Aim of the Project

To predict and analyze the fraudulent transactions that happen on daily basis, using Credit cards. Provide countermeasures for the same. Build a Model to prevent such transactions using Data Science, and Machine Learning Applications.

Life Cycle of the Project

Extracted the data from Kaggle open source. Performed Data Exploration to understand the descriptive stats w.r.t. the data, in order to manipulate the data to build a robust ML model. Used Pandas, & Numpy for Data Pre-processing, to decrease the redundancy, by taking care of the missing values, and duplicates. Carried out extensive EDA using LMPLOT, COUNT PLOT,& SCATTER PLOTS to understand the data, its outliers and as its a classification problem, To understand the ratio of Legit : Fraud Transactions. Used Under Sampling technique, to convert data to 50:50 ratio & Enhance model accuracy. Used BOX-PLOT Method to detect and handle the Outliers = To avoid OVERFITTING of the Model. Trained the model using Sci-Kit Learn. Used Logistic Regression Classifier to build the ML Model with Utmost Accuracy. Build & Deployed the Model with 94% Accuracy.

Results from the Project

Check out the Detail Project Overview on GitHub Repository

Technologies Used | Python | Seaborn | Numpy | Pandas | Scikit Learn |

| Flask | Matplotlib | Numpy |