I want to measure the effectiveness of my search engine, one of the ways i can do that is by measuring the rate at which a customer reformulates the previous query. Hence, I need to quantify inter-query relationship
An approach binary classifier that operates on a pair of consecutive queries and checks whether this pair is interrelated or not, There are several interesting considerations to make here. This is how one of my search queries data looks like- ['water', 'canned drinks', 'soda', 'hot dog buns', 'hot dogs']
Can you elaborate on the simplest model and also explore any other possible solutions to this problem?
