Automated feedback-based application optimization
Approaches presented herein enable optimization of a developing application to a user base. More specifically, application-centric data is gathered during a cultivation phase of the developing application. Substantially concurrently with the cultivation phase of the developing application, the application-centric data is analyzed according to static code of the developing application, a testing of the developing application, or a user experience (UX) design of the developing application. A machine learning model is applied to the analyzed application-centric data. This machine learning model is trained on historic application feedback data from applications available to the user base. Based on the machine learning model, a recommended change to optimize the developing application to the user base is generated.
1. A method for optimizing a developing application to a user base, the method comprising:
gathering application-centric data during a cultivation phase of the developing application;
analyzing, during the cultivation phase of the developing application, the application-centric data according to static code of the developing application, a testing of the developing application, or a user experience (UX) design of the developing application;
applying a machine learning model to the analyzed application-centric data, the machine learning model being trained on historic application feedback data from historic applications in a same category as the developing application to associate user responses with features of the developing application from the application-centric data, the historic application feedback data being obtained from the user base responsive to features of applications available to the user base, wherein the historic application feedback data is structured to correlate features of applications available to the user base with a number of active users, user activity, and application downloads of the applications available to the user base; and
generating, based on the machine learning model, a recommended change to optimize the developing application to the user base.
2. The method of claim 1 , the application-centric data comprising a security level of the developing application, and at least one element of static code of the developing application, the element being selected from the group consisting of: a number of screens, a story board, a color palette, a code sign, a cyclomatic complexity, and a number of instances of deprecation.
3. The method of claim 1 , the application-centric data comprising at least one set of test data of the developing application, the test data being selected from the group consisting of: a unit test case, an automation test case, a performance analysis test, a system integration test (SIT), and a user acceptance test (UAT).
4. The method of claim 1 , the application-centric data comprising at least one UX element, the UX element being selected from the group consisting of: a number of taps, a number of data insertion points, a color contrast, and a usage heat map.
5. The method of claim 1 , the historic application feedback data on which the machine learning model is trained comprising historical data selected from at least one member of the group consisting of: active users, reviews, ratings, pricing, a subscription rate, and a total number of downloads of an application available to the user base.
6. The method of claim 1 , the method further comprising setting a set of weights in the machine learning model by training the machine learning model over a period of time on the application data from applications available to the user base.
7. The method of claim 1 , the method further comprising attaching the recommended change to optimize the developing application to the user base to the developing application as metadata.
8. A computer system for optimizing a developing application to a user base, the computer system comprising:
a memory medium comprising program instructions;
a bus coupled to the memory medium; and
a processor, for executing the program instructions, coupled to an application optimization engine via the bus that when executing the program instructions causes the system to:
gather application-centric data during a cultivation phase of the developing application;
analyze, during the cultivation phase of the developing application, the application-centric data according to static code of the developing application, a testing of the developing application, or a user experience (UX) design of the developing application;
apply a machine learning model to the analyzed application-centric data, the machine learning model being trained on historic application feedback data from historic applications in a same category as the developing application to associate user responses with features of the developing application from the application-centric data, the historic application feedback data being obtained from the user base responsive to features of applications available to the user base, wherein the historic application feedback data is structured to correlate features of applications available to the user base with a number of active users, user activity, and application downloads of the applications available to the user base; and
generate, based on the machine learning model, a recommended change to optimize the developing application to the user base.
9. The computer system of claim 8 , the application-centric data comprising a security level of the developing application, and at least one element of static code of the developing application, the element being selected from the group consisting of: a number of screens, a story board, a color palette, a code sign, a cyclomatic complexity, and a number of instances of deprecation.
10. The computer system of claim 8 , the application-centric data comprising at least one set of test data of the developing application, the test data being selected from the group consisting of: a unit test case, an automation test case, a performance analysis test, a system integration test (SIT), and a user acceptance test (UAT).
11. The computer system of claim 8 , the application-centric data comprising at least one UX element, the UX element being selected from the group consisting of: a number of taps, a number of data insertion points, a color contrast, and a usage heat map.
12. The computer system of claim 8 , the historic application feedback data on which the machine learning model is trained comprising historical data selected from at least one member of the group consisting of: active users, reviews, ratings, pricing, a subscription rate, and a total number of downloads of an application available to the user base.
13. The computer system of claim 8 , the instructions further causing the system to set a set of weights in the machine learning model by training the machine learning model over a period of time on the application data from applications available to the user base.
14. The computer system of claim 8 , the instructions further causing the system to attach the recommended change to optimize the developing application to the user base to the developing application as metadata.
15. A computer program product for optimizing a developing application to a user base, the computer program product comprising a computer readable hardware storage device, and program instructions stored on the computer readable hardware storage device, to:
gather application-centric data during a cultivation phase of the developing application;
analyze, during the cultivation phase of the developing application, the application-centric data according to static code of the developing application, a testing of the developing application, or a user experience (UX) design of the developing application;
apply a machine learning model to the analyzed application-centric data, the machine learning model being trained on historic application feedback data from historic applications in a same category as the developing application to associate user responses with features of the developing application from the application-centric data, the historic application feedback data being obtained from the user base responsive to features of applications available to the user base, wherein the historic application feedback data is structured to correlate features of applications available to the user base with a number of active users, user activity, and application downloads of the applications available to the user base; and
generate, based on the machine learning model, a recommended change to optimize the developing application to the user base.
16. The computer program product of claim 15 , the application-centric data comprising a security level of the developing application, and at least one element of static code of the developing application, the element being selected from the group consisting of: a number of screens, a story board, a color palette, a code sign, a cyclomatic complexity, and a number of instances of deprecation.
17. The computer program product of claim 15 , the application-centric data comprising at least one set of test data of the developing application, the test data being selected from the group consisting of: a unit test case, an automation test case, a performance analysis test, a system integration test (SIT), and a user acceptance test (UAT).
18. The computer program product of claim 15 , the application-centric data comprising at least one UX element, the UX element being selected from the group consisting of: a number of taps, a number of data insertion points, a color contrast, and a usage heat map.
19. The computer program product of claim 15 , the historic application feedback data on which the machine learning model is trained comprising historical data selected from at least one member of the group consisting of: active users, reviews, ratings, pricing, a subscription rate, and a total number of downloads of an application available to the user base, wherein the computer readable storage device further comprises instructions to set a set of weights in the machine learning model by training the machine learning model over a period of time on the application data from applications available to the user base.
20. The computer program product of claim 15 , the computer readable storage device further comprising instructions to attach the recommended change to optimize the developing application to the user base to the developing application as metadata.