Abstract: Various embodiments of the present disclosure provide feature engineering techniques for improving machine learning model development, performance, and maintenance. The feature engineering techniques include generating a model description vector from a textual model description for a target machine learning model and using the model description vector to generate one or more description-based similarity vectors that each include one or more of a plurality of similarity scores for a plurality of machine learning features. The feature engineering techniques include generating a label-based similarity vector based on a comparison between training data for the target machine learning model and a plurality of feature values of the plurality of machine learning features. The feature engineering techniques include providing a predictive feature set for the target machine learning model based on the one or more similarity vectors and the one or more label-based similarity vectors.

Abstract: Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, for performing predictive recommendation. In one example embodiment, a method is provided. The method includes generating guideline data objects for a plurality of service need conditions. The method includes generating a compliance profile data object for each of a plurality of provider entities. The compliance profile data object for a provider entity includes compliance scores with respect to the plurality of service need conditions, a compliance score determined using procedural record data objects associated with each provider entity and the guideline data objects. The method further includes selecting a subset of the plurality of provider entities according to the compliance profile data object for each provider entity. The method further includes performing at least one automated recommendation-based action based at least in part on the selected subset.

Abstract: Various embodiments of the present invention introduce techniques for efficient and resilient network-wide supervision of a hierarchically-segmented blockchain network. A hierarchically-segmented blockchain network may include S segment ledger systems associated with S network segments and G local ledger systems. In response, various embodiments of the present invention utilize a centralized global ledger monitoring system that non-persistently monitors the S+G monitored systems via periodic chaincodes that are configured to verify targeted transactions associated with particular local ledgers and/or segment-wise ledgers during particular transactional junctures associated with ledger data.

Abstract: In general, this disclosure describes techniques for automatically restructuring a database to improve one or more parameters of the database. In some examples, a computing system is configured to extract a set of columns and merge the set of columns into a new table of a first new candidate model of the database; determine a table of the database based on a number of columns of that are involved in query “where” or “join” clauses; merge the table with one or more connected tables in a second new candidate model of the database, wherein the one or more connected tables are connected to the table by at least one of the “where” or “join” clauses; select a model of the database from among the candidate models based on one or more parameters; and use the selected model as the current model of the database.

Abstract: Various embodiments of the present invention introduce techniques for efficient and resilient network-wide supervision of a hierarchically-segmented blockchain network. A hierarchically-segmented blockchain network may include S segment ledger systems associated with S network segments and G local ledger systems. In response, various embodiments of the present invention utilize a centralized global ledger monitoring system that non-persistently monitors the S+G monitored systems via periodic chaincodes that are configured to verify targeted transactions associated with particular local ledgers and/or segment-wise ledgers during particular transactional junctures associated with ledger data.

Abstract: Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, for performing predictive recommendation. In one example embodiment, a method is provided. The method includes generating guideline data objects for a plurality of service need conditions. The method includes generating a compliance profile data object for each of a plurality of provider entities. The compliance profile data object for a provider entity includes compliance scores with respect to the plurality of service need conditions, a compliance score determined using procedural record data objects associated with each provider entity and the guideline data objects. The method further includes selecting a subset of the plurality of provider entities according to the compliance profile data object for each provider entity. The method further includes performing at least one automated recommendation-based action based at least in part on the selected subset.

Abstract: There is a need for solutions for more efficient predictive data analysis systems. This need can be addressed, for example, by a system configured to receive temporal inferences for a predictive task, where each temporal inference is associated with a temporal benchmark and the temporal benchmarks include a base temporal benchmark and supplemental temporal benchmarks; generate a cross-temporal prediction for the predictive task by applying one or more cross-temporal probabilistic updates to the base temporal inference, where each cross-temporal probabilistic update is associated with a supplemental temporal benchmark; and display the cross-temporal prediction using a cross-temporal prediction interface.

Abstract: In general, this disclosure describes techniques for automatically restructuring a database to improve one or more parameters of the database. In some examples, a computing system is configured to extract a set of columns and merge the set of columns into a new table of a first new candidate model of the database; determine a table of the database based on a number of columns of that are involved in query “where” or “join” clauses; merge the table with one or more connected tables in a second new candidate model of the database, wherein the one or more connected tables are connected to the table by at least one of the “where” or “join” clauses; select a model of the database from among the candidate models based on one or more parameters; and use the selected model as the current model of the database.

Abstract: Solutions for more efficient and effective traversal of infection networks are disclosed.

Abstract: There is a need for solutions for more efficient predictive data analysis systems. This need can be addressed, for example, by a system configured to receive temporal inferences for a predictive task, where each temporal inference is associated with a temporal benchmark and the temporal benchmarks include a base temporal benchmark and supplemental temporal benchmarks; generate a cross-temporal prediction for the predictive task by applying one or more cross-temporal probabilistic updates to the base temporal inference, where each cross-temporal probabilistic update is associated with a supplemental temporal benchmark; and display the cross-temporal prediction using a cross-temporal prediction interface.

Abstract: There is a need for solutions for more efficient predictive data analysis systems. This need can be addressed, for example, by a system configured to obtain, for each predictive task of a plurality of predictive tasks, a plurality of per-model inferences; generate, for each predictive task, a cross-model prediction based on the plurality of per-model inferences for the predictive task; and generate, based on each cross-model prediction associated with a predictive task, a cross-prediction for the particular predictive task, wherein determining the cross-prediction comprises applying one or more probabilistic updates to the cross-model prediction for the particular predictive task and each probabilistic update is determined based on the cross-model prediction for a related predictive task of the one or more related predictive tasks.