System and method for dynamically controlling sample rates and data flow in a networked measurement system by dynamic determination of statistical significance

摘要

A system and methods for dynamically controlling sample rates and data flow in a distributed networked environment by dynamic determination of statistical significance or characteristics for an unlimited number of data collection scripts concurrently executed on concurrently rendering web pages operating an unlimited number of advertisements. Consumer and media behaviors are sampled on all the different components of the distributed environment to gather information, which is transmitted to a downstream statistical analytics system. The system and methods are configured to balance the communication data flow and load among servers and browsers in this distributed networked environment that are engaged in viewing of online content including online content with one or more advertisements.

主权项

1. A method implemented on one or more computing devices, for dynamically adjusting sample rates of variables relating to attention by users to online content, wherein the online content is displayed on a plurality of user devices concurrently connected to a plurality of different websites, the method comprising:
defining, using at least one of the one or more computing devices, a desired sample rate based on determining one or more statistical characteristics of aggregated data derived from gathering sample data relating to attention by a plurality of users to the online content; monitoring, using at least one of the one or more computing devices, aggregated data flows from the plurality of user devices to determine if current new information for a particular online content is required for statistical accuracy, wherein the monitoring is at least in part by a sample data collection script placed in the plurality of user devices; assessing the impact of the aggregated data flows, using at least one of the one or more computing devices, on a downstream analytic server; and adjusting the aggregated data flows, using at least one of the one or more computing devices, by changing sample rate parameters for measurement scripts provided to the plurality of user devices.