Artificial intelligence (ai) based predictions and recommendations for equipment

An artificial intelligence (AI) based equipment attribute prediction generating method comprising:

• accessing historical data related to an attribute of at least one equipment wherein the historical data includes data values tracking the equipment attribute and features of the equipment attribute over different time periods;
• generating a plurality of feature combinations from the historical data, wherein the plurality of feature combinations include each possible combination of the features of the equipment attribute;
• obtaining a plurality of attribute predictions by applying each possible feature combination to each of a plurality of models;
• selecting a top N models and corresponding possible feature combinations from the plurality of models using model selection criteria, wherein N is a natural number and the model selection criteria include error estimations of the plurality of attribute predictions;
• identifying a best scoring model of the top N Models using a scoring scheme;
• receiving a user request for prediction of the attribute for a plurality of pieces of the equipment;
• loading multiple instances of the best scoring model;
• generating a respective attribute prediction for each of the plurality of equipment by each instance of the best scoring model in accordance with a user request wherein the user request includes a plurality of sets of new data values for features included in the possible feature combination corresponding to the best scoring model;
• and
• deriving recommendations for one or more of the plurality of equipment pieces, the recommendations being derived based on the possible feature combinations corresponding to the best scoring model and the respective attribute predictions of the one or more equipment pieces.

A non-transitory processor-readable storage medium comprising machine-readable instructions that cause a processor to:

• access historical data related to an attribute of at least one equipment wherein the historical data includes data values tracking the equipment attribute and features of the equipment attribute over different time periods;
• generate a plurality of feature combinations that include each possible combination of the features of the equipment attribute from the historical data, the plurality of feature combinations are generated based on a data type of the features and operators that can be applied to the data types;
• obtain a plurality of attribute predictions by applying each possible feature combination to each of a plurality of models;
• select a top N models and corresponding possible feature combinations from the plurality of models wherein N is a natural number, wherein the top N models are selected using model selection criteria that include an error estimation of the plurality of attribute predictions and multi-sample testing for consistency;
• identify a best scoring model of the top N models using a scoring scheme;
• generate an attribute prediction in accordance with a user request wherein the user request includes new data values for the features included in the possible feature combination corresponding to the best scoring model;
• and
• derive at least one recommendation by analyzing coefficients of an equation representing the best scoring model based on the possible feature combination corresponding to the best scoring model and the attribute prediction.