Data driven featurization and modeling

Abstract

Computer-implemented systems and methods are disclosed for data driven expertise mapping. The systems and methods provide for obtaining data sets from data sources, wherein the data sets include services related data, analyzing the data sets, wherein the analysis generates information representative of the services related data, and generating training sets related to the data sets, wherein the training sets are based on known values. The systems and methods further provide for generating models, wherein the models are based on determining services provided by service providers using a combination of the services related data, the analysis of the data sets and the training sets, and provide a mapping of at least one service to service providers. The systems and methods additionally include evaluating the models based on known values and storing an indication for providing to a graphical user interface based on more models.

1 .- 18 . (canceled) 
     
     
         19 . A data-driven dynamic modeling system:
 one or more memory devices storing processor executable instructions; and   one or more processors configured to execute the instructions to cause the data-driven dynamic modeling system to perform:
 obtaining one or more data records from one or more data sets, wherein at least one of the one or more data records is associated with a professional; 
 aggregating, using an aggregation engine, the one or more data records, based on related attributes of the one or more data records; 
 analyzing, using a pre-computation engine, the one or more combined data records and one or more data records stored in the one or more data sets; 
 computing additional data based on the analysis; 
 generating one or more models, using a model builder, based on the one or more combined data records, the one or more data records, and the computed additional data. 
 training the one or more models using training sets; 
 evaluating the one or more trained models based on known values; and 
 using the one or more models, determining a specialty associated with the professional. 
   
     
     
         20 . The data-driven dynamic modeling system device of  claim 19 , wherein:
 the one or more data records contain domain specific data; and   the related attributes of the one or more data records are associated with the domain.   
     
     
         21 . The data-driven dynamic modeling system of  claim 20 , wherein the domain specific data includes at least one of medical claim data or prescription drug data. 
     
     
         22 . The data-driven dynamic modeling system of  claim 20 , wherein the domain specific data includes at least one of Current Procedural Terminology (CPT) codes, Healthcare Common Procedure Coding (HCPCS) codes, or International Statistical Classification of Diseases and Related Health Problems (ICD) codes. 
     
     
         23 . The data-driven dynamic modeling system of  claim 19 , wherein the computed additional data corresponds to the aggregated data records. 
     
     
         24 . The data-driven dynamic modeling system of  claim 19 , wherein the training sets include at least one of a positive training set identifying professional activities associated with a first specialty or a negative training set identifying professional activities not associated with a second specialty. 
     
     
         25 . The data-driven dynamic modeling system of  claim 19 , wherein the training sets include publications categorized by medical subject heading (MeSH) terms. 
     
     
         26 . A method performed by one or more processors and comprising:
 obtaining one or more data records from one or more data sets, wherein at least one of the one or more data records is associated with a professional;   aggregating, using an aggregation engine, the one or more data records, based on related attributes of the one or more data records;   analyzing, using a pre-computation engine, the one or more combined data records and one or more data records stored in the one or more data sets;   computing additional data based on the analysis;   generating one or more models, using a model builder, based on the one or more combined data records, the one or more data records, and the computed additional data.   training the one or more models using training sets;   evaluating the one or more trained models based on known values; and   using the one or more models, determining a specialty associated with the professional.   
     
     
         27 . The method of  claim 26 , wherein:
 the one or more data records contain domain specific data; and   the related attributes of the one or more data records are associated with the domain.   
     
     
         28 . The method of  claim 27 , wherein the domain specific data includes at least one of medical claim data or prescription drug data. 
     
     
         29 . The method of  claim 27 , wherein the domain specific data includes at least one of Current Procedural Terminology (CPT) codes, Healthcare Common Procedure Coding (HCPCS) codes, or International Statistical Classification of Diseases and Related Health Problems (ICD) codes. 
     
     
         30 . The method of  claim 26 , wherein the training sets include at least one of a positive training set identifying professional activities associated with a first specialty or a negative training set identifying professional activities not associated with a second specialty. 
     
     
         31 . The method of  claim 26 , wherein the training sets include domain specific information. 
     
     
         32 . A non-transitory computer readable storage medium storing instructions that are executable by a first computing device that includes one or more processors to cause the first computing device to perform a method for data driven expertise mapping, the method comprising:
 obtaining one or more data records from one or more data sets, wherein at least one of the one or more data records is associated with a professional;   aggregating, using an aggregation engine, the one or more data records, based on related attributes of the one or more data records;   analyzing, using a pre-computation engine, the one or more combined data records and one or more data records stored in the one or more data sets;   computing additional data based on the analysis;   generating one or more models, using a model builder, based on the one or more combined data records, the one or more data records, and the computed additional data.   training the one or more models using training sets;   evaluating the one or more trained models based on known values; and   using the one or more models, determining a specialty associated with the professional.   
     
     
         33 . The non-transitory computer readable medium of  claim 32 , wherein:
 the one or more data records contain domain specific data; and   the related attributes of the one or more data records are associated with the domain.   
     
     
         34 . The non-transitory computer readable medium of  claim 33 , wherein the domain specific data includes at least one of medical claim data or prescription drug data. 
     
     
         35 . The non-transitory computer readable medium of  claim 33 , wherein the domain specific data includes at least one of Current Procedural Terminology (CPT) codes, Healthcare Common Procedure Coding (HCPCS) codes, or International Statistical Classification of Diseases and Related Health Problems (ICD) codes. 
     
     
         36 . The non-transitory computer readable medium of  claim 32 , wherein the computed additional data corresponds to the aggregated data records. 
     
     
         37 . The non-transitory computer readable medium of  claim 32 , wherein the training sets include at least one of a positive training set identifying professional activities associated with a first specialty or a negative training set identifying professional activities not associated with a first specialty. 
     
     
         38 . The non-transitory computer readable medium of  claim 32 , wherein the training sets include domain specific information, the domain specific information including at least publications categorized by medical subject heading (MeSH) terms.