Abstract: Provided are methods and systems for improved data management, data analysis, and processing. A computing device may receive one or more global queries. Each of the global queries may be associated with one or more local components, such as individual nodes of a cloud network. The computing device may determine one or more indexlets associated with each local component. The computing device may then generate query results for the one or more global queries using a global query plan and the one or more indexlets.

Abstract: An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.

Abstract: Provided are methods and systems comprising receiving a plurality of data tables, wherein each data table comprises at least one row, generating a first handle for a first value in a table of the plurality of tables, wherein the first handle comprises an indication of whether a row in each of the plurality of tables is associated or not associated with the first value, and performing one or more operations on the first handle.

Abstract: The present disclosure relates to computer implemented methods and systems for data management, data analysis, and processing. The disclosed methods and systems can incorporate external data analysis into an otherwise closed data analysis environment.

Abstract: Described herein are machine learning methods and systems for application programming Interface (API) management. One or more machine learning-based models, such as a neural network, may be trained to provide a prediction(s) that an API request is likely to succeed (e.g., not cause the API to crash) or to fail (e.g., cause the API to crash, freeze, etc.). The one or more machine learning-based models may be trained using historical API requests that were successful and historical API requests that are not successful. Various aspects of the API requests, as well as system properties associated with the machine(s) that executes/processes the historical API requests, may be used as well when training the one or more machine learning-based models.

Abstract: Provided are methods and systems comprising determining one or more relationships between a plurality of data sets, determining a score for each of the one or more relationships, generating a graphical data set object for each of the plurality of data sets, classifying each graphical data set object as connected or unconnected based on the score for each of the one or more relationships, generating a graphical connector object between connected graphical data set objects, and outputting the connected graphical data set objects with corresponding graphical connector objects and the unconnected graphical data set objects.

Abstract: In an aspect, provided is a method comprising monitoring one or more data analysis sessions, determining, based on the monitoring, a common data analysis technique performed across common data analysis sessions, identifying the common data analysis technique as a precedent, and providing the precedent to a precedent engine.

Abstract: Technologies are provided for detection and mitigation of high-risk online activity. The detection and mitigation can be implemented in real-time. In some embodiments, a computing system can determine that a risk assessment for an online activity is unavailable from an in-memory storage. The computing system can obtain the risk assessment for the online activity from a second computing system configured to apply a prediction model to data defining the online activity. The risk assessment can comprise a risk score and a risk category. The computing system can update the in-memory storage to incorporate the data and the risk assessment, and can determine that the risk assessment is indicative of the online activity being high-risk activity. The computing system can then cause denial of access to a computing platform to a user device associated with the online activity.

Abstract: Technologies are provided for database modification using a script component. In some embodiments, a method comprises executing, by a computing system comprising at least one processor, a script component comprising one or more functions to transform a database. The method also includes modifying, by the computing system, the database based on at least one transformation defined by the one or more functions in response to executing the script component.

Abstract: Set analysis may be used to determine the best data analysis model(s) (e.g., data charts, data tables, data graphs, data maps, graphical objects, key performance indicators (KPIs), etc.) for representing the results of an undetermined query (e.g., an imprecise query, an undefined query, an incomplete query, a partially expressed query, a portioned query, etc.).

Abstract: Systems and methods for processing queries are described herein. As an example, a query may comprise an expression. Based on the expression, one or more indexlets may be determined. Using the one or more indexlets, a result of the expression may be determined.

Abstract: Provided are methods and systems comprising receiving a plurality of data tables, wherein each data table comprises at least one row, generating a first handle for a first value in a table of the plurality of tables, wherein the first handle comprises an indication of whether a row in each of the plurality of tables is associated or not associated with the first value, and performing one or more operations on the first handle.

Abstract: Provided are methods and systems for traversing a data model with a plurality of workers to generate a plurality of virtual records for use in evaluating an expression by a plurality of aggregators. Each aggregator may receive a respective virtual record and evaluate a hypercube function and determine a respective hash based on the respective virtual record. The virtual records based on the respective hash values of the respective virtual records may be stored by the plurality of aggregators.

Abstract: In an aspect, provided is a method comprising receiving a data model, partitioning a first table in the data model into a first plurality of blocks of rows, generating a first plurality of indexlets, the first plurality of indexlets comprising a first plurality bidirectional indexes, each of the first plurality of bidirectional indexes being generated based on a corresponding one of the first plurality of blocks of rows.

Abstract: Provided are methods comprising receiving a query for information from a database, determining particular data element types and data element values that are the subject of the query, instantiating a query data structure containing the data element types and the data element values that are the subject of the query, identifying records within the database that contain one or more data element types and/or data element values that are included in the query data structure, and instantiating a results data structure comprising information relating to the identified records.

Abstract: Methods and systems for improved analytics are provided. A Software as a Service (SaaS) platform may be implemented as a distributed system using a public infrastructure, such as a public cloud, and an on-premises infrastructure, such as a private cloud. A control plane for the SaaS platform may reside in the public cloud, while a data plane for the SaaS platform may reside in the on-premises private cloud.

Abstract: Provided are methods and systems comprising determining one or more relationships between a plurality of data sets, determining a score for each of the one or more relationships, generating a graphical data set object for each of the plurality of data sets, classifying each graphical data set object as connected or unconnected based on the score for each of the one or more relationships, generating a graphical connector object between connected graphical data set objects, and outputting the connected graphical data set objects with corresponding graphical connector objects and the unconnected graphical data set objects.

Abstract: Methods and systems for representing data are disclosed. An example method can comprise providing a first representation of data and receiving a request to change resolution of the data. An example method can comprise, transforming, based on at least one wavelet function, the data to at least one of reduced data or expanded data. An example method can comprise providing a second representation of the data based on at least one of the reduced data or expanded data.

Abstract: A technology is described for automating deployment of a machine learning model. An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.

Abstract: In an aspect, provided is a method comprising receiving, at a master node, capability information associated with a plurality of worker nodes, receiving, at the master node, an indexation request, and in response to the indexation request, distributing one or more tasks to the plurality of worker nodes based on the respective capability information, wherein the one or more tasks relate to generating a plurality of indexlets.