associated with a transaction description that does not contain a text string of the one or more text strings; calculating a second unity metric based on the second categorical distribution; determining a reliability metric for the rule; and providing the reliability metric.

Abstract: Certain aspects of the present disclosure provide techniques for placing targeted messages in communications within a software application using machine learning models. An example method generally includes retrieving, from a repository, a data set of targeted messages. For each respective targeted message in the data set of targeted messages, an effectiveness score for a party associated with the respective targeted message, a distance score between the party associated with the respective targeted message and a host party, and a match score between the party associated with the respective targeted message and the host party. Based on the effectiveness score, the distance score, and the match score for each respective targeted message in the data set of targeted messages, a message is selected to be included in one or more communications by the host party. The one or more communications including the selected message are generated and output for transmission.

Abstract: Certain aspects of the present disclosure provide techniques for adaptively reducing the bit size of features in a training data set used to train a machine learning model. An example method generally includes receiving a data set to be used in training a machine learning model and a definition of the machine learning model to be trained. A reduced number of bits to represent features in the data set is determined based on values of each feature in the data set and the definition of the machine learning model. A reduced bit-size data set is generated by reducing a bit size of each feature in the data set according to the reduced number of bits, and the reduced bit-size data set is encrypted using a homomorphic encryption scheme. A machine learning model is trained based on the encrypted reduced bit-size data set.

Abstract: A method including generating, by a state engine from data describing behaviors of users in an environment external to the state engine, an executable process. An agent executes the executable process by determining, from the data describing the behaviors of the users, a problem of at least some of the users, and selects, based on the problem, a chosen action to alter the problem. At a first time, a first electronic communication describing the chosen action to the at least some of the users is transmitted. Ongoing data describing ongoing behaviors of the users is monitored. A reward is generated based on the ongoing data to change a parameter of the agent. The parameter of the agent is changed to generate a modified agent. The modified agent executes the executable process to select a modified action. At a second time, a second electronic communication describing the modified action is transmitted.

Abstract: A method of determining whether a user has a self-control problem. A computing system receives, from a plurality of financial institutions associated with a target user, a plurality of transactions associated with the target user. The computing system groups the plurality of transactions into a category or subcategory based on transaction data associated with each respective transaction. The computing system determines, based on the plurality of transactions, that the target user has a self-control problem. The computing system, responsive to determining that the target user has the self-control problem, generates an alert or recommendation to the target user. The alert or recommendation notifies the target user of the self-control problem.

Abstract: A method and system identify characteristics of transaction description strings. The method and system extracts time data and location data from transaction description strings. The method and system generate estimated time data and location data for transaction strings that lack time data and location data by analyzing the time data and location data extracted from other transaction description strings. The method and system generate a user profile based on the estimated time data and estimated location data.

Abstract: A method may including obtaining a voice transcript corpus and a chat transcript corpus, extracting voice transcript sentences from the voice transcript corpus and chat transcript sentences from the chat transcript corpus, encoding, by a series of neural network layers, the voice transcript sentences to generate voice sentence vectors, encoding, by the series of neural network layers, the chat transcript sentences to generate chat sentence vectors, determining, for each voice sentence vector, a matching chat sentence vector to obtain matching voice-chat vector pairs, and adding, to a parallel corpus, matching voice-chat sentence pairs using the matching voice-chat vector pairs. Each of the matching voice-chat sentence pairs may include a voice transcript sentence and a matching chat transcript sentence. The method may further include training a disfluency remover model using the parallel corpus.

Abstract: Certain aspects of the present disclosure provide techniques for performing inferences in a distributed computing environment. An example method generally includes receiving a request to perform an inference with respect to a set of input data. One or more client devices are selected for use in performing the inference with respect to the set of input data. A request to perform the inference is transmitted to the selected one or more client devices. The request generally includes an anonymized, vectorized version of the set of input data such that the selected one or more client devices are to perform the inference based on anonymized data. An inference response is received from each of the selected one or more client devices.

