Interactive adaptation of machine learning models for time series data

One or more non-transitory computer-readable storage media storing one or more sequences of program instructions which, when executed using one or more processors, cause the one or more processors to execute:

• using a first computer, establishing programmatic connections to a digitally stored first database comprising over one million records, each of the records comprising time series data organized as an event with a timestamp and an event data, the first database being a multi-tenant data store programmatically coupled to a data warehouse manager and a query engine;
• using the first computer, reading a configuration file that specifies one or more tables in the first database;
• successively reading each particular table that is identified in the configuration file;
• for each particular table among the one or more tables, forming and submitting a plurality of queries to the first database, each of the queries specifying one or more data aggregation operations, and in response to the plurality of queries, receiving a set of aggregated records of the first database and creating and storing reduced-size tables based on the aggregated records;
• training a machine learning model using a portion of the set of the aggregated records as a training dataset;
• using the first computer, determining a plurality of hyper-parameters for a machine learning model, the plurality of hyper-parameters including a plurality of outlier values that are represented in the set of aggregated records, one or more change points that are represented in the set of aggregated records, a plurality of seasonality patterns that are represented in the set of aggregated records;
• using the machine learning model with the hyper-parameters, evaluating the aggregated records of the first database using the machine learning model to output forecasted event data as a second time series;
• and
• generating presentation instructions using a computer display device configured to display one or more graphical visualizations in a graphical user interface of the computer display device, the graphical visualizations comprising a time series analysis and a graphical timeline of a forecasted time series that specifies a set of events, seasonality, trend, or a collinearity are likely to be seen in the future;
• using the first computer receiving, from a second computer, input specifying the plurality of hyper-parameters for the machine learning model, wherein the plurality of hyper-parameters have been modified using the seasonality, trend, or collinearity and updating the machine learning model using the plurality of hyper-parameters;
• using the machine learning model with the hyper-parameters after the updating, evaluating the aggregated records of the first database using the machine learning model to output forecasted event data as a third time series;
• generating presentation instructions using a computer display device configured to display one or more graphical visualizations in a graphical user interface of the computer display device, the graphical visualizations comprising the time series analysis and a graphical timeline of the third time series.