Providing predictive analytics with predictions tailored for a specific domain

A computer program product for providing predictions tailored for a specific domain, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code comprising the programming instructions for:

• identifying a target concept tagged to a target field;
• identifying concepts that have an influential impact directly to said target concept or indirectly to a concept tagged to a field associated with said target field;
• identifying fields as candidates for predictors from said identified concepts;
• calculating influential confidence scores for each of said identified candidates for predictors;
• evaluating numeric metadata information for each of said identified candidates for predictors;
• computing a numeric analytics score for each of said identified candidates for predictors based on said evaluated numeric metadata information, wherein said numeric analytics score comprises a value corresponding to how influential a candidate is in affecting a value of said target field;
• computing a final confidence score for each of said identified candidates for predictors using said influential confidence scores and said numeric analytics scores;
• ranking said identified candidates for predictors based on said final confidence scores;
• and
• selecting a portion of said candidates for predictors to build a statistical model based on said ranking.

A system, comprising:

• a memory for storing a computer program for providing predictions tailored for a specific domain;
• and
• a processor connected to said memory, wherein said processor is configured to execute the program instructions of the computer program comprising:
• identifying a target concept tagged to a target field;
• identifying concepts that have an influential impact directly to said target concept or indirectly to a concept tagged to a field associated with said target field;
• identifying fields as candidates for predictors from said identified;
• calculating influential confidence scores for each of said identified candidates for predictors;
• evaluating numeric metadata information for each of said identified candidates for predictors;
• computing a numeric analytics score for each of said identified candidates for predictors based on said evaluated numeric metadata information, wherein said numeric analytics score comprises a value corresponding to how influential a candidate is in affecting a value of said target field;
• computing a final confidence score for each of said identified candidates for predictors using said influential confidence scores and said numeric analytics scores;
• ranking said identified candidates for predictors based on said final confidence scores;
• and
• selecting a portion of said candidates for predictors to build a statistical model based on said ranking.