Abstract: Systems and methods for securely verifying integrity of application responses are disclosed. One example method includes receiving, from a client, an application encrypted in accordance with a fully homomorphic encryption (FHE) algorithm, generating, with a trained machine learning model associated with the FHE algorithm, a plurality of first application labels, each first application label indicating a true or false response associated with the application, inverting a randomly selected portion of the plurality of first application labels, generating a first randomly sorted list including the plurality of first application labels, transmitting the first randomly sorted list to the client, receiving a first decrypted list from the client, performing a validation of at least the first decrypted list, the validation based at least in part on the plurality of first application labels, and in response to the validation being successful, providing the client with a response to the application.

Abstract: This disclosure relates to systems and methods for constructing a customized debt reduction plan for a user. In some implementations, a customized debt reduction system obtains a plurality of financial attributes of the user and a plurality of other users, where the plurality of financial attributes are indicative of credit card debt, and identifies users from the plurality of other users who successfully repaid their credit card debt based on their respective financial attributes and one or more repayment techniques that resulted in successful repayment of their credit card debt. The customized debt reduction system correlates the plurality of financial attributes of the user with the plurality of financial attributes of a number of the identified users and determines a personalized score for the user, using a trained machine learning model, based on the correlation to determine a customized debt reduction plan for the user based on the personalized score.

Abstract: Systems, methods, and media for the automated removal of private information are provided herein. In an example implementation, a method for automatic removal of private information may include: receiving a transcript of communication data; applying a private information rule to the transcript in order to identify private information in the transcript; tagging the identified private information with a tag comprising an identification of the private information; applying a complicate rule to the tagged transcript in order to evaluate a compliance of the transcript with privacy standards; removing the identified private information from the transcript to produce a redacted transaction; and storing the redacted transcript.

Abstract: Certain aspects of the present disclosure provide techniques for providing an indicator to an inexperience business owner to enter transactions into an accounting system. Transaction data from applications is grouped into two groups based on experience of each group. Transaction data from an experienced group will have transactions with accounting professionals, while an inexperienced group may not, or have fewer such transactions. A transaction is decomposed into at least two transaction events, each with showing two accounts per transaction event, as per double entry accounting rules. Probability values for each transaction event are determined based on the accounts involved: probability value=p(account_1=account_type_1, credit/debit amount, account_2=account_type_2, credit/debit amount|previous event account_3=account_type_3, credit/debit amount, account_4=account_type_4, credit/debit amount).

Abstract: Certain embodiments of the present disclosure provide techniques for detecting anomalous activity in a computing system. The method generally includes receiving a request to perform an action in a computing system. The request is added to a historical time-series data set. A portion of the historical time-series data set is selected for use in determining whether the received request is an anomalous request, and a set of previously identified outliers are removed from the selected portion of the historical time-series data set. An anomaly score is calculated based on a statistical analysis of the received request and the selected portion of the historical time-series data set, wherein the anomaly score comprises a predicted number of operations executed to isolate the received request from the selected portion of the historical time-series data set. One or more actions are taken to process the received request based on the calculated anomaly score.

Abstract: Systems and methods for asset-centered expense forecasting.

Abstract: Aspects of the present disclosure provide techniques for detecting sensitive information. Embodiments include determining a first likelihood that a record contains at least a given type of sensitive information using a first detection technique that involves providing one or more inputs to a machine learning model based on the record and receiving the first likelihood as an output from the machine learning model based on the one or more inputs. Embodiments include determining a second likelihood that the record contains at least the given type of sensitive information using a second detection technique comprising a search of the record. Embodiments include applying a policy to determine whether the record contains sensitive information based on the first likelihood and the second likelihood. Embodiments include performing one or more actions based on whether the record contains sensitive information.

Abstract: A computer-implemented method is provided to preforming re-categorization of financial transactions. The re-categorization is implemented by a server computing device which receives the financial transactions associated with a merchant and a first category. The server computing device receives user inputs that are each associated with re-categorizing a financial transaction from the first category to one or more other categories. Based at least in part on a count of the first category and counts of the one or more other categories, the server computing device determines a set of normalized ratios for the first category and the one or more other categories with respect to a total number of respective financial transactions received. The server computing device determines a second category corresponding to a minimum value in the set of the normalized ratios for each financial transaction associated with the merchant.