© 2020 JETIR November 2020, Volume 7, Issue 11 www.jetir.org (ISSN-2349-5162)
JETIR2011009 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 51
Abstract: There are many types of cancers that need our
attention and a lot of human time spent in researching
for their cure by analyzing a lot of symptoms. Many
patients with similar health problems receive different
kinds of treatment and eventually different extents of
cure. Breast Cancer is one of the most exquisite and
internecine disease among all of the diseases in medical
science. It’s mainly effective for women. It is one of the
crucial reasons of death among the females all over the
world. Various supervised machine learning techniques
such as Logistic Regression,Decision tree
Classifier,Random Forest ,K-NN,Support Vector
Machine has been used for classification of data .The
very famous data set such as Wisconsin breast cancer
diagnosis (WBCD) data set has been used for
classification of data. The experimental result shows
that the Random Forest classifier gives the highest
accuracy of 96.50% among the other classifier. The aim
is for early detection of cancer because the early
detection of cancer can be helpful to remove the cancer
completely.
Keywords: Machine Learning, Classification,
Decision tree Classifier, K-Nearest Neighbor, Logistic
Regression, Random Forest,Support Vector
Machine,accuracy etc.
I. Introduction
Machine learning (ML) is a significant method for data
analysis that iteratively learns from the available data
with the aid of learning algorithms. Machine learning
can be defined as a technique for programming
computers to optimize a performance criterion using
example data or past experience i.e, defining a model
up to some parameters, and learning by executing a
computer program to optimize the parameters of a
model using the training data or past experience. The
model has been made predictive to make predictions in
the future or descriptive to gather some
knowledge/information from data. Machine learning is
an artificial intelligence (AI) application that enables
systems to learn and improve automatically without
being explicitly programmed. Machine learning focuses
on developing programs that are able to use the data and
to learn from it.
Breast Cancer is the prime reason for death of women.
It is the second most dangerous cancer after lung
cancer. Breast cancer is the most common cancer
among women worldwide accounting for 25 percent of
all cancer cases. In the year 2018 according to the
statistics provided by World Cancer Research Fund it is
estimated that over 2 million new cases were recorded
out of which 626,679 deaths were approximated. Of all
the cancers, breast cancer constitutes of 11.6% in new
cancer cases and come up with 24.2% of cancers among
women [1]. Most of the experienced researchers come
to conclusion that the most experienced
physicians/oncologist can diagnose cancer with 79
percent accuracy while 91 percent correct diagnosis has
been achieved using machine learning techniques. The
procedure for early diagnosis of breast cancer must be
accurate and reliable to distinguish between benign
breast tumours from malignant ones.
II ) Related Work
1) The problem of detection of breast cancer from the
set of symptoms attracted many researchers worldwide.
Ebrahim et. al [2], have proposed the experiments using
Wisconsin Diagnosis Breast Cancer database to classify
Breast cancer Prediction using Machine
Learning Techniques
Ashok Deulkar, Dr.J.A.Laxminarayana
Dept.of Computer Science & Engg.,Goa College Of Engineering, Farmagudi-Goa, India,
2
Head of Department, Computer Science & Engg.,Goa College Of Engineering, Farmagudi-Goa, India.