Explainable classifications with abstention using client agnostic machine learning models
Embodiments relate to providing explainable classifications with abstention using client agnostic machine learning models. A technique includes classifying, by a processor, a record with a label using a machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of an information technology (IT) domain. The processor generates an explanation of a decision by the machine learning model to classify the record with the label and displays the explanation in a human readable form.
1 . A computer-implemented method comprising:
classifying, by a processor, a record with a label using a machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of an information technology (IT) domain that is associated with computer systems operating in an IT computing environment;
generating, by the processor, an explanation of a decision by the machine learning model to classify the record with the label associated with the computer systems operating in the IT computing environment;
displaying the explanation in a human readable form; and
preventing the given record from being input to an automated resolution system based on the given record being outside of the scope of the IT domain associated with the computer systems operating in the IT computing environment.
2 . The computer-implemented method of claim 1 , wherein the human readable form comprises a disjunctive normal form.
3 . The computer-implemented method of claim 1 , wherein the explanation of the decision by the machine learning model is based on a linear classifier formula utilized by the machine learning model.
4 . The computer-implemented method of claim 1 , wherein:
the explanation of the decision by the machine learning model is based on features and respective coefficients corresponding to the features, the features and the respective coefficients being derived from a linear classifier formula of the machine learning model; and
the features are extracted from text of the record.
5 . The computer-implemented method of claim 1 , wherein the human readable form comprises a display of pertinent positive features with respective contributions for each of the pertinent positive features to the decision by the machine learning model, the pertinent positive features being associated with the computer systems operating in the IT computing environment.
6 . The computer-implemented method of claim 1 , wherein the machine learning model is trained on training data in the IT domain.
7 . The computer-implemented method of claim 1 , wherein:
the machine learning model comprises a linear classifier algorithm; and
the record is a ticket of technical problems in an IT environment.
8 . A system comprising:
a memory having computer readable instructions; and
one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
classifying a record with a label using a machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of an information technology (IT) domain that is associated with computer systems operating in an IT computing environment;
generating an explanation of a decision by the machine learning model to classify the record with the label associated with the computer systems operating in the IT computing environment;
displaying the explanation in a human readable form; and
preventing the given record from being input to an automated resolution system based on the given record being outside of the scope of the IT domain associated with the computer systems operating in the IT computing environment.
9 . The system of claim 8 , wherein the human readable form comprises a disjunctive normal form.
10 . The system of claim 8 , wherein the explanation of the decision by the machine learning model is based on a linear classifier formula utilized by the machine learning model.
11 . The system of claim 8 , wherein:
the explanation of the decision by the machine learning model is based on features and respective coefficients corresponding to the features, the features and the respective coefficients being derived from a linear classifier formula of the machine learning model; and
the features are extracted from text of the record.
12 . The system of claim 8 , wherein the human readable form comprises a display of pertinent positive features with a measure of respective contributions for each of the pertinent positive features to the decision by the machine learning model.
13 . The system of claim 8 , wherein the machine learning model is trained on training data in the IT domain.
14 . The system of claim 8 , wherein:
the machine learning model comprises a linear classifier algorithm; and
the record is a ticket of technical problems in an IT environment.
15 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
classifying a record with a label using a machine learning model, the machine learning model abstaining from classifying a given record in response to the given record being outside of a scope of an information technology (IT) domain that is associated with computer systems operating in an IT computing environment;
generating an explanation of a decision by the machine learning model to classify the record with the label associated with the computer systems operating in the IT computing environment;
displaying the explanation in a human readable form; and
preventing the given record from being input to an automated resolution system based on the given record being outside of the scope of the IT domain associated with the computer systems operating in the IT computing environment.
16 . The computer program product of claim 14 , wherein the human readable form comprises a disjunctive normal form.
17 . The computer program product of claim 15 , wherein the explanation of the decision by the machine learning model is based on a linear classifier formula utilized by the machine learning model.
18 . The computer program product of claim 15 , wherein:
the explanation of the decision by the machine learning model is based on features and respective coefficients corresponding to the features, the features and the respective coefficients being derived from a linear classifier formula of the machine learning model; and
the features are extracted from text of the record.
19 . The computer program product of claim 15 , wherein the human readable form comprises a display of pertinent positive features with a measure of respective contributions for each of the pertinent positive features to the decision by the machine learning model.
20 . The computer program product of claim 15 , wherein the machine learning model is trained on training data in the IT domain.