Time series forecasting
A method for time series forecasting includes receiving a time series forecasting query from a user requesting the data processing hardware to perform a plurality of time series forecasts. Each time series forecast is a forecast of future data based on respective current data. Simultaneously, for each time series forecast of the plurality of time series forecasts requested by the time series forecasting query, the method includes training a plurality of models for the respective time series forecast. The method also includes determining which model of the plurality of models best fits the respective time series forecast and forecasting the future data based on the determined best fitting model and the respective current data. The method also includes returning, to the user, the forecasted future data for each of the plurality of time series forecasts request by the timer series forecasting query.
1 . A computer-implemented method executed by data processing hardware that causes the data processing hardware to perform operations comprising:
receiving a time series forecasting query requesting a time series forecast, the time series forecast comprising a forecast of future data based on current data;
training a plurality of machine learning models for the time series forecast using an order of a moving-average model, wherein:
each respective machine learning model of the plurality of machine learning models is trained on the same data blocks of the current data using a different order of the moving-average model; and
each machine learning model of the plurality of machine learning models is trained to predict the time series forecast based on the same data blocks of the current data;
for each respective model of the plurality of machine learning models, determining, using the current data, a respective prediction error of the respective machine learning model;
selecting, using the respective prediction error of each respective machine learning model, a single one of the plurality of machine learning models that best fits the respective time series forecast;
forecasting the future data based on the selected best fitting machine learning model and the current data; and
returning the forecasted future data for the time series forecast requested by the time series forecasting query.
2 . The method of claim 1 , wherein the operations further comprise using the respective prediction error of each respective machine learning model without relying on empirical means.
3 . The method of claim 1 , wherein the time series forecasting query comprises a Structured Query Language (SQL) query.
4 . The method of claim 1 , wherein the time series forecasting query comprises a reference to three columns of a table.
5 . The method of claim 4 , wherein the three columns of the table comprise:
a first column comprising timestamp data;
a second column comprising the current data; and
a third column comprising time series forecast identification data.
6 . The method of claim 1 , wherein each machine learning model of the plurality of machine learning models comprises an auto regressive integrated moving average model.
7 . The method of claim 6 , wherein training the plurality of machine learning models comprises performing hyper-parameter tuning.
8 . The method of claim 1 , wherein forecasting the future data comprises modeling seasonal effects.
9 . The method of claim 1 , wherein forecasting the future data comprises modeling drift.
10 . The method of claim 1 , wherein selecting the one of the plurality of machine learning models that best fits the respective time series forecast comprises determining which machine learning model has a lowest Akaike information criterion (AIC).
11 . A system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations comprising:
receiving a time series forecasting query requesting a time series forecast, the time series forecast comprising a forecast of future data based on current data;
training a plurality of machine learning models for the time series forecast using an order of a moving-average model, wherein:
each respective machine learning model of the plurality of machine learning models is trained on the same data blocks of the current data using a different order of the moving-average model; and
each machine learning model of the plurality of machine learning models is trained to predict the time series forecast based on the same data blocks of the current data;
for each respective model of the plurality of machine learning models, determining, using the current data, a respective prediction error of the respective machine learning model;
selecting, using the respective prediction error of each respective machine learning model, a single one of the plurality of machine learning models that best fits the respective time series forecast;
forecasting the future data based on the selected best fitting machine learning model and the current data; and
returning the forecasted future data for the time series forecast requested by the time series forecasting query.
12 . The system of claim 11 , wherein the operations further comprise using the respective prediction error of each respective machine learning model without relying on empirical means.
13 . The system of claim 11 , wherein the time series forecasting query comprises a Structured Query Language (SQL) query.
14 . The system of claim 11 , wherein the time series forecasting query comprises a reference to three columns of a table.
15 . The system of claim 14 , wherein the three columns of the table comprise:
a first column comprising timestamp data;
a second column comprising the current data; and
a third column comprising time series forecast identification data.
16 . The system of claim 11 , wherein each model of the plurality of machine learning models comprises an auto regressive integrated moving average model.
17 . The system of claim 16 , wherein training the plurality of machine learning models comprises performing hyper-parameter tuning.
18 . The system of claim 11 , wherein forecasting the future data comprises modeling seasonal effects.
19 . The system of claim 11 , wherein forecasting the future data comprises modeling drift.
20 . The system of claim 11 , wherein selecting the one of the plurality of machine learning models that best fits the respective time series forecast comprises determining which machine learning model has a lowest Akaike information criterion (AIC).