Closed ramana2074 closed 3 days ago
Thanks for creating the issue in ML-Nexus!🎉 Before you start working on your PR, please make sure to:
Thanks for raising this issue! However, we believe a similar issue already exists. Kindly go through all the open issues and ask to be assigned to that issue.
@ramana2074 once check your points and let me know
Updated @UppuluriKalyani
Updated @UppuluriKalyani
I mean your contributions exceeded 200 points?
180 points are done
Is your feature request related to a problem? Please describe. Self-Organizing Map (SOM) algorithm for fraud detection using credit card application data
Describe the solution you'd like Fraud detection in credit card applications requires identifying patterns within the dataset that indicate potential fraudulent activity. The challenge is to process the dataset and apply the SOM algorithm for clustering and anomaly detection.
Approach to be followed (optional) Load the dataset from a CSV file, assign feature values to X and the fraud classification to y. Scale the features using MinMaxScaler from sklearn.preprocessing to bring values to a uniform range between 0 and 1. Initialize a SOM using MiniSom from the minisom library, with a 10x10 grid of neurons and an input length of 15 (number of features).Train the SOM using train_random for a specified number of iterations.The SOM will group credit card applications into clusters, helping to identify potential fraud through anomaly detection.