Computing processes with data and file management control systems for database classification

A computing system for process management and control for database classification, comprising:

• a computer with one or more processor and memory that stores computer-readable instructions;
• and
• wherein, upon execution, by the one or more processor, of the computer-readable instructions, the computer performs steps comprising:
• accessing a data frame;
• applying predetermined rules for reconfiguring data in the data frame to a standard format, wherein the data reconfiguring includes replacing missing or null values in the data with default values;
• training a plurality of machine learning models on the data to generate a plurality of candidate rules, wherein the data includes records with a positive classification and records with a negative classification, wherein each of the plurality of machine learning models is a decision tree model, wherein each of the candidate rules is a branch of one of the decision trees, wherein the candidate rules are based on different sampling ratios of positive classification records to negative classification records, and wherein the machine learning models have a sampling ratio that incrementally increases for each model, wherein the training includes:
• inserting training data into an iterative training and testing loop to predict a target variable;
• using features in the training test data to train the model based on weights and iterative calculations;
• and
• repeatedly predicting the target variable during each iteration of the training and testing loop, wherein each iteration of the training and testing loop has differing weights, each of the differing weights being updated with each iteration of the training and testing loop to reduce error in predicting the target variable, until the model surpasses a predetermined minimum threshold level of accuracy;
• computing each of the candidate rules using the data as input, and generating a score for each of the candidate rules;
• generating an output file including the candidate rules and the associated scores;
• and
• storing the output file for further use.