storing recorded data in a data storage as a plurality of time series, each time series having a first recorded value corresponding to a first time and a final recorded value corresponding to an end of the time series;

providing, within a first time window, interpolated values using a Bayesian model, the interpolated values being used for missing values in the plurality of time series;

storing the interpolated values as prediction data in a prediction storage;

loading at least a portion of the recorded data from the data storage, the at least a portion of the recorded data being defined using a second time window;

loading at least a portion of the prediction data from the prediction storage, the at least a portion of the prediction data corresponding to one or more gaps in the second time window;

predicting, using the Bayesian model, prediction values for a sub-set of time series, time series in the sub-set of time series comprising time series that are absent loaded recorded data and loaded prediction data in at least one of the one or more gaps in the second time window; and

adjusting one or more of devices of the system that generate the recorded data based on the prediction values.