Scribd
Upload
4 views

Breast_Cancer_Classification_Report

This project report details the development of a machine learning model for classifying breast cancer as benign or malignant using the Wisconsin Breast Cancer Dataset. The SVM classifier, optimized through hyperparameter tuning, achieved high accuracy compared to other models like Random Forest and Logistic Regression. Future work includes incorporating more data and exploring deep learning techniques for real-time diagnostic support.

Uploaded by

Khadija Tajir
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
4 views

Breast_Cancer_Classification_Report

This project report details the development of a machine learning model for classifying breast cancer as benign or malignant using the Wisconsin Breast Cancer Dataset. The SVM classifier, optimized through hyperparameter tuning, achieved high accuracy compared to other models like Random Forest and Logistic Regression. Future work includes incorporating more data and exploring deep learning techniques for real-time diagnostic support.

Uploaded by

Khadija Tajir
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Breast Cancer Classification Using

Machine Learning
Data Science Project Report

Author: Khadija Tajir

Date: April 06, 2025


Table of Contents
1. 1. Introduction
2. 2. Problem Statement
3. 3. Dataset Overview
4. 4. Data Cleaning
5. 5. Exploratory Data Analysis (EDA)
6. 6. Data Preprocessing
7. 7. Predictive Modeling (SVM)
8. 8. Model Optimization
9. 9. Model Comparison
10. 10. Evaluation Metrics
11. 11. Results and Discussion
12. 12. Conclusion
13. 13. Future Work
14. 14. References
Introduction
This report documents a comprehensive machine learning project aimed at classifying
breast cancer as benign or malignant using predictive analytics.
Problem Statement
Early detection of breast cancer significantly improves the chances of successful treatment.
The goal is to develop a robust classification model to assist medical diagnosis.
Dataset Overview
The dataset used in this project originates from the Wisconsin Breast Cancer Dataset. It
contains features computed from digitized images of fine needle aspirate (FNA) of breast
masses.
Data Cleaning
Initial steps involved checking for null values, handling duplicates, and removing irrelevant
columns such as unnamed indexes or IDs.
Exploratory Data Analysis (EDA)
EDA revealed relationships between variables such as mean radius and texture. Distribution
plots, correlation heatmaps, and class balance visualization were performed.
Data Preprocessing
StandardScaler was used for normalization, and label encoding was applied to the target
variable to convert categories into binary format.
Predictive Modeling (SVM)
An SVM classifier was trained using the preprocessed data. The kernel function used was
RBF, which works well for non-linear classification.
Model Optimization
Hyperparameter tuning was done using GridSearchCV to optimize the performance of the
SVM classifier, adjusting parameters like C and gamma.
Model Comparison
Other models like Random Forest, Logistic Regression, and KNN were compared based on
accuracy, precision, and recall.
Evaluation Metrics
Confusion matrix, classification report, ROC-AUC score, and accuracy were used to evaluate
the model’s performance.
Results and Discussion
The optimized SVM model achieved high classification accuracy, outperforming baseline
models in most metrics.
Conclusion
The project successfully built a predictive model for breast cancer classification,
highlighting the strength of SVM in medical diagnosis.
Future Work
Incorporate additional data, experiment with deep learning, and deploy the model as a web
application for real-time diagnosis support.
References
1. UCI Machine Learning Repository
2. scikit-learn documentation
3. Breast Cancer Research Journals

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy