Autonomous intelligent system for feature enhancement and improvement prioritization
Systems and methods for prioritizing enhancement and/or improvements of features of a user application are disclosed. In at least one embodiment, a method includes retrieving analytics data generated by an analytics engine, where the analytics data includes data relating to user interactions with a feature of the user application. A plurality of vectors is generated from the analytics data. The plurality of vectors include vectors corresponding to user interactions with the feature. A priority is assigned to enhancing and/or improving the feature of the user application based on a weighted sum of the plurality of vectors.
1. A computer-implemented method for prioritizing enhancement and/or improvements of features of a user application, comprising:
monitoring, by an analytics engine, analytics data comprising at least one of performance of a feature and user interactions with a feature of the user application;
storing, by the analytics engine, the analytics data in an analytics datastore;
retrieving, by an analytics interface engine, the analytics data from the analytics datastore;
providing, by the analytics interface engine to a prioritization engine, the analytics data, wherein the prioritization engine generates a plurality of vectors using the analytics data, wherein the plurality of vectors include vectors corresponding to one or more of:
a feature performance vector based on performance metrics of the feature of the user application;
a feature engagement vector based on metrics for user engagement with the feature of the user application;
a feature visitor vector based on metrics associated with new visitors and/or returning visitors using the feature of the user application; and
a feature adoption vector based on user adoption of prior features, wherein the feature adoption vector is generated using a regression classification model trained using historical characteristics of features having similar characteristics to the feature that is being analyzed for prioritization assignment;
assigning a weight to each of the plurality of vectors;
assigning a priority to enhancing and/or improving the feature of the user application based on a weighted sum of the plurality of vectors; and
providing, by a user interface engine, feature prioritization information to a user interface, wherein a prioritization system comprises the analytics interface engine, the prioritization engine, and the user interface engine.
2. The computer-implemented method of claim 1 , wherein the weighted sum of the plurality of vectors is used to generate an index value corresponding to the priority for enhancing and/or improving the feature.
3. The computer-implemented method of claim 1 , wherein one or more of the feature performance vector, the feature engagement vector, and the feature adoption vector are generated from a corresponding plurality of sub-vectors.
4. The computer-implemented method of claim 1 , wherein the plurality of vectors include a feature performance vector based on one or more feature performance sub-vectors, wherein the one or more sub-vectors of the feature performance vector include:
a sub-vector corresponding to the time taken for opening sessions associated with the feature;
a sub-vector corresponding to the time taken for performing actions associated with the feature; and
wherein the feature performance vector is determined as a weighted sum of the one or more feature performance sub-vectors.
5. The computer-implemented method of claim 1 , wherein the plurality of vectors include a feature engagement vector based on one or more feature engagement sub-vectors, wherein the one or more feature engagement sub-vectors include:
a sub-vector corresponding to the number of clicks that users have made while engaging with the feature;
a sub-vector corresponding to the time that the users have spent using the feature;
a sub-vector corresponding to the bounce rates for pages viewed by users engaging the feature; and
a sub-vector corresponding to the number of pages viewed by users during a session; and
wherein the feature engagement vector is determined as a weighted sum of the one or more feature engagement sub-vectors.
6. The computer-implemented method of claim 1 , wherein the plurality of vectors include a feature adoption vector, wherein the feature adoption vector corresponds to the user adoption of prior features operating in a same context as the feature.
7. The computer-implemented method of claim 6 , wherein the feature adoption vector is derived from a regression analysis of one or more of:
ratings of the prior features given by users of the prior features; and
ratings given to the prior features by owners of products including the prior features.
8. A system comprising:
one or more information handling systems, wherein the one or more information handling systems include:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus;
wherein the computer program code included in one or more of the information handling systems is executable by the processor of the information handling system so that the information handling system, alone or in combination with other information handling systems, executes operations comprising:
monitoring, by an analytics engine, analytics data comprising at least one of performance of a feature and user interactions with a feature of a user application;
storing, by the analytics engine, the analytics data in an analytics datastore;
retrieving, by an analytics interface engine, the analytics data from the analytics datastore;
providing, by the analytics interface engine to a prioritization engine, the analytics data, wherein the prioritization engine generates a plurality of vectors using the analytics data, wherein the plurality of vectors include vectors corresponding to one or more of:
a feature performance vector based on performance metrics of the feature of the user application;
a feature engagement vector based on metrics for user engagement with the feature of the user application;
a feature visitor vector based on metrics associated with new visitors and/or returning visitors using the feature of the user application; and
a feature adoption vector based on user adoption of prior features, wherein the feature adoption vector is generated using a regression classification model trained using historical characteristics of features having similar characteristics to the feature that is being analyzed for prioritization assignment;
assigning a weight to each of the plurality of vectors;
assigning a priority to enhancing and/or improving the feature of the user application based on a weighted sum of the plurality of vectors; and
providing, by a user interface engine, feature prioritization information to a user interface, wherein a prioritization system comprises the analytics interface engine, the prioritization engine, and the user interface engine.
