A method of machine learning algorithm selection may include obtaining a dataset that includes multiple data entries. In some embodiments, each of the data entries may include multiple features and one of the multiple features may be designated as a target variable. The method may further include selecting a subset of the data entries. In some embodiments, selecting the subset of the data entries may include binning the data entries into multiple data bins based on values in the target variable and selecting a subset of the binned data entries from each of the multiple data bins as the subset of the data entries. The method may further include constructing multiple machine learning models using the subset of the data entries and selecting one of the multiple machine learning models based on an evaluation of the multiple machine learning models.

A method trains and generates a matrix solving approach library package for optimizing a matrix solving application. A computer system with implemented the method may 1) receive requests to train a matrix solving Machine Learning (ML) model; 2) design a model structure of the ML Model accordingly; 3) select a set of matrices solving sampling data for training the defined matrix solving ML model; 4) use the selected matrix solving data and constructed IMSA Structure as inputs to train the matrix solving ML model; 5) generates a new matrix solving ML model with optimized IMSA parameters as ML model outputs; optimize the weights for each ML model node according to the provided training data sets; 6) verify the trained matrix solving approach library package with untrained data sets (matrix solving problems). The trained matrix solving approach library package may optimize matric solving application for solving matrix with result.