Keywords: linear models, tree models, gradient boosting, XGBoost, neural network
Description:
According to CDC, breast cancer is a disease in which cells in the breast grow out of control.
It is a type of cancer that begins in different parts of the breast and can spread outside the breast through blood vessels and lymph vessels.
Early detection of breast cancer and access to the most advanced cancer treatments are two of the most important strategies for preventing death
from breast cancer.
In our studies, we try to build a Classification Model to predict whether a person has the presence of breast cancer
based on physical features of the cell nucleus of that person by applying different algorithms.
We acquired the original datasets (Breast Cancer Wisconsin Diagnostic Data Set) from UCI Machine Learning Repository.
The data includes attribute information and ten features computed from a digitized image of a fine needle aspirate (FNA) of a breast mass,
such as radius, texture, smoothness, compactness concavity, concave points, and fractal dimension.
We employ linear models, tree models, random forest, gradient boosting, and neural network to make classification.
Report: Please mail to me (hw2894@columbia.edu) or through the mail symbol at the right bottom.