AI AND ML RESEARCH METHODOLOGY

Considering that research approaches have an effect on the quality
and reliability of the results, machine learning is an extremely
important field. The major objectives of this article were to
investigate the many techniques that have been taken to study on
machine learning, as well as to investigate new issues and the
possible implications that they may have on the field. In order for
the researchers to achieve this goal, they looked at one hundred
different articles that were published in IEEE journals. Based on
the findings of this study, it can be concluded that the most
prevalent quantitative research methodologies used in machine
learning are experimental research designs. The research indicates
that in today’s world, academics often use more than one algorithm
in order to find solutions to challenges. A growing number of
researchers are depending on optimum feature selection as a
method to improve the effectiveness of machine learning
algorithms. Despite the fact that academics are increasingly taking
processing time into consideration when assessing the performance
of an algorithm, the confusion matrix and its versions continue to
be the dominant techniques. It is common practice to use the
Python programming language and its libraries for the purposes of
model development, training, and testing. When it comes to
addressing classification and prediction challenges, the most often
used techniques are Decision Tree, Naïve Bayes, Support Vector
Machine, Random Forest, and Artificial Neural Networks.