Abstract: Embodiments of the disclosed technologies receive a first-party trained model and a first-party data set from a first-party system into a protected environment, receive a first third-party data set into the protected environment, and, in a data clean room, joining the first-party data set and the first third-party data set to create a joint data set for the particular segment, tuning a first-party trained model with the joint data set to create a third-party tuned model, sending model parameter data learned in the data clean room as a result of the tuning to an aggregator node, receiving a globally tuned version of the first-party trained model from the aggregator node, applying the globally tuned version of the first-party trained model to a second third-party data set to produce a scored third-party data set, and providing the scored third-party data set to a content distribution service of the first-party system.

Abstract: Techniques are provided for creating mock responses based on default data and mapping actual requests to those mock responses so that a service under test (SUT) may be executed within a simulated integration. In one technique, multiple example requests (ERs) that exemplify actual requests that the SUT may send during a test case are created. Each ER is configured to invoke a downstream service. For each ER, a mock downstream response that is based on default values is created. In a mapping, an association between each ER and its mock downstream response is stored. During the test, the SUT is invoked. Responsively, the SUT generates downstream requests to downstream services, regardless of actual availability. The computer intercepts each invocation of a downstream request. Based on the downstream request, the computer selects a mock downstream response from the mapping and provides the mock downstream response to the SUT.