Abstract: A computer-implemented method for automated product recommendations personalized to a user browsing a webpage of an e-commerce website or web application via a computer device. Image data of one or more product items displayed on the webpage is captured responsive to user input, and then sent to a server over a network. A software module that executes on the server analyzes the image data and segments it into one or more of attributes, constituent items, or objects of the one or more product items. The software module also receives media content feeds that contain images representative of style preferences of the user. The software module selects one or more specific items from a product catalogue of the e-commerce website or web application based, in part, on a visual similarity to the images representative of the style preferences of the user.