Abstract: Systems, methods, and computer-readable media for generating responses to natural-language queries regarding items in unstructured documents are disclosed. An application instance that includes one or more machine learning models receives, from a subscriber computing system, a query and document comprising unstructured data. Based on the unstructured data, the application instance generates a searchable data structure using a machine learning model. A query response is generated by performing a semantic search on the searchable data structure. The query response is provided to a target application.

Abstract: The techniques disclosed herein enhance the efficiency and functionality of directory systems. This is accomplished by augmenting a primary table with an extended table for storing properties of an associated entity (e.g., a user, a company). A table serves to organize directory data and comprises rows and columns. Each row of the primary table stores an entity with each column storing an associated property. In contrast, the primary table is configured with an extended table in which each row of the extended table stores a property for an associated entity while each column stores additional information for the property such as timestamps and metadata. Storing specific properties in the extended table eliminates empty spaces in the primary table thereby reducing the volume of stored data. Moreover, by including additional data for properties, the extended table enables property-specific features such as search, synchronization, extensibility, and lifecycle management.

Abstract: Methods and systems for recommending safe vehicle seats and/or predicting the replacement time of vehicle seats. The systems and methods may include (1) training a machine learning model using a set of characteristics of previously recommended vehicle seats to generate a vehicle seat recommendation score for one or more vehicle seats; (2) receiving a request for a vehicle seat recommendation; (3) receiving input data; (4) determining a set of characteristics of the input data; (5) applying the set of characteristics of the input data to the machine learning model to generate a vehicle seat recommendation score for the one or more vehicle seats; (6) ranking the one or more vehicle seats by vehicle seat recommendation score to generate a vehicle seat recommendation list; and/or (7) presenting the vehicle seat recommendation list to a client device.

Abstract: Methods and systems for recommending safe vehicle seats and/or predicting the replacement time of vehicle seats. The systems and methods may include (1) training a machine learning model for predicting a replacement time of one or more vehicle seats using (i) a set of characteristics of a previously recommended vehicle seat and/or (ii) replacement times for the previously recommended vehicle seat; (2) receiving input data related to a previously recommended vehicle seat; (3) determining a set of characteristics of the input data; (4) applying the set of characteristics of the input data to the machine learning model to determine the predictive replacement time for replacing the one or more vehicle seats; and/or (5) providing an indication of the predictive replacement time for display on a client device.

Abstract: A system and method model a time series from missing data by imputing missing values, denoising measured but noisy values, and forecasting future values of a single time series. A time series of potentially noisy, partially-measured values of a physical process is represented as a non-overlapping matrix. For several classes of common model functions, it can be proved that the resulting matrix has a low rank or approximately low rank, allowing a matrix estimation technique, for example singular value thresholding, to be efficiently applied. Applying such a technique produces a mean matrix that estimates latent values, of the physical process at times or intervals corresponding to measurements, with less error than previously known methods. These latent values have been denoised (if noisy) and imputed (if missing). Linear regression of the estimated latent values permits forecasting with an error that decreases as more measurements are made.

Abstract: A computer-implemented method includes: identifying, from first and second data, interventions common to a target unit and one or more of a plurality of donor units as filtered donor units, the first data corresponding to the target unit under one or more interventions, the second data corresponding to the plurality of donor units each under one or more interventions; identifying, from the first data, third data corresponding to the target unit under the common interventions; identifying, from the second data, fourth data corresponding to the filtered donor units under the common interventions; identifying, from the second data, fifth data corresponding to the filtered donor units under a subject intervention; generating, from the third and fourth data, a learned model representing to a relationship between the target unit and the filtered donor units; applying the learned model to the fifth data to generate the synthetic data; and outputting the synthetic data.

Abstract: A system and method model a time series from missing data by imputing missing values, denoising measured but noisy values, and forecasting future values of a single time series. A time series of potentially noisy, partially-measured values of a physical process is represented as a non-overlapping matrix. For several classes of common model functions, it can be proved that the resulting matrix has a low rank or approximately low rank, allowing a matrix estimation technique, for example singular value thresholding, to be efficiently applied. Applying such a technique produces a mean matrix that estimates latent values, of the physical process at times or intervals corresponding to measurements, with less error than previously known methods. These latent values have been denoised (if noisy) and imputed (if missing). Linear regression of the estimated latent values permits forecasting with an error that decreases as more measurements are made.

Abstract: A system and method model a time series from missing data by imputing missing values, denoising measured but noisy values, and forecasting future values of a single time series. A time series of potentially noisy, partially-measured values of a physical process is represented as a non-overlapping matrix. For several classes of common model functions, it can be proved that the resulting matrix has a low rank or approximately low rank, allowing a matrix estimation technique, for example singular value thresholding, to be efficiently applied. Applying such a technique produces a mean matrix that estimates latent values, of the physical process at times or intervals corresponding to measurements, with less error than previously known methods. These latent values have been denoised (if noisy) and imputed (if missing). Linear regression of the estimated latent values permits forecasting with an error that decreases as more measurements are made.

Abstract: A system and method model a time series from missing data by imputing missing values, denoising measured but noisy values, and forecasting future values of a single time series. A time series of potentially noisy, partially-measured values of a physical process is represented as a non-overlapping matrix. For several classes of common model functions, it can be proved that the resulting matrix has a low rank or approximately low rank, allowing a matrix estimation technique, for example singular value thresholding, to be efficiently applied. Applying such a technique produces a mean matrix that estimates latent values, of the physical process at times or intervals corresponding to measurements, with less error than previously known methods. These latent values have been denoised (if noisy) and imputed (if missing). Linear regression of the estimated latent values permits forecasting with an error that decreases as more measurements are made.