Sp Global, Inc.

Hyunyoung Choi

Yuanli Pei

Hao Yan

Hao Jiang

Bo Liu

Dun Wang

Seung-jae Bang

Hanchul Choi

Yue Wen

Xu Cai

Jiachen Xu

Qiuhao Zhang

A method, apparatus, system, and computer program product for method for dynamically managing an ontology for classifying data is provided. The ontology is generated from the classifications of a plurality of entities. Models are generated that predict classifications according to the ontology and natural language descriptions of the entities. Unclassified entities are modelled by according to the models to identify at least one classification within the ontology. Responsive to identifying a plurality of probable classifications within the ontology, a new classification is generated based on the plurality of probable classifications, an updated ontology is generated that includes the new classification, and the unclassified entity is classified according to the new classification.

Dynamic ontology classification system

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.

Property valuation model and visualization

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.

Calculating voice share and company sentiment

Growing community of inventors

Boston, MA, United States of America

Hyunyoung Choi