search

BLarzalere / LSTM-Autoencoder-for-Anomaly-Detection

AI deep learning neural network for anomaly detection using Python, Keras and TensorFlow
192 stars 75 forks source link

Is the model using scalar value #3

Open kaku2000 opened 2 years ago

kaku2000 commented 2 years ago

Seems the dataset is using scalar value here

merged_data = merged_data.append(dataset_mean_abs)

Is it right you're using lstm for scalar data?

BLarzalere commented 2 years ago

There are no issues with using LSTM's on scalar data. A lot of financial planning such as stock market predictions, marketing and inventory predictions are done using LSTM time series.

kaku2000 commented 2 years ago

At least should use raw time series as one sample here for anomaly detection, don't you think so.

That's different to do predictions in those time series data.

2021年12月23日(木) 0:19 Brent Larzalere @.***>:

There are no issues with using LSTM's on scalar data. A lot of financial