Patent application number | Description | Published |
20140200872 | ONLINE LEARNING USING INFORMATION FUSION FOR EQUIPMENT PREDICTIVE MAINTENANCE IN RAILWAY OPERATIONS - An aspect of an online learning system includes collecting data, via a computer processing device, from a plurality of data sources including multiple disparate detectors, the data including at least one of historical alarm data, failures, maintenance records, and environment observations. The data is stored in tables each corresponding to a subject of measurement. The online learning system also includes identifying common fields shared across the tables, merging at least a portion of the data across the tables having the common fields, and creating an integrated data model based on results of the merging. | 07-17-2014 |
20140200873 | ONLINE LEARNING USING INFORMATION FUSION FOR EQUIPMENT PREDICTIVE MAINTENANCE IN RAILWAY OPERATIONS - An aspect of an online learning system includes collecting data, via a computer processing device, from a plurality of data sources including multiple disparate detectors, the data including at least one of historical alarm data, failures, maintenance records, and environment observations. The data is stored in tables each corresponding to a subject of measurement. The online learning system also includes identifying common fields shared across the tables, merging at least a portion of the data across the tables having the common fields, and creating an integrated data model based on results of the merging. | 07-17-2014 |
20140200951 | SCALABLE RULE LOGICALIZATION FOR ASSET HEALTH PREDICTION - An aspect of scalable rule logicalization for asset health management includes aggregating data, via a computer processing device, from data sources, extracting a set of features from the data, projecting the features to a lower dimensional space, generating a prediction based on the projecting, logicalizing a decision boundary for the prediction, and estimating a confidence level of the prediction based on the decision boundary. | 07-17-2014 |
20140200952 | SCALABLE RULE LOGICALIZATION FOR ASSET HEALTH PREDICTION - An aspect of scalable rule logicalization for asset health management includes aggregating data, via a computer processing device, from data sources, extracting a set of features from the data, projecting the features to a lower dimensional space, generating a prediction based on the projecting, logicalizing a decision boundary for the prediction, and estimating a confidence level of the prediction based on the decision boundary. | 07-17-2014 |
20150081377 | DYNAMIC PRICING FOR FINANCIAL PRODUCTS - An aspect of product pricing includes classifying customers into groups based on shared, predefined characteristics and financial transactions, and identifying services rendered and available but not rendered. For each customer, a risk associated with a service is estimated; availability and prices of the service by third parties are determined; a price for the service set by the entity is compared with the prices set by the third parties; and a demand for the service of the entity is estimated as a function of the availability and prices of the service by the third parties. For each customer, a probability that the customer will purchase the service is estimated based on the demand, and a price for the service that is customized for the customer is calculated, as a function of the risk, the demand, and the probability of purchase, and in view of a target profit and/or target revenue. | 03-19-2015 |
20150081388 | CUSTOMER SELECTION FOR SERVICE OFFERINGS - An aspect of customer selection processes includes classifying, by a computer processor, customers of an entity into groups based on commonly shared, predefined characteristics among the customers. For each of the groups: services rendered for corresponding customers are identified; for each of the services rendered, a risk relationship and a reward relationship between each of the corresponding customers and the service is determined; and for each of the services rendered, a score that defines a combination of the risk relationship and the reward relationship is calculated. For each of the services rendered by the entity, the corresponding score is applied to a candidate customer having a set of characteristics matching the characteristics of one of the groups, and the service is offered to the candidate customer as a function of the score. | 03-19-2015 |
20150081390 | CUSTOMER SELECTION FOR SERVICE OFFERINGS - An aspect of customer selection processes includes classifying, by a computer processor, customers of an entity into groups based on commonly shared, predefined characteristics among the customers. For each of the groups: services rendered for corresponding customers are identified; for each of the services rendered, a risk relationship and a reward relationship between each of the corresponding customers and the service is determined; and for each of the services rendered, a score that defines a combination of the risk relationship and the reward relationship is calculated. For each of the services rendered by the entity, the corresponding score is applied to a candidate customer having a set of characteristics matching the characteristics of one of the groups, and the service is offered to the candidate customer as a function of the score. | 03-19-2015 |
20150081391 | ANALYTICS-DRIVEN PRODUCT RECOMMENDATION FOR FINANCIAL SERVICES - An aspect of product recommendation processes includes classifying customers into groups based on commonly shared, predefined characteristics and common financial transaction activities conducted. For each service offered, the product recommendation processes include estimating a cost of recommendation of the service; and estimating, for each of the customers in a group, a transaction risk of providing the service. For each group, the product recommendation processes include: identifying services available that are not rendered; estimating, based on economic health data associated with the corresponding customers, a probability of an acceptance by the corresponding customers of an offer for available services; estimating a profit based on historical profit data acquired from results of rendering the service to the customers of the group; and selecting a subset of the available services to offer the customers as a function of the cost of recommendation, the transaction risk, the probability of acceptance, and estimated profit. | 03-19-2015 |
20150081519 | DYNAMIC PRICING FOR FINANCIAL PRODUCTS - An aspect of product pricing includes classifying customers into groups based on shared, predefined characteristics and financial transactions, and identifying services rendered and available but not rendered. For each customer, a risk associated with a service is estimated; availability and prices of the service by third parties are determined; a price for the service set by the entity is compared with the prices set by the third parties; and a demand for the service of the entity is estimated as a function of the availability and prices of the service by the third parties. For each customer, a probability that the customer will purchase the service is estimated based on the demand, and a price for the service that is customized for the customer is calculated, as a function of the risk, the demand, and the probability of purchase, and in view of a target profit and/or target revenue. | 03-19-2015 |
20150081520 | ANALYTICS-DRIVEN PRODUCT RECOMMENDATION FOR FINANCIAL SERVICES - An aspect of product recommendation processes includes classifying customers into groups based on commonly shared, predefined characteristics and common financial transaction activities conducted. For each service offered, the product recommendation processes include estimating a cost of recommendation of the service; and estimating, for each of the customers in a group, a transaction risk of providing the service. For each group, the product recommendation processes include: identifying services available that are not rendered; estimating, based on economic health data associated with the corresponding customers, a probability of an acceptance by the corresponding customers of an offer for available services; estimating a profit based on historical profit data acquired from results of rendering the service to the customers of the group; and selecting a subset of the available services to offer the customers as a function of the cost of recommendation, the transaction risk, the probability of acceptance, and estimated profit. | 03-19-2015 |