Abstract: Systems, methods, and apparatuses for managing deposits and payments for variable weighted and variable priced agricultural products are disclosed. In an example, an apparatus includes a memory device configured to store a data structure that includes product information of at least one vendor, wherein the product information includes information of variable weighted and variable priced agricultural products, including a product description, at least one price per unit of the variable weighted and variable priced agricultural products, and an estimated range of units for the variable weighted and variable priced agricultural products. The apparatus further includes an interface controller configured to provide interactive interfaces for buyer devices or vendor devices to enable at least one vendor or at least one buyer to display, sell, or buy the variable weighted and variable priced agricultural products, and a processor in communication with the memory device and the interface controller.

Abstract: Systems, methods, and computer readable media related to determining one or more responses to provide that are responsive to an electronic communication that is generated through interaction with a client computing device. For example, determining one or more responses to provide for presentation to a user as suggestions for inclusion in a reply to an electronic communication sent to the user. Some implementations are related to training and/or using separate input and response neural network models for determining responses for electronic communications. The input neural network model and the response neural network model can be separate, but trained and/or used cooperatively.

Abstract: Methods, systems, and devices supporting epsilon (?)-closure for frequent pattern (FP) analysis are described. Some database systems may analyze data sets to determine FPs. In some cases, the FP set may include a large number of semi-redundant patterns, resulting in significant memory or processing overhead. To reduce the redundancy of these patterns, the database system may implement pre-configured or dynamic threshold occurrence differences (e.g., ? values) to test against related patterns. For example, the database system may calculate the difference between the data objects covered by a sub-pattern and a super-pattern (e.g., where the super-pattern includes all the same data attributes of the sub-pattern, plus one additional attribute). This difference may be compared to a corresponding ? value, and if the difference is less than the ? value, the database system may remove one of the patterns (e.g., the sub-pattern) from the set of valid FPs to limit redundancy.

Abstract: A method for providing a performance result in a computer video game application is provided. Target user performance data of a target control object controlled by a target user and additional performance data of at least one additional control object in an execution process of a target scene of the computer video game application are obtained. The performance result of the target control object in the execution process of the target scene is determined based on (i) the target user performance data and (ii) a relationship between the target user performance data and the additional performance data. The performance result is transmitted to a terminal of the target control object.

Abstract: In one embodiment, a method includes generating, for each of a plurality of first entities of an online social network, a plurality of candidate keywords associated with the first entity by extracting a plurality of n-grams from a plurality of content objects associated with the first entity. The method also includes identifying, from the plurality of first entities, responsive to determining that a second entity of the online social network is interacting with a search interface of the online social network, a plurality of entities associated with the second entity based at least in part on a search history of the second entity. The method also includes sending, to a client system of the second entity, for each of the plurality of identified entities associated with the second entity, instructions for presenting one or more suggested queries comprising one or more of the generated candidate keywords associated with the identified entity.

Abstract: An image query method and apparatus, where the method may include obtaining a global feature of a query image and an attributive feature of the query image, where the attributive feature is a feature used to describe a specific attribute area in the query image, querying an image library using the global feature to obtain a first image set that includes at least one image, where an image included in the image library includes the attributive feature, selecting at least one image whose similarity of the attributive feature to the attributive feature of the query image is greater than a preset threshold from the first image set, and setting the at least one selected image as a second image set. Hence, the method may improve image query efficiency.

Abstract: Embodiments of the present disclosure provide a method and apparatus for optimizing a tag of a point of interest. The method includes: acquiring a set of points of interest and a set of tags of points of interest in the set of points of interest; generating a point of interest-tag matrix based on the set of points of interest and the set of tags of points of interest in the set of points of interest; extracting a feature of a point of interest-tag in the point of interest-tag matrix; inputting the feature of the point of interest-tag in the point of interest-tag matrix into a pre-trained ternary self-adaptive collaborative learning model, to obtain a point of interest-tag score matrix; and optimizing the set of tags of points of interest in the set of points of interest based on the point of interest-tag score matrix.

Abstract: A vehicle anomaly detection server includes: a communicator that communicates with a vehicle to receive a log of an in-vehicle network in the vehicle; a processor; and a memory including at least one set of instructions that, when executed by the processor causes the processor to perform operations including: selecting, when information indicating that an anomaly is occurring to a first vehicle among vehicles is obtained by the processor, an anomaly-related vehicle from among the vehicles based on the anomaly, the first vehicle being the vehicle that communicates with the communicator; transmitting, to the anomaly-related vehicle via the communicator, a first request to transmit a log of an in-vehicle network in the anomaly-related vehicle; and determining whether an anomaly is occurring to the anomaly-related vehicle, based on information indicated by the log transmitted from the anomaly-related vehicle and received by the communicator.

