search

curiousily / Credit-Card-Fraud-Detection-using-Autoencoders-in-Keras

iPython notebook and pre-trained model that shows how to build deep Autoencoder in Keras for Anomaly Detection in credit card transactions data
https://www.curiousily.com/posts/credit-card-fraud-detection-using-autoencoders-in-keras/
MIT License
505 stars 279 forks source link

Why did we use the threshold of 2.9 #3

Open gowthambalachandhiran opened 6 years ago

svjack commented 5 years ago

I think, this reconstruction distance based method for fault conclusion valid. should take the count based on distance linspace counts change. When the value mass blow change into small, this is the character for fault. Not simple setting to one num, but can change with precision recall you need.

svjack commented 5 years ago

one facet can defined by precision and recall in valid set, the other facet may be defined by diff between linspace range num count, use the neighborhood of monotone change point choose as the threshold. And the Second-order derivative of linspace range num count may be a prefered a criterion for early-stop of autoencoder, the train loss for generalize the model but the Second-order derivative of linspace range num may measure the discrimination between fraud and normal points. This is my suppose, Dose there some criterions for convergence of unsupervised learning for fraud detection ? If you know, Please tell me.

Haythemmighri commented 5 months ago

execuse mei just wanna ask you one simple question, why did you drop the 'Time'. data = df.drop(['Time'], axis=1) could you please response to this question