Model for anomalies detection

[RocketFan]

I will try to implement SOM clustering to detect anomalies. For this, dataset need to be divided into chunks, which then will be forwarded to the algorithm to group them.

Problem can be also described as Fraud detection, which can be solved with other algorithms:

• LSTM autoencoders (e.g. DeepAnt)
• Graph neural network
• Other clustering algorithms

[RocketFan]

https://www.superdatascience.com/blogs/the-ultimate-guide-to-self-organizing-maps-soms - nice tutorial for SOM algorithm