Abstract: A method for visualizing corporate hierarchies is provided. The method comprises receiving a selection of a first company stored in a database and retrieving, from the database, an ultimate parent company of the first company. All other known companies with the same ultimate parent company as the first company are then retrieved from the database. An interactive hierarchical tree diagram is displayed in an interface, wherein the first company, the ultimate parent company, and the other known companies with the same ultimate parent company are displayed as nodes according to parent/child relationships among the companies. Also displayed in the interface, adjacent to the tree diagram, is a collapsible nested tree list comprising the first company, the ultimate parent company, and the other known companies with the same ultimate parent company. The tree diagram and nested tree list have synchronized responses to user input.

Abstract: A method of information retrieval is provided. The method comprises receiving a query from a user and parsing the query in real-time as the user enters the query. The parsed query is interpreted dynamically based on a defined schema of a knowledge base, and a number of query interpretations is displayed in real-time as the user enters the query. When a selection of one of the query interpretations is received from the user information is retrieved from the knowledge base according to the selected query interpretation.

Abstract: A computer implemented method, computer system, and computer program product display market transactions in a graphical user interface. A market transaction system identifies a selected market and a market session displayed in a first region of the graphical user interface. In the first region of the graphical user interface, the market transaction system displays transactions for market participants in the selected market over the market session. The transactions submitted by each market participant are separately displayed from those of other market participants. In a second region of the graphical user interface, the market transaction system may display a number of reports that are relevant to the selected market. The market transaction system subscribes a user to a report in response to receiving the user's selection of the report from the second region of the graphical user interface.

Abstract: Automated property value calculation is provided. The method comprises receiving historic transaction data for a group of real estate properties over a specified time and receiving characteristic data regarding the properties for a number of defined categories. Historic data is also received for a number of demographic parameters over the specified time. The demographic data corresponds to regions in which the properties are located. A predictive valuation model is built with the financial transaction data, characteristic data, and demographic data. Individual values are calculated with the predictive valuation model for a new group of real estate properties according to their characteristics. The individual values are then aggregated. Financial transaction data is received for the new group of properties, and a net asset value of the new group of properties is calculated according to the aggregated valuations and financial transaction data.

Abstract: A method of extracting data from documents is provided. The method comprises receiving input of a number of documents and input of a schema of data items available for extraction from the documents. The documents are parsed into a machine-readable representation, and data items in the machine-readable representation are identified according to the schema. Interpretations of data items are propagated within the documents to disambiguate identified data items, and identified data items are matched with other data items in the documents according to the schema. Only identified data items that include a minimal set of interpretations specified by the schema are extracted.

Abstract: A method, apparatus, system, and computer program product for processing news items. A computer system receives news items from a network. The computer system identifies relevant news items in the news items based on events in the news items that relate an ability for set of operators to operate a set of properties. The computer system determines a context for the events in the relevant news items. The computer system clusters the relevant news items according to the events in the relevant news items into clusters based on the events such that the relevant news items about the same events are grouped together in the clusters. The same events are determined using the context for the events. The computer system matches the events in the clusters to transactions for the set of properties for the events to form matched transactions. The computer system performs actions for the matched transactions.

Abstract: A method of forecasting raw material demand is provided. The method comprises retrieving news articles related to raw material suppliers as well as raw material industry articles related to specified raw materials. The news articles are classified as either ESG articles or non-ESG articles. The news articles and raw material industry articles are vectorized, and a subset of relevant articles are selected from the non-ESG articles. The ESG articles, relevant non-ESG articles, and raw material industry articles are fed into a sentiment scoring model, which generates sentiment scores for the raw material suppliers as well as sentiment scores for the raw materials. The sentiment scores are fed into an ESG forecast model along with supply chain data related to the raw materials and ESG data related to the raw material suppliers. The ESG forecast model then forecasts demand for the raw material suppliers to supply the raw materials.

Abstract: A framework for an automated news recommendation system for financial analysis. The system includes the automated ingestion, relevancy, clustering, and ranking of news events for financial analysts in the capital markets. The framework is adaptable to any form of input news data and can seamlessly integrate with other data used for analysis like financial data.

