Banknote Authentication Dataset (Preprocessed for DEA)
Description
Banknote Authentication Dataset ( Preprocessed for DEA)
Files
Steps to reproduce
The dataset used in this study is based on the Banknote Authentication Dataset, originally available on Kaggle. The raw dataset contains four features extracted from images of banknotes using wavelet transform analysis: variance, skewness, kurtosis, and entropy. For the purposes of applying Data Envelopment Analysis (DEA), the raw data were further preprocessed. Specifically, negative values in the original dataset were transformed into positive values using Min–Max scaling, mapping the data into a standardized positive range. This preprocessing step ensures compatibility with DEA efficiency measurement models. No additional instruments, reagents, or manual data collection were involved. The preprocessing workflow was implemented using Python (NumPy and scikit-learn libraries), and the resulting dataset preserves the original structure while making it suitable for reproducibility in DEA-based experiments
Institutions
- Vysoka Skola Banska-Technicka Univerzita Ostrava