Abstract: A computer-implemented method, according to one embodiment, includes collecting user data associated with a user's behavior with respect to a predetermined product and analyzing the user data for determining a subset of the user data that constitutes an implicit request for a new candidate feature for the predetermined product. A new candidate feature for the predetermined product that satisfies the implicit request is determined based on the subset of the user data. The method further includes outputting an indication of the determined new candidate feature to a device associated with development of the predetermined product. A computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a computer to cause the computer to perform the foregoing method.

Abstract: A user experience theme description is obtained, along with a new user experience feature image set. The theme description and new user experience feature image set are input into a generative adversarial network (GAN). The GAN is trained to output multiple user experience designs based on the new feature image set. The multiple designs are displayed on an electronic display device that includes an eye gaze tracking system. User interface elements and their corresponding positions within a user interface are identified based on eye gaze of a user towards the electronic display device. The position and type of user interface elements are compared between a desired user interface design and a generated user interface design. Errors between the desired user interface design and the generated user interface design are input as feedback into the GAN to further enhance the results.

Abstract: Embodiments of the present invention provide an approach for identifying outliers (e.g., detecting the outliers and generating outlier explainability) in a heterogeneous system. Heterogeneous input data is received from any number of data sources having any number of data types and converted into a single predefined format. Global outliers are detected in a first pass of the data. Contextual outliers are detected in a second pass. Global and contextual outliers are then collectively grouped based on outlier type. Output data is then generated including explainability for each detected outlier.