One or more processors track internet usage of a user. The tracking includes tracking a first user input into one or more websites using a keylogging subprogram. One or more processors analyze the first user input. Analyzing the first user input includes using machine learning to gain knowledge of one or more interests of the first user based on the first user input. One or more processors determine a proximity of the first user to at least one point of interest within a first threshold distance of the first user while the first user is mobile, match at least one interest of the one or more interests of the first user with one or more interests associated with the at least one point of interest, and provide a notification that the first user is within the first threshold distance of the at least one point of interest.