Abstract: An embodiment includes generating an input document that includes a plurality of text fields of attribute data. The embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models, where the first machine learning model scores terms in the input document and the second machine learning model includes a deep learning model. The embodiment also includes calculating feature-selection values for respective features of the set of candidate features and generating tag information for a remote computing asset using a machine learning classifier that predicts the tag information based on the feature-selection values.

Abstract: An embodiment includes generating an input document that includes a plurality of text fields of attribute data. The embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models, where the first machine learning model scores terms in the input document and the second machine learning model includes a deep learning model. The embodiment also includes calculating feature-selection values for respective features of the set of candidate features and generating tag information for a remote computing asset using a machine learning classifier that predicts the tag information based on the feature-selection values.

Abstract: A machine learning assessment system is provided. The system identifies multiple datasets and multiple machine learning (ML) modeling algorithms based on the client profile. The system assesses a cost of data collection for each dataset of the multiple datasets. The system assesses a performance metric for each ML modeling algorithm of the multiple modeling algorithms. The system recommends a dataset from the multiple datasets and an ML modeling algorithm from the multiple ML modeling algorithm based on the assessed costs of data collection for the multiple datasets and the assessed performance metrics for the multiple ML modeling algorithms.

Abstract: A system, computer program product, and method to deriving a cost model and dynamic adjustment of the derived model responsive to dynamic modification of one or more of the resources in a hybrid shared resource environment. Resources and corresponding configuration information are collected while monitoring runtime utilization of resource performance. As changes to the resources are discovered, the changes are subject to an assessment. A hybrid cost model is derived and configured to account for the one or more resources. The derived hybrid cost model is leveraged to conduct a multi-dimensional resource evaluation of the assessed changed configuration information. Responsive to the multi-dimensional evaluation, a generated resource utilization optimization of the one or more resources is selectively implemented.

Abstract: An embodiment includes generating an input document that includes a plurality of text fields of attribute data. The embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models, where the first machine learning model scores terms in the input document and the second machine learning model includes a deep learning model. The embodiment also includes calculating feature-selection values for respective features of the set of candidate features and generating tag information for a remote computing asset using a machine learning classifier that predicts the tag information based on the feature-selection values.

Abstract: A system, computer program product, and method to deriving a cost model and dynamic adjustment of the derived model responsive to dynamic modification of one or more of the resources in a hybrid shared resource environment. Resources and corresponding configuration information are collected while monitoring runtime utilization of resource performance. As changes to the resources are discovered, the changes are subject to an assessment. A hybrid cost model is derived and configured to account for the one or more resources. The derived hybrid cost model is leveraged to conduct a multi-dimensional resource evaluation of the assessed changed configuration information. Responsive to the multi-dimensional evaluation, a generated resource utilization optimization of the one or more resources is selectively implemented.

Abstract: A machine learning assessment system is provided. The system identifies multiple datasets and multiple machine learning (ML) modeling algorithms based on the client profile. The system assesses a cost of data collection for each dataset of the multiple datasets. The system assesses a performance metric for each ML modeling algorithm of the multiple modeling algorithms. The system recommends a dataset from the multiple datasets and an ML modeling algorithm from the multiple ML modeling algorithm based on the assessed costs of data collection for the multiple datasets and the assessed performance metrics for the multiple ML modeling algorithms.

Abstract: An embodiment includes generating an input document that includes a plurality of text fields of attribute data. The embodiment also includes extracting a set of candidate features from the attribute data using a feature extraction module that evaluates the attribute data using first and second machine learning models, where the first machine learning model scores terms in the input document and the second machine learning model includes a deep learning model. The embodiment also includes calculating feature-selection values for respective features of the set of candidate features and generating tag information for a remote computing asset using a machine learning classifier that predicts the tag information based on the feature-selection values.

Abstract: A method, system and computer program product for fulfilling an online order. An online order to purchase an item(s) is received. The “candidate locations” that stock the item(s) of the online order and that can be used to fulfill at least a portion of the online order are determined. A stockout cost for each of these candidate locations for fulfilling an item of the online order may be calculated, where the stockout cost is a cost of a potential lost sale of the item of the online order by the candidate location if the candidate location fulfills the item of the online order. A shipping location among the candidate locations to fulfill the item is then determined based at least in part on the stockout cost for each of the candidate locations for fulfilling the item. The item is then shipped to the customer from the determined shipping location.

Abstract: A markdown budget user interface is provided that implements access to large-scale computational resources capable of concurrently manipulating a number of multi-million item data sets and that allows a retailer to specify inputs. The inputs include a markdown budget constraint that applies across all retailer stores, a group of store-product data sets that each include initial prices and markdown start prices of different combinations of products within all of the retailer stores, and a markdown objective, selected from a group including profit, revenue, and sales volume, to be maximized within the markdown budget constraint. The inputs are received from the retailer using the markdown budget user interface and the large-scale computational resources are invoked to determine a markdown recommendation that includes an indication of the store-product data sets that satisfy both the markdown budget constraint and the markdown objective. The markdown recommendation is provided to the retailer.

Abstract: In an aspect of the invention, a computer-implemented method includes: receiving, by a computing device via computer network, a plurality of session data records indicating computer network browsing activity between a plurality of client devices and a merchant server hosting an online store; aggregating, by the computing device, a subset of the plurality of session data records for a single product, of a plurality of products, identified in the session data records and offered for purchase by the online store; extracting, by the computing device, features from the aggregated subset of session data records relating to customer demand for a the single product; modeling, by the computing device, customer demand for the single product based on the extracted features; optimizing, by the computing device, a price for the single product based on results of the modeling; and publishing, by the computing device, the optimized price.

Abstract: A method, system and computer program product for fulfilling an online order. An online order to purchase an item(s) is received. The “candidate locations” that stock the item(s) of the online order and that can be used to fulfill at least a portion of the online order are determined. A stockout cost for each of these candidate locations for fulfilling an item of the online order may be calculated, where the stockout cost is a cost of a potential lost sale of the item of the online order by the candidate location if the candidate location fulfills the item of the online order. A shipping location among the candidate locations to fulfill the item is then determined based at least in part on the stockout cost for each of the candidate locations for fulfilling the item. The item is then shipped to the customer from the determined shipping location.

Abstract: In an aspect of the invention, a computer-implemented method includes: receiving, by a computing device via computer network, a plurality of session data records indicating computer network browsing activity between a plurality of client devices and a merchant server hosting an online store; aggregating, by the computing device, a subset of the plurality of session data records for a single product, of a plurality of products, identified in the session data records and offered for purchase by the online store; extracting, by the computing device, features from the aggregated subset of session data records relating to customer demand for a the single product; modeling, by the computing device, customer demand for the single product based on the extracted features; optimizing, by the computing device, a price for the single product based on results of the modeling; and publishing, by the computing device, the optimized price.

Abstract: A markdown budget user interface is provided that implements access to large-scale computational resources capable of concurrently manipulating a number of multi-million item data sets and that allows a retailer to specify inputs. The inputs include a markdown budget constraint that applies across all retailer stores, a group of store-product data sets that each include initial prices and markdown start prices of different combinations of products within all of the retailer stores, and a markdown objective, selected from a group including profit, revenue, and sales volume, to be maximized within the markdown budget constraint. The inputs are received from the retailer using the markdown budget user interface and the large-scale computational resources are invoked to determine a markdown recommendation that includes an indication of the store-product data sets that satisfy both the markdown budget constraint and the markdown objective. The markdown recommendation is provided to the retailer.

Abstract: A method, system and computer program product for selecting the optimal cloud service provider(s) to service a user's needs. A physical capacity of servers in a non-virtualized data center is converted into a cloud capacity to be used. A list of cloud service providers may be generated from a catalog of providers based on the cloud capacity to be used. Additional requirements and constraints received from the user are used to select an optimal cloud service provider(s) from the generated list of cloud service providers.