A system, method, and computer-readable medium for performing a customer service interaction estimation operation, comprising: training a customer service interaction estimation system using a training dataset of cases to provide a trained predictive model; identifying current open cases via the customer service interaction system; applying the trained predictive model to the current open cases to identify low customer experience cases; generating an estimation output relating to the current open cases, the estimation output identifying an open case subset of cases having a high risk of high effort to resolve.