Utilizing machine learning models to predict system events based on time series data generated by a system

A device, comprising:

• one or more memories;
• and
• one or more processors, coupled to the one or more memories, configured to:
• perform block bootstrapping of historic time series data associated with a system, based on a parameter, to generate blocks of data points of the historic time series data,
• wherein the parameter is modified based on feedback associated with a prediction;
• process the blocks of data points, with first machine learning models, to calculate first predictions;
• apply first weights to the first predictions to generate weighted first predictions;
• aggregate the weighted first predictions to generate an aggregated first prediction;
• process the blocks of data points, with second machine learning models, to calculate second predictions;
• apply second weights to the second predictions to generate weighted second predictions;
• aggregate the weighted second predictions to generate an aggregated second prediction;
• apply final weights to the aggregated first prediction and the aggregated second prediction to generate weighted aggregated predictions;
• aggregate the weighted aggregated predictions to generate a final prediction;
• and
• perform one or more actions based on the final prediction.

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

• one or more instructions that, when executed by one or more processors of a device, cause the device to:
• receive historic time series data identifying events associated with a system;
• perform block bootstrapping of the historic time series data, based on a parameter, to generate blocks of data points of the historic time series data,
• wherein the parameter defines a quantity of data points to be included in each of the blocks of data points, and
• wherein the parameter is modified based on feedback associated with a prediction;
• process the blocks of data points, with first machine learning models, to calculate first predictions;
• apply first weights to the first predictions to generate weighted first predictions;
• aggregate the weighted first predictions to generate an aggregated first prediction;
• process the blocks of data points, with second machine learning models, to calculate second predictions;
• apply second weights to the second predictions to generate weighted second predictions;
• aggregate the weighted second predictions to generate an aggregated second prediction;
• process the blocks of data points, with third machine learning models, to calculate third predictions;
• apply third weights to the third predictions to generate weighted third predictions;
• aggregate the weighted third predictions to generate an aggregated third prediction;
• apply final weights to the aggregated first prediction, the aggregated second prediction, and the aggregated third prediction to generate weighted aggregated predictions;
• aggregate the weighted aggregated predictions to generate a final prediction;
• and
• perform one or more actions based on the final prediction.