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;
• training a plurality of AI models implementing different methodologies for generating predictions for the equipment attribute;
• obtaining a plurality of attribute predictions by applying each possible feature combination to each of the plurality of AI models;
• selecting a top N AI models and corresponding possible feature combinations from the plurality of AI 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 AI model of the top N AI models and a particular feature combination from the possible feature combinations for the equipment attribute using a scoring scheme;
• receiving a user request for prediction of the attribute for a plurality of pieces of the equipment;
• loading into a non-transitory processor-readable storage medium multiple instances of the best scoring AI model;
• obtaining a respective attribute prediction for each piece of the plurality of pieces of equipment from each instance of the multiple instances of the best scoring AI 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 AI model;
• 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 AI model and the respective attribute predictions of the one or more equipment pieces;
• calculating variances between actual values of the equipment attribute obtained for the plurality of equipment pieces from multiple instances of the best scoring AI model and the respective attribute prediction;
• and
• further training the best scoring AI model on the actual values based at least on the variances.

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;
• train a plurality of AI models implementing different methodologies for generating predictions for the equipment attribute;
• obtain a plurality of attribute predictions by applying each possible feature combination to each of the plurality of AI models;
• select a top N AI models and corresponding possible feature combinations from the plurality of AI models wherein N is a natural number, wherein the top N AI 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 AI model of the top N AI models and a particular feature combination from the possible feature combinations for the equipment attribute using a scoring scheme;
• load into the non-transitory, processor-readable medium, a single instance of the best scoring AI model in response to a user request for prediction for the equipment attribute for a single piece of the at least one customized equipment;
• obtain from the single instance the best scoring AI model and the particular feature combination, 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 AI model;
• derive at least one recommendation by analyzing coefficients of an equation representing the best scoring AI model based on the possible feature combination corresponding to the best scoring AI model and the attribute prediction;
• calculate variance between an actual value of the equipment attribute and the attribute prediction;
• and
• further train the best scoring AI model on the actual value based at least on the variance.