Detection of Breast Tumor Using Various Machine Learning Techniques

Breast tumor is among the world's most typically malignancies tumors is a condition when the breast's cells develop quickly and uncontrolled. Breast tumors can begin in a variety of locations within the breast and spread to other areas of the body. Breast tumor diagnosis and prognosis have attracted the attention of numerous researchers. Every technique has a different precision rate, which varies based on the conditions, resources, and datasets employed. Our main objective is to evaluate and contrast the many Machine Learning methods now in use in order to decide which one is the most efficient and will produce high prediction accuracy for the large dataset. The Kaggle Dataset has been applied in this paper. Our objective is to examine the data and evaluate how well various algorithm techniques identify breast tumor. The algorithm like Decision Tree, Random Forest, XGBoost, MLP, and Ridge in this case allows for the classification of cell type, including whether it is normal or malignant. To determine the best algorithm, the accuracy of each is calculated and contrasted. Two of the most popular techniques, Random Forest and XGBoost that have been used to the breast tumor sample in this study based on the analysis, and the results are compared using performance metrics. With this approach, dataset accuracy is greater than 95% and precision is 97%, making it much superior to previous algorithms.