Machine learning has revolutionized the way we approach problems and has opened up new possibilities for solving complex issues. One such problem is the detection of fake notes, which has been an ongoing challenge for financial institutions and businesses. It is possible to train models that can precisely predict the veracity of banknotes using machine learning. These algorithms can learn to recognise patterns and features that separate authentic notes from fakes by training them on vast datasets of both real and counterfeit notes. The way we approach challenges has been transformed by machine learning, which has also created new opportunities for resolving challenging problems. The detection of counterfeit notes is one such issue, which has been a persistent difficulty for businesses and financial institutions.
This project aims to develop a machine learning model to predict the authenticity of banknotes. The model uses features such as variance, skewness, kurtosis, and entropy of wavelet-transformed images of the banknotes. The target value is 0 for real banknotes and 1 for fake banknotes.
✅ The dataset used in this project is the Banknote Authentication Dataset from the UCI Machine Learning Repository.
✅ It contains 1,372 instances of banknotes, each with five numeric input variables and one binary target variable.
✅ Use a pairplot to plot it 
✅ Balanced the dataset 
✅ Used model using intel oneAPI
Building application using intel oneDAL:The Intel oneAPI Data Analytics Library (oneDAL) contributes to the acceleration of big data analysis by providing highly optimised algorithmic building blocks for all phases of data analytics (preprocessing, transformation, analysis, modelling, validation, and decision making) in batch, online, and distributed processing modes of computation.The library optimizes data ingestion along with algorithmic computation to increase throughput and scalability.
✅ The result is as shown
This project requires the following dependencies:
✅ Python 3.7 or higher
✅ Scikit-learn
✅ XGBoost
✅ Pandas
✅ NumPy
✅ Matplotlib
✅ Seaborn
To run the project, follow these steps:
- Clone this repository to your local machine.
- Install the dependencies listed above.
- Open a terminal and navigate to the project directory.
- Run the fake_currency_detection.ipynb Jupyter notebook to train and evaluate the machine learning model.
This project is licensed under the MIT License - see the LICENSE file for details.