Abstract: A method, system and computer program product are disclosed for searching for data. In one embodiment, the invention provides a method comprising identifying a query and a search scope including a set of specified entities; and for each of these entities, estimating a number of documents that would be identified in a search through the entity to answer the query. On the basis of this estimating, a subset of the entities is formed. The query and this subset of entities are sent to a search engine to search the subset of entities to answer the query. In one embodiment, the estimating includes collecting statistical information from queries to build up a historical cache using heuristics or machine learning techniques, wherein the query includes a key word and a scope, and the historical cache contains a maximum number of returned results for an entity given the queries executed.

Abstract: A computing device and method for contextual access, including the computing device to implement a traversal of a property graph of data. The traversal includes using contextual information to determine whether to grant access to vertices of the property graph and to outgoing edges of the vertices.

Abstract: Techniques disclosed herein provide more efficient and more relevant item recommendations to users in large-scale environments in which only positive interest information is known. The techniques use a rank-constrained formulation that generalizes relationships based on known user interests in items and/or use a randomized singular value decomposition (SVD) approximation technique to solve the formulation to identify items of interest to users in an efficiently, scalable manner.

Abstract: An estimation method executed by a computer, the estimation method includes estimating a fouling degree of a target ship based on an accumulation period since a most recent maintenance on the target ship; selecting, as training data, one piece of data that has a fouling degree that resembles the estimated fouling degree, from among a plurality of pieces of data, when generating a machine learning model for estimating an amount of fuel consumption due to navigation; and generating the machine learning model based on the selected training data.

Abstract: Systems, methods, and computer-readable media for representing data via a multi-structured table are disclosed. The systems and methods may involve maintaining a main table having a first structure and containing a plurality of rows; receiving a first electronic request for establishment of a first sub-table associated with the main table, wherein the electronic request includes column heading definitions and wherein the column heading definitions constitute a second structure; storing the second structure in memory as a default sub-table structure; associating the first sub-table with a first row in the main table; receiving a second electronic request for association of a second sub-table with a second row of the main table; performing a lookup of the default sub-table structure following receipt of the second electronic request; applying the default sub-table structure to the second sub-table.

Abstract: Methods, systems, and computer readable medium for improving opt-out compliance are disclosed. A method includes identifying an opportunity to transmit a digital component to a client device that is identified by a given unique identifier, accessing a database, identifying, within the database and based on the accessing, an opt-out timestamp specifying when a given user corresponding to the given unique identifier was presented the opt-out opportunity, determining, whether the timestamp indicates that the user was presented with the opportunity within a specified amount of time, and processing the opportunity by submitting the opportunity to transmit the digital component to third party digital component sources in response to determining that the given user was presented with the opportunity within the specified amount of time, or refraining from submitting the opportunity in response to determining that the given user was not presented with the opportunity within the specified amount of time.

Abstract: A method of simulating avatar attention in a virtual environment includes, for a given avatar within the environment; periodically calculating the respective interest value of a plurality of elements in the virtual environment in dependence upon one or more factors, where at least one of said factors is evaluated responsive to a relationship between the respective element and that given avatar, selecting the element with the highest calculated interest value, and causing a representation of that given avatar's eyes to point at the selected element within the virtual environment.

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises receiving data associated with an initiation of a process; dynamically determining a sequence of a plurality of sub-processes associated with the received data based the initiated process; dynamically prioritizing the determined sequence of the plurality of sub-processes associated with the received data based on an analysis of eligible variations and a pre-stored database of variations associated with each respective sub-process; dynamically performing the process based the prioritized sequence of the plurality of sub-processes associated with the received data; and transmitting a result of the dynamic prioritization of the determined sequence of a plurality of variations to a user interface of another computing device.

Abstract: A method for generating recommendations involves selecting a first platform message, making a first determination that the first platform message is potentially associated with a plurality of topics including a first topic and a second topic, obtaining additional information associated with the first platform message including at least one of information about an account that authored the first platform message and information about third party accounts engaging with the first platform message, making a second determining that the first platform message is associated with the first topic using the plurality of topics and at least a portion of the additional information, wherein the first topic is an initial classification of the first platform message, generating a recommendation for at least one account based on the second determination, and providing the recommendation to at least one account.

Abstract: A method comprising receiving a request from a first user to generate an employee dataset for a second user associated with one or more attributes; generating an instruction configured to be transmitted to a plurality of network nodes associated with a blockchain to receive a latest valid blockchain associated with one or more users; upon receiving the latest valid blockchain, generating a score corresponding to each user based on the data within each user's latest valid blockchain and based on a scoring algorithm received from the computing device associated with the first user; generating a graphical user interface comprising a plurality of fields configured to display data associated the one or more users comprising each user's score; upon displaying, the graphical user interface on the first computing device, receiving a selection of users; and generating, a notification to the selected users comprising identification information regarding the first user.

Abstract: Disclosed is a method and apparatus for capturing, collecting, and distributing event information displayed on signs. The method may include capturing, by a mobile device, an image of a sign that displays information for an event. The method may also include extracting information for the event from the captured image of the sign, and determining a location of the mobile device when the image of the sign was captured. Furthermore, the method may include uploading, to a server, a time when the image was captured, the information for the event extracted from the captured image, a location of the event determined from extracted event information, a location of the sign, or a combination thereof.

Abstract: A reader platform system generates a display of a document that is formed based on a tree structure from a structured document template with an idea type attribute and content of a supporting idea type attribute that is based on the idea type attribute. The idea type attribute and the content of the supporting idea type attribute are validated based on taxonomy rules for the structured document template. The reader platform system receives a reader feedback of the document via a feedback user interface of the display. The profile of a reader of the document and the profile of an author of the document are updated based on the reader feedback. The feed of another reader related to the reader of the document is updated based on the updated profile of the reader of the document.

Abstract: A computer-implemented system and method for updating user interest profiles is provided. An interest profile having a mapping of interest categories and interest scores for each interest category is obtained. User generated items are identified from online profiles and a portion of the user generated items are associated with a time stamp. A similarity mapping is performed by comparing each user generated item with each interest category. An interest index score is determined for each interest category based on one of the user generated items compared. A threshold is applied to the interest index scores for each category. The interest score associated with one such category in the mapping is replaced with the interest index score, when the interest index score for that category is above the threshold. The interest profile is adjusted by applying a decay to those interest index scores associated with time stamps determined for the categories.

Abstract: A computer system for providing digital advertiser referrals comprising a third party referral provider operable to maintain a store of digital referral objects, each digital referral object associated with an advertiser for referral to a consumer. The third party referral provider being further operable to engage with a consumer while the consumer is accessing digital content on a publisher site subscribing to the third party referral provider by way of a computer presentation interface, such that once the consumer has engaged with the third party referral provider, the third party referral provider is operable to refer one or more of the advertisers to the consumer through presentation of an associated digital referral object on the presentation interface.

Abstract: Embodiments for managing natural language user input are provided. Natural language input is received from a user utilizing a computing node. The natural language input is analyzed. The analyzing of the natural language input includes attempting to identify at least one of an intent associated with the natural language input, an entity associated with the natural language input, and context data associated with the natural language input. The natural language input is evaluated against a pre-trained model based on the analyzing of the natural language input. A quality score for the natural language input is calculated based on the evaluating of the natural language input. An action is caused to be performed utilizing the computing node based on the calculated quality score.

Abstract: A computerized method and system for teaching foreign language. Users can define flashcards for study words and words in study sentences and select associated images to be shown with the flashcards during review. An improved method and system for identifying and searching for images to show is provided. Improved methods for presenting flashcards for words with multiple definitions and improved database architecture for storing flashcard data for plural users is also provided.

Abstract: A different combination of multiple portions of a content item is selected for display to each of multiple sets of users of an online messaging application. The different combination of portions of the content item is sent for display to the corresponding set of users within a user interface of the online messaging application in association with information identifying a set of message threads in which each user is participating. A request to view the entire content of the content item is then received from a subset of each of the sets of users and a performance metric associated with each combination of portions of the content item is tracked based on the received request. Based on the performance metric, a performance of each portion of the content item is evaluated and used to select an optimal combination of the portions of the content item.

Abstract: Sentence pairs can be filtered using dual monolingual conditional cross-entropy filtering. The filtered sentence pairs can be used to train a model for performing a language processing task, such as machine translation.

Abstract: Embodiments are provided that facilitate training and utilization of specially configured multi-armed bandit model(s). Such embodiments configure multi-armed bandit model(s) to provide selected network asset scoring model(s) from a network asset scoring model set and/or a selected data tagged network asset set from a set of data tagged network asset sets. Such selections are performable for a particular user profile, for example to perform accurate and/or efficient process(es) for provision of network asset data object(s) to the user profile(s). Some embodiments access enterprise network interaction data, access a set of data tagged network asset sets, train a multi-armed bandit model to provide a selected network asset scoring model and a selected data tagged network asset set, and provides one or more network asset data objects based on the selected network asset scoring model and the selected data tagged network asset set.

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method as described herein are directed to a Personalized Article Engine that generates respective prediction models for each article in a plurality of candidate articles in a social network system. The Personalized. Article Engine generates a respective article score according to each article's prediction model and at least one feature of a target member account. The Personalized Article Engine generates a plurality of output scores based on combining each respective article score with a corresponding article's global model score. The Personalized Article Engine ranks the output scores to identify a subset of candidate articles relevant to the target member account.

Abstract: Systems, methods, and products, are described herein for self-curative computer process automates. Execution of an automate for testing of an application is initiated. The application includes a plurality of user interface elements, each user interface element having a plurality of properties. A change to a user interface element of the plurality of user interface elements during the execution of the automate is identified based on a change to at least one property of the plurality of properties associated with the user interface element. A modification to the plurality of properties associated with the user interface element is generated based on a ranking of the plurality of user interface elements, the generated modification curing the change to the at least one property. The generated modification is caused to display on a graphical user interface for further acceptance of the generated modification to the automate.

Abstract: Methods, systems, and devices supporting differential support for frequent pattern (FP) analysis are described. Some database systems may analyze data sets to determine FPs of data attributes within the data sets. However, if data distributions for different types of data attributes vary greatly, more frequent data attribute types may skew the FPs away from the less frequent types. To reduce the noise of common attributes while maintaining sensitivity to the less common attributes, the database system may implement multiple minimum support (e.g., frequency) thresholds. For example, the database system may adaptively categorize the different data attribute types into data categories based on their distributions and may dynamically determine support thresholds for the categories. Using different minimum support thresholds for different data categories allows the system to filter out data attribute patterns based on the distributions of the data attribute types in the pattern.

Abstract: A storage device includes a non-volatile memory (NVM) and a storage device controller. The storage device controller includes a NVM interface coupled to the NVM and one or more task queues. The storage device controller is operable to pick a task from one or more queues of the storage device. The task is parsed based upon presence of an extra header segment with an execution condition. The task without the extra header segment is sent to execution. Whether the execution condition of the extra header segment of the task is met is determined. The task with the execution condition met is sent to execution. The task with the execution condition unmet is postponed.

Abstract: Methods, systems and computer program products are described herein that enable data workload optimization through “what-if” modeling of indexes and index recommendation. In an example aspect, a system is configured to accept a workload in the form of a plurality of data queries, extract indexable columns from the queries, generate candidate indexes from the indexable columns, select and then build the best candidate indexes. Furthermore, the system may receive a query, generate a query plan for the query configured to use one or more of the built candidate indexes, and execute the query plan to generate a query result.

Abstract: Implementations described herein disclose an informed join recommendation system that allows users to make informed decision about joining various information sources such as a feed, an application, a group, a blog, a news source, etc., based on an activity grade of the information sources. The informed join recommendation system analyzes information dissemination activity of information sources over a predetermined time period to determine an activity grade of the information source, and in response to the request from a user to join the information source, provides the user the activity grade of the information source.

Abstract: A system and method for recommending matches between persons are provided. Data processing is performed using artificial intelligence technology. A supervised machine learning engine is trained from empirical data about existing relationships which have been evaluated as to quality of the relationships. Quality of candidate relationships is calculated as an output of the supervised machine learning engine when provided input data of attributes of two candidate persons. Likelihood of a successful relationship between two candidate persons is predicted by comparing the calculated quality of the candidate relationship against a threshold. The prediction in this learning task may be made by a neural network. A user is notified of a candidate match that is likely to become a successful relationship.

Abstract: Aspects of the technology enable selective updating of search results and refreshing an entire webpage while minimizing the amount of information transmitted between a client device and a web server. The approach involves determining whether a change in a detected location of the client device would alter the search results or other portions of the webpage. Current and previously received location information is analyzed and compared against a threshold value, which indicates whether there would be a change to location-relevant information. A location signal is provided to the client device based on this analysis, which is used to determine whether to refresh the received search results, to refresh an entire webpage, or to not refresh either the received search results or the entire webpage.

Abstract: Methods, systems, and apparatus for receiving a query image, receiving one or more entities that are associated with the query image, identifying, for one or more of the entities, one or more candidate search queries that are pre-associated with the one or more entities, generating a respective relevance score for each of the candidate search queries, selecting, as a representative search query for the query image, a particular candidate search query based at least on the generated respective relevance scores and providing the representative search query for output in response to receiving the query image.

Abstract: Users may consume and/or share information through various types of content items. For example, user may post a family photo through a social network, create a running blog through a microblogging service, etc. Because users may be overwhelmed by the amount of available content items, it may be advantageous to recommend content items, such as blogs to follow, to users. Accordingly, inductive matrix completion is used to evaluate user interactions with content items (e.g., a user following a blog), content item features (e.g., text and/or images of a blog is evaluated to identify a topic of the blog), and/or user features (e.g., a user liking or reblogging a blog, user demographics, user interests, etc.) to determine whether to recommend a content item to a user. Additionally, graph proximity is used to recommend content items based upon weights of edges connecting user nodes to content item nodes within a directed graph.

Abstract: A system and method analyzes computer actions to identify computer-based processes (e.g. computer-user interactions) which are automation candidates. A data gathering process executed by a processor on a computer may collect low-level user action information or items, each low-level user action information or item including for example an input type description, a user name, and screen window information. At a computer sequential pattern mining may be applied to determine a set of subprocesses, each subprocess including a series of low-level user actions, each user action associated with a user action vector, and each subprocess associated with a subprocess vector generated from user action vectors associated with (typically generalized) low-level user actions comprised in the subprocess. The subprocess vectors may be grouped or clustered to create processes. For each process, an automation score may be calculated using the actions in the subprocesses in the process.

Abstract: Product recommendations are selected according to a model. Product recommendations may be annotated with rules of the model used to select the products. A user may modify the model and be provided with a URL and a cookie associated with the modified model. Subsequent requests or the URL and presenting the cookie are processed using the modified model. A context may be associated with the cookie and modified by the user to observe performance of the model for the context. An interface may permit a user to specify rules for the model or otherwise model its behavior. User interactions with a website result in recommendations according to the model. A journey is recorded that records content, recommendations, and parameters of the model corresponding to the recommendations. The journeys of users may be filtered and visually presented to a user.

Abstract: A system configured to rank and display candidate documents for human annotation task. The system executes instructions to receive a human annotation of a first unannotated document in a list of documents from a document set; update an annotated entities and corresponding entity types set based on the human annotation of the document from the document set; perform auto-mapping of annotated entities to corresponding entity types on a remaining set of documents in the document set based on the updated annotated entities and corresponding entity types set; calculate a score for each document in the remaining set of documents based on the auto-mapping of annotated entities; and update an order of the remaining set of documents being displayed for human annotation based on the calculated score for each document in the remaining set of documents in the document set.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that facilitate identifying entity-attribute relationships in text corpora. Methods include determining whether an attribute in a candidate entity-attribute pair is an actual attribute of the entity in the entity-attribute candidate pair. This includes generating embeddings for words in the set of sentences that include the entity and the attribute and generating, using known entity-attribute pairs. This also includes generating an attribute distributional embedding for the entity based on other attributes associated with the entity from the known entity-attribute pairs, and generating an attribute distributional embedding for the attribute based on known attributes associated with known entities of the attribute in the known entity-attribute pairs.

Abstract: Embodiments are provided that include receiving a search query that represents a particular table of a plurality of tables contained in a database and that includes an additional criterion. Records are contained within the tables, which are organized in a tree structure. An index of the database contains a plurality of entries, each corresponding to a respective record in the plurality of tables. A particular entry in the index includes a path string that is indicative of a location, within the tree structure, of a table that contains a record that corresponds to the particular entry. The embodiments also include determining whether the entries in the index satisfy the search query by: (i) determining that the path string of the particular entry begins with a further path string of the particular table, and (ii) responsively determining whether a particular record that corresponds to the particular entry satisfies the additional criterion.

Abstract: Manual human processing of documents often generates results that are subjective and include human-error. The cost and relatively slow speed of manual, human analysis makes it effectively impossible or impracticable to perform document analysis at the scale, speed, and cost desired in many industries. Accordingly, it may be advantageous to employ objective, accurate rule-based techniques to evaluate and process documents. This application discloses data processing equipment and methods specially adapted for a specific application: analysis of the breadth of documents. The processing may include context-dependent pre-processing of documents and sub-portions of the documents. The sub-portions may be analyzed based on word count and commonality of words in the respective sub-portions. The equipment and methods disclosed herein improve upon other automated techniques to provide document processing by achieving a result that quantitatively improves upon manual, human processing.

Abstract: Systems and methods are described herein for inserting dialogue into query responses by generating and using dialogue metadata in conjunction with response templates. Metadata for each portion of dialogue of a plurality of portions of dialogue from a number of content items is stored, including information regarding the source content item, a transcript of the dialogue, and grammatical information. Upon receiving a query related to a content item, a type of response is first determined. Based on the type of response, and using the dialogue metadata, a portion of dialogue is identified for insertion into the response. The identified portion of dialogue is retrieved and inserted at an appropriate position within the response. The response is then generated for output.

Abstract: A computer implemented method including generating, by one or more processors, an activation request, receiving, from a user device, an activation confirmation, configuring a protection account specific to the user, where configuring the protection account comprises, identifying one or more of the user's social network accounts, authenticating one or more of the user's social network accounts, and generating a protection portal for the user, providing a link to the protection portal to the user, and providing one or more alerts to the user on the protection portal, wherein the one or more alerts identify security risks associated with one or more of the user's social network accounts.

Abstract: Embodiments of the present invention provide improved techniques for determining long term relevance and user behavior using query chains. The query chains may first be detected and then annotated into different types of chains based at least in part on various decision rules, machine-learned classifiers, and inter-query relationships. The query chains may then be subsequently used to train models for predicting user behavior and providing more relevant results to a user's queries. A content provider system according to various embodiments may aggregate historical data associated with previous search and/or transaction data, which may be analyzed to detect query chains, for example, whether queries are chained to each other. Determining whether queries are chained to each other may involve incorporating decision rules and reformulation models, analyzing temporal windows between queries, and/or analyzing inter-query relationships.

Abstract: Data merge processing based on difference between source and merged data includes creating merged data from a source data records, the merged data including data fields, performing a difference determination as between the merged data and the source data records, the difference determination including, for each source data record of the source data records, comparison of data in data fields of the merged data to the source data record, and performing processing with respect to the merged data based on the difference determination. Performing processing can include aborting a merge operation to save a merged data record with the merged data, or storing and maintaining a merged data record including the merged data, based on the difference determination determining, for each source data record of the source data records, that the degree of difference between the merged data and the source data record does not exceed a threshold.

Abstract: A method for processing a data stream to identify a structure of the data stream includes receiving the data stream a sequence of characters, retrieving a set of rules for encoding characters into at least one token, and parsing the data stream. Parsing includes generating a plurality of tokens according to the set of rules. Each token represents a corresponding portion of the sequence of characters. Parsing includes forming a sequence of tokens from the plurality of tokens and assigning at least one attribute value describing the corresponding portion of the sequence of characters of the corresponding token to which the attribute value is assigned. The sequence of tokens are assigned to a cluster by determining that the sequence of tokens matches a pattern by which the cluster is characterized. The sequence of tokens is merged with the cluster. A representation of the cluster is output.

Abstract: Disclosed herein are systems and methods for an analytics server to efficiently generate a control group dataset, including receiving, by the analytics server, a request to generate a control group dataset based on a test dataset and potential control dataset; generating, by the analytics server, an instruction to receive a first dataset based on the request; identifying, by the analytics server, data points within the first dataset corresponding to a number of users and user attributes; generating, by the analytics server, a second dataset by normalizing the user attributes; generating, by the analytics server, a third dataset comprising a space-filling curve, where each space-filling curve data point corresponds to the normalized user attributes and the number of users; determining, by the analytics server, control users by matching the space-filling curve data points with the user attribute; and generating, by the analytics server, an instruction for display on a client device.

Abstract: An automated predictive analytics system disclosed herein provides a novel technique for industry classification. In one implementation, the analytic system provides a method of matching company names, the method including generating a provider-side company dataset, for each record in a client's company records, identify a list of match candidates from the provider-side company dataset that has overlapping company signature fragments, for each client-side company, compute match scores against the list of provider-side match candidates on each signature fragment and form an overall match score, for each client-side company, use the match scores to rank candidates and keep a predetermined number of top predetermined matches, and display the predetermined number of top predetermined matches using a user interface.