Abstract: A method of determining controversy voice share is provided. The method comprises identifying keywords related to a controversy topic and identifying information sources relevant to the controversy topic based on occurrences of the keywords within each source. An external voice score is calculated for an organization regarding the controversy topic, wherein the external voice score is calculated based on information sources that are external to the organization. An internal voice score is calculated for the organization regarding the controversy topic, wherein the internal voice score is calculated based on information sources internal to the organization. An overall voice share of the organization is then calculated from the external voice score and internal voice score. The overall voice share of the organization represents a proportion of influence the organization contributes to public commentary on the controversy topic relative to other organizations within a same industry sector.

Abstract: A framework for an automated news recommendation system system for financial analysis. The system includes the automated ingestion, relevancy, clustering, and ranking of news events for financial analysts in the capital markets. The framework is adaptable to any form of input news data and can seamlessly integrate with other data used for analysis like financial data.

Abstract: A framework for an automated news recommendation system for financial analysis. The system includes the automated ingestion, relevancy, clustering, and ranking of news events for financial analysts in the capital markets. The framework is adaptable to any form of input news data and can seamlessly integrate with other data used for analysis like financial data.

Abstract: A method, apparatus, system, and computer program product for searching for documents. A query comprising search terms is received. A search is performed on a collection of documents for each search term in the search terms. Search results are received for the search terms. Each search result includes documents from the collection of documents containing a search term in the search terms and scores associated with the documents. Aggregate scores for the search terms in the search results are associated with each document in the documents returned to form combined results in which a combined result in the combined results comprises the document and an aggregate score associated with the document. The documents in the combined results are ranked based on the aggregate scores to form a ranked order for the documents. The combined results with the aggregate scores in the ranked order are displayed on a display system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for voice and graphical user interfaces. One of the methods includes receiving an audio input, analyzing the audio input to determine a requested task, determining response data in response to the requested task, determining at least a first part of the response data to be presented as an audio output and at least a second part of the response data to be presented as a visual output, forwarding the first part of the response data to an audio output for presentation to a user, forwarding the second part of the response data to a visual output for presentation to a user; and forwarding to at least one of the audio output and the visual output data describing sources and/or assumptions used to construct the response data.

Abstract: This specification relates to methods and systems for content management. One of the methods includes: receiving data identifying a user; verifying that the user is an authorized user; receiving initial content from the authorized user; encrypting the initial content using an encryption key to produce encrypted content; forwarding the encrypted content for storage; creating content storage metadata; encrypting the content storage metadata to provide encrypted content storage metadata; and forwarding the encrypted content storage metadata to a blockchain such as a public ledger.

Abstract: Predicting the impact of controversial events on an entity, such as a company, can indicate the entity's ability to operate successfully in the future and optimize long-term value. This specification describes systems and methods to detect controversial events, identify the context of an event, measure the scope of the event, measure its current impact on the entity's performance, and predict the event's future impact on the entity's performance.

Abstract: This specification describes methods and systems for sentiment analysis. One of the methods includes: receiving a plurality of documents, each document having text data and for each of the documents: (1) representing at least part of the document's text data in a multi-dimensional vector space to produce vectorized text data; (2) applying a neural network to the vectorized text data to calculate a sentiment score, wherein the neural network has been trained using a two step process including (a) training the neural network with a non-domain specific training set; and (b) training the neural network with a domain specific training set; and (3) determining a sentiment score for an entity based at least in part on the sentiment scores for the plurality of documents.

Abstract: A system and method for delivering content in real-time using advanced messaging technology that reduces the risk of content being lost or dropped in transmission. The system and method utilize a custom, simplified XML format to deliver real-time textual, numeric, and metadata content directly to subscribers. The XML tag set specifies all of the information needed to package, process, and distribute real-time content messages and includes an advanced tagging structure that allows granular content customization. Messages are built on the fly using multi-channel data processing techniques. The XML delivery system and method offers an array of real-time market-specific page-based “Alert” services and aggregated newswires with accompanying real-time numeric data feeds. These feeds contain proprietary assessments and other price data across a broad spectrum of global and regional commodity markets, including oil, petrochemicals, metals, electric power, natural gas, coal, and risk.