9. The system of claim 8 , wherein the weighted sum of the plurality of vectors is used to generate an index value corresponding to the priority for enhancing and/or improving the feature.
10. The system of claim 8 , wherein one or more of the feature performance vector, the feature engagement vector, and the feature adoption vector are generated from a corresponding plurality of sub-vectors.
11. The system of claim 8 , wherein the plurality of vectors include a feature performance vector based on one or more feature performance sub-vectors, wherein the one or more sub-vectors of the feature performance vector include:
a sub-vector corresponding to the time taken for opening sessions associated with the feature;
a sub-vector corresponding to the time taken for performing actions associated with the feature; and
wherein the feature performance vector is determined as a weighted sum of the one or more feature performance sub-vectors.
12. The system of claim 8 , wherein the plurality of vectors include a feature engagement vector based on one or more feature engagement sub-vectors, wherein the one or more feature engagement sub-vectors include:
a sub-vector corresponding to the number of clicks that users have made while engaging with the feature;
a sub-vector corresponding to the time that the users have spent using the feature;
a sub-vector corresponding to the bounce rates for pages viewed by users engaging the feature; and
a sub-vector corresponding to the number of pages viewed by users during a session; and
wherein the feature engagement vector is determined as a weighted sum of the one or more feature engagement sub-vectors.
13. The system of claim 8 , wherein the plurality of vectors include a feature adoption vector, wherein the feature adoption vector corresponds to the user adoption of prior features operating in the same context as the feature.
14. The system of claim 13 , wherein the feature adoption vector is derived from a regression analysis of one or more of:
ratings of the prior features given by users of the prior features; and
ratings given to the prior features by owners of products including the prior features.
15. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer-executable instructions configured for:
monitoring, by an analytics engine, analytics data comprising at least one of performance of a feature and user interactions with a feature of a user application;
storing, by the analytics engine, the analytics data in an analytics datastore;
retrieving, by an analytics interface engine, the analytics data from the analytics datastore;
providing, by the analytics interface engine to a prioritization engine, the analytics data, wherein the prioritization engine generates a plurality of vectors using the analytics data, wherein the plurality of vectors include vectors corresponding to one or more of:
a feature performance vector based on performance metrics of the feature of the user application;
a feature engagement vector based on metrics for user engagement with the feature of the user application;
a feature visitor vector based on metrics associated with new visitors and/or returning visitors using the feature of the user application; and
a feature adoption vector based on user adoption of prior features, wherein the feature adoption vector is generated using a regression classification model trained using historical characteristics of features having similar characteristics to the feature that is being analyzed for prioritization assignment;
assigning a weight to each of the plurality of vectors;
assigning a priority to enhancing and/or improving the feature of the user application based on a weighted sum of the plurality of vectors; and
providing, by a user interface engine, feature prioritization information to a user interface, wherein a prioritization system comprises the analytics interface engine, the prioritization engine, and the user interface engine.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the weighted sum of the plurality of vectors is used to generate an index value corresponding to the priority for enhancing and/or improving the feature.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein one or more of the feature performance vector, the feature engagement vector, and the feature adoption vector are generated from a corresponding plurality of sub-vectors.
18. The non-transitory, computer-readable storage medium of claim 15 , wherein the plurality of vectors include a feature performance vector based on one or more feature performance sub-vectors, wherein the one or more sub-vectors of the feature performance vector include:
a sub-vector corresponding to the time taken for opening sessions associated with the feature;
a sub-vector corresponding to the time taken for performing actions associated with the feature; and
wherein the feature performance vector is determined as a weighted sum of the one or more feature performance sub-vectors.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the plurality of vectors include a feature engagement vector based on one or more feature engagement sub-vectors, wherein the one or more feature engagement sub-vectors include:
a sub-vector corresponding to the number of clicks that users have made while engaging with the feature;
a sub-vector corresponding to the time that the users have spent using the feature;
a sub-vector corresponding to the bounce rates for pages viewed by users engaging the feature; and
a sub-vector corresponding to the number of pages viewed by users during a session; and
wherein the feature engagement vector is determined as a weighted sum of the one or more feature engagement sub-vectors.
20. The non-transitory, computer-readable storage medium of claim 15 , wherein the plurality of vectors include a feature adoption vector, wherein the feature adoption vector corresponds to the user adoption of price features operating in the same context as the feature.