Machine Learning (ML) requires a certain number of features (i.e., attributes) to train the model. One of the main challenges is to determine the right number and the type of such features out of the given dataset’s attributes. It is not uncommon for the ML process to use dataset of available features without computing the predictive value of each. Such an approach makes the process vulnerable to overfit, predictive errors, bias, and poor generalization. Each feature in the dataset has either a unique predictive value, redundant, or irrelevant value. However, the key to better accuracy and fitting for ML is to identify the optimum set (i.e., grouping) of the right feature set with the finest matching of the feature’s value. This paper proposes a novel approach to enhance the Feature Engineering and Selection (eFES) Optimization process in ML. eFES is built using a unique scheme to regulate error bounds and parallelize the addition and removal of a feature during training. eFES also invents local gain (LG) and global gain (GG) functions using 3D visualizing techniques to assist the feature grouping function (FGF). FGF scores and optimizes the participating feature, so the ML process can evolve into deciding which features to accept or reject for improved generalization of the model. To support the proposed model, this paper presents mathematical models, illustrations, algorithms, and experimental results. Miscellaneous datasets are used to validate the model building process in Python, C#, and R languages. Results show the promising state of eFES as compared to the traditional feature selection process.

Accuracy metric has become a gold standard for measuring various models and systems. However, the latest development and research have shown its limitations, especially during training/testing of the machine learning models. It fails to keep the integrity of the reliability of the outcome for unbalanced data modeling. This problem is known as Accuracy Paradox. This paper presents a unique approach utilizing the underlying standard metrics and creating internals 3D evaluation of fitness factors, a part of enhanced machine learning engine engineering. The model is trained under the internal tuning of parameters and trade-off is handled as a collateral benefit using built-in parallelism. Moreover, the way this metric is engineered, it opens up generalized options for data engineers and model creators to incorporate (mathematically) the metrics (standard or the new one) of their choice based on how the model is trained for any type of data domain. This approach shows the improved integrity of the internal metrics measurements using mathematical constructs and governing algorithm for enhanced Weighted Performance Metric. Included sample experiments on real-world datasets, and results support the contribution of this research.

Machine learning (ML) has shown enormous potential in various domains with the wide variations of underlying data types. Because of the miscellany in the data sets and the features, ML classifiers often suffer from challenges, such as feature miss-classification, unfit algorithms, low accuracy, overfitting, underfitting, extreme bias, and high predictive errors. Through the lens of related study and latest progress in the field, this paper presents a novel scheme to construct logical table (LT) unit with two internal sub-modules for algorithm blend and feature engineering. The LT unit works in the deepest layer of an enhanced ML engine engineering (eMLEE) process. eMLEE consists of several low-level modules to enhance the ML classifier progression. A unique engineering approach is adopted in eMLEE to blend various algorithms, enhance the feature engineering, construct a weighted performance metric, and augment the validation process. The LT is an in-memory logical component, that governs the progress of eMLEE, regulates the model metrics, improves the parallelism, and keep tracks of each module of eMLEE as the classifier learns. Optimum fitness of the model with parallel “check, validate, insert, delete, and update”mechanism in 3-D logical space via structured schemas in the LT is obtained. The LT unit is developed in Python, C#, and R libraries and tested using miscellaneous data sets. Results are created using GraphPad Prism, SigmaPlot, Plotly, and MS Excel software. To support the built and implementation of the proposed scheme, complete mathematical models along with the algorithms, and necessary illustrations are provided in this paper. To show the practicality of the proposed scheme, several simulation results are presented with a comprehensive analysis of the outcomes for the metrics of the model that the LT regulates with improved outcomes.