Technology to automatically stream confidence and prediction intervals for non-parametric and non-stationary time series data

摘要

Methods and systems may provide for technology to generate a plurality of predictions associated with a test period based on an analytics model and generate an error model of the plurality of predictions based on first non-parametric time series data associated with the test period, wherein the error model is to be generated independently of the analytics model. Additionally, the technology may automatically determine an interval based on the error model, the first non-parametric time series data and a margin of error input, wherein the interval is to include an upper bound on a scale associated with the first non-parametric time series data at a time instance in a forecast period and a lower bound on the scale at the time instance.