Abstract: Methods, systems, and apparatus, including computer program products, for detecting and estimating lost sales. A demand distribution for a product provided by a retail presence is determined. A probability of a lost sales occurrence is evaluated, including determining a predetermined time period and a probability of no sales over the predetermined time period. A determination of whether no sales have occurred over a time period corresponding in length to the predetermined time period is made. If the probability of no sales is below a threshold, an estimate of lost sales is determined.

Abstract: Methods, systems, and apparatus, including computer program products, for providing recommendations in a retail environment. A recommendation system includes a centralized knowledge base including one or more rules for defining logic to provide recommendations based on one or more detected system alerts, an alert engine for determining alert conditions in a retail presence including out of stock conditions, a root cause engine for determining one or more root causes for out of stock conditions that are detected, a mapping engine for mapping between alerts and recommendations, and a recommendation engine for issuing one or more recommendations associated with given alerts and determined root causes.