Cancer is one of the leading causes of death worldwide due to its severity and prevalence. But the higher number of lives lost to it might also be due to its fluency in metastasizing and resisting treatment. In my opinion, developing effective cancer control policy and improving healthcare systems are necessary in order to have a positive impact on the mortality rate caused by this disease. In the context of detecting cancer cells, microarray data is very important as it encompasses detailed information regarding genetic material and its expression within cancer cells. This technique allows cancer-related researchers and physicians to conceive the simultaneous expression of many genes and identify unique gene repertoires for different types and subtypes of cancer. This specific element enabled uncovering of significant details from the broad genomic masses of information acquired through the application of machine learning algorithms to the microarray data and even more essential in cancer detection. That is quite interesting as the aim of this study is to create an ML-based system that would enable accurate cancer diagnostics. To achieve that, the model would require Correlation Feature Selection (CFS) and Particle Swarm Optimization (PSO) in the extraction of relevant features from microarray data. Next, seven different types of the ML classifiers like Support Vector Machine (SVM), Random Forest (RF), AdaBoost, XGBoost, and so on are used, and their performance is evaluated using various machine learning evaluation parameters.