GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → yazanobeidi → Fraud Detection

yazanobeidi / Fraud Detection

Licence: apache-2.0
Credit Card Fraud Detection using ML: IEEE style paper + Jupyter Notebook

Labels

jupyter-notebookmachine-learningscikit-learnkagglecard

Projects that are alternatives of or similar to Fraud Detection

Machinelearningcourse
A collection of notebooks of my Machine Learning class written in python 3
Stars: ✭ 35 (-39.66%)
Mutual labels:  kaggle, jupyter-notebook, scikit-learn
The Deep Learning With Keras Workshop
An Interactive Approach to Understanding Deep Learning with Keras
Stars: ✭ 34 (-41.38%)
Mutual labels:  jupyter-notebook, scikit-learn
Prediciting Binary Options
Predicting forex binary options using time series data and machine learning
Stars: ✭ 33 (-43.1%)
Mutual labels:  jupyter-notebook, scikit-learn
Computer Vision
Computer vision sabbatical study materials
Stars: ✭ 39 (-32.76%)
Mutual labels:  jupyter-notebook, scikit-learn
Kaggle Web Traffic Time Series Forecasting
Solution to Kaggle - Web Traffic Time Series Forecasting
Stars: ✭ 29 (-50%)
Mutual labels:  kaggle, jupyter-notebook
Python for ml
brief introduction to Python for machine learning
Stars: ✭ 29 (-50%)
Mutual labels:  jupyter-notebook, scikit-learn
Healthcheck
Health Check ✔ is a Machine Learning Web Application made using Flask that can predict mainly three diseases i.e. Diabetes, Heart Disease, and Cancer.
Stars: ✭ 35 (-39.66%)
Mutual labels:  kaggle, jupyter-notebook
Icon2017
Repository for the ICON 2017 hackathon 'multivoxel pattern analysis (MVPA) of fMRI data in Python'
Stars: ✭ 14 (-75.86%)
Mutual labels:  jupyter-notebook, scikit-learn
Machine Learning
notebooks with example for machine learning examples
Stars: ✭ 45 (-22.41%)
Mutual labels:  jupyter-notebook, scikit-learn
Data Science Complete Tutorial
For extensive instructor led learning
Stars: ✭ 1,027 (+1670.69%)
Mutual labels:  jupyter-notebook, scikit-learn
Mlkatas
A series of self-correcting challenges for practicing your Machine Learning and Deep Learning skills
Stars: ✭ 58 (+0%)
Mutual labels:  jupyter-notebook, scikit-learn
Deep learning projects
Stars: ✭ 28 (-51.72%)
Mutual labels:  jupyter-notebook, scikit-learn
Pythondatasciencehandbook
The book was written and tested with Python 3.5, though other Python versions (including Python 2.7) should work in nearly all cases.
Stars: ✭ 31,995 (+55063.79%)
Mutual labels:  jupyter-notebook, scikit-learn
Machine Learning Alpine
Alpine Container for Machine Learning
Stars: ✭ 30 (-48.28%)
Mutual labels:  jupyter-notebook, scikit-learn
Crime Analysis
Association Rule Mining from Spatial Data for Crime Analysis
Stars: ✭ 20 (-65.52%)
Mutual labels:  jupyter-notebook, scikit-learn
Ds and ml projects
Data Science & Machine Learning projects and tutorials in python from beginner to advanced level.
Stars: ✭ 56 (-3.45%)
Mutual labels:  jupyter-notebook, scikit-learn
Kaggle Carvana Image Masking Challenge
Top 15% ranked solution to the Carvana Image Masking Challenge on Kaggle
Stars: ✭ 13 (-77.59%)
Mutual labels:  kaggle, jupyter-notebook
Interview
Interview = 简历指南 + LeetCode + Kaggle
Stars: ✭ 7,207 (+12325.86%)
Mutual labels:  kaggle, jupyter-notebook
The Hello World Of Machine Learning
Learn to build a basic machine learning model from scratch with this repo and tutorial series.
Stars: ✭ 41 (-29.31%)
Mutual labels:  jupyter-notebook, scikit-learn
Lung Diseases Classifier
Diseases Detection from NIH Chest X-ray data
Stars: ✭ 52 (-10.34%)
Mutual labels:  kaggle, jupyter-notebook
View All Similar Projects ➔

Credit Card Fraud Detection using Machine Learning

Credit card fraud is a growing issue with many challenges including temporal drift and heavy class imbalance. This project attempts to tackle class imbalance using state-of-the-art techniques including Adaptive Synethtic Sampling Approach (ADASYN) and Synethetic Minority Oversampling Technique (SMOTE). Over 280k real transactions made in Europe in September 2013 [1] are used as the training dataset. Three types of machine learning models are compared: Random Forest, Support Vector Machine, and Multi-Layer Perceptron. Results show that the optimal sampling method for an imbalanced dataset is dependent on the dataset and the model being used.

This project has the following components:

a) IEEE style Paper in PDF format

b) Jupyter Notebook walking through machine learning tests conducted. You can run view and run them yourself. Included are also comments, reasoning, and figures. For your convenience I have included a copy of the original dataset [1] in this git repo, however please refer to the original source for the most up-to-date version.

This project was done as part of SYDE 522: Machine Learning at the University of Waterloo in Winter 2017.

Installation

  1. Clone the project:

    $ git clone https://github.com/yazanobeidi/fraud-detection.git && cd fraud-detection

  2. Pip-install dependencies. For example using a virtualenv:

    $ virtualenv env && source env/bin/activate && pip install -r requirements.txt

Usage

a) Read the Paper (PDF):

credit_card_fraud_detection_yazan_obeidi.pdf

b) Run the Jupyter Notebook:

  1. First unzip the dataset:

$ unzip data/creditcardfraud.zip

  1. Generate a balanced dataset using ADASYN resampling (this will take several minutes):

$ python adasyn.py

  1. Run the notebook:

$ jupyter notebook

Authors

Yazan Obeidi

Copyright

2017, Yazan Obeidi

References

[1] Kaggle. (2017, Jan. 12). Credit Card Fraud Detection [Online]. Available: https://www.kaggle.com/dalpozz/creditcardfraud

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].