Interface for visualizing and improving model performance

1. A method comprising:

receiving data characterizing performance of a generated model, wherein the received data is based on monitoring performance of the generated model while the generated model is being used for classification on live data;

determining a first performance value of the generated model based on the received data characterizing performance of the generated model;

rendering, within a graphical user interface, a plot including a first axis and a second axis, the first axis including a characterization of a first performance metric and the second axis including a characterization of a second performance metric; and

rendering, within the graphical user interface and the plot, a first graphical object at a first location characterizing the first performance value, the first graphical object providing a visual representation of the characteristics of the generated model and/or requirements of the generated model.

2. The method of claim 1 , further comprising:

rendering, within the graphical user interface and the plot, a first line indicative of random model performance, a second line indicative of constant accuracy, and/or a third line indicative of constant cost.

3. The method of claim 1 , wherein the first performance metric includes rate of false positive, count of false positive, cost of false positive, benefit missed by false positive, true positive, benefit of true positive, benefit of minimizing false positive, benefit of maximizing true positive, or a combination thereof; and

wherein the second performance metric includes rate of false negative, count of false negative, cost of false negative, benefit missed by false negative, true negative, benefit of true negative, benefit of minimizing false negative, benefit of maximizing true negative, or a combination thereof.

4. The method of claim 1 , further comprising:

determining a second performance value of the generated model at a second point in time; and

rendering, within the graphical user interface and the plot, a second graphical object at a second location characterizing the second performance value.

5. The method of claim 1 , wherein the first graphical object includes a shape and/or color indicative of a characteristic of the generated model, the characteristic including a complexity metric.

6. The method of claim 1 , further comprising:

monitoring performance of a second generated model while the second generated model is being used for classification on live data, the monitoring including determining a third performance value of the second generated model at the first point in time and determining a fourth performance value of the second generated model at the second point in time; and

rendering, within the graphical user interface and the plot, a third graphical object at a third location characterizing the third performance value and a fourth graphical object at a fourth location characterizing the fourth performance value.

7. The method of claim 1 , further comprising:

automatically identifying subgroups of data associated with the generated model;

determining a performance value of each subgroup at a first point in time; and

rendering, within the graphical user interface and the plot, a graphical object for each subgroup at respective locations for the first point in time.

8. The method of claim 7 , wherein a size of the graphical object for each subgroup is indicative of a relative proportion size of the data associated with the generated model.

9. The method of claim 1 , further comprising:

automatically identifying subgroups of data associated with the generated model;

determining a performance value of each subgroup at a first point in time; and

determining that the generated model can be improved based on the performance value of each subgroup; and

rendering, within the graphical user interface, a prompt to a user to split the generated model based on the performance of the subgroups.

10. The method of claim 1 , wherein characteristics of the generated model, comprise one or more of complexity of the model, target accuracy, relative cost of error, or model finding budget.

11. The method of claim 1 , wherein requirements of the generated model comprise one or more of human-understandability status, auditability, capability of providing real-time results, or immutability.

12. A system comprising:

at least one processor;

memory storing instructions which, when executed by the at least one processor, causes the at least one processor to perform operations comprising:

receiving data characterizing performance of a generated model, wherein the received data is based on monitoring performance of the generated model while the generated model is being used for classification on live data;

determining a first performance value of the generated model based on the received data characterizing performance of the generated model;

rendering, within a graphical user interface, a plot including a first axis and a second axis, the first axis including a characterization of a first performance metric and the second axis including a characterization of a second performance metric; and

rendering, within the graphical user interface and the plot, a first graphical object at a first location characterizing the first performance value, the first graphical object providing a visual representation of the characteristics of the generated model and/or requirements of the generated model.

13. The system of claim 12 , the operations further comprising:

rendering a first line indicative of random model performance, a second line indicative of constant accuracy, and/or a third line indicative of constant cost.

14. The system of claim 12 , wherein the first performance metric includes rate of false positive, count of false positive, cost of false positive, benefit missed by false positive, true positive, benefit of true positive, benefit of minimizing false positive, benefit of maximizing true positive, or a combination thereof; and

wherein the second performance metric includes rate of false negative, count of false negative, cost of false negative, benefit missed by false negative, true negative, benefit of true negative, benefit of minimizing false negative, benefit of maximizing true negative, or a combination thereof.

15. The system of claim 12 , the operations further comprising:

determining a second performance value of the generated model at a second point in time; and

rendering, within the graphical user interface and the plot, a second graphical object at a second location characterizing the second performance value.

16. The system of claim 12 , wherein the first graphical object includes a shape and/or color indicative of a characteristic of the generated model, the characteristic including a complexity metric.

17. The system of claim 12 , the operations further comprising:

monitoring performance of a second generated model while the second generated model is being used for classification on live data, the monitoring including determining a third performance value of the second generated model at the first point in time and determining a fourth performance value of the second generated model at the second point in time; and

rendering, within the graphical user interface and the plot, a third graphical object at a third location characterizing the third performance value and a fourth graphical object at a fourth location characterizing the fourth performance value.

18. The system of claim 12 , the operations further comprising:

automatically identifying subgroups of data associated with the generated model;

determining a performance value of each subgroup at a first point in time; and

rendering, within the graphical user interface and the plot, a graphical object for each subgroup at respective locations for the first point in time.

19. The system of claim 18 , wherein a size of the graphical object for each subgroup is indicative of a relative proportion size of the data associated with the generated model.

20. A non-transitory computer program product storing instructions, which when executed by at least one processor of at least one computing system, cause the at least one processor to perform operations comprising:

receiving data characterizing performance of a generated model, wherein the received data is based on monitoring performance of the generated model while the generated model is being used for classification on live data;

determining a first performance value of the generated model based on the received data characterizing performance of the generated model;

rendering, within a graphical user interface, a plot including a first axis and a second axis, the first axis including a characterization of a first performance metric and the second axis including a characterization of a second performance metric; and

rendering, within the graphical user interface and the plot, a first graphical object at a first location characterizing the first performance value, the first graphical object providing a visual representation of the characteristics of the generated model and/or requirements of the generated model.