Banknotes Authentication

You can enter your own values and check your banknote is a valid one or not.

We can improve this model by changing the model architecture, and adding more training data. At this level I wanted to showcase my work towards implementation and deployment of Machine Learning model.

Development summary

High-level architecture of the application

Model summary

In this project I have trained data on 4 algorithms.
  1. Logistic Regression Classifier
  2. Random Forest Classifier
  3. KNN Classifier
  4. Support Vector Classifier

Among them, KNN and Logistic Regression shows accuracy ~100%

Classification Report (Logistic Regression)
                precision    recall  f1-score   support

           0       1.00      1.00      1.00       240
           1       0.99      0.99      0.99       172

    accuracy                           1.00       412
   macro avg       1.00      1.00      1.00       412
weighted avg       1.00      1.00      1.00       412
Confusion Matrix (Logistic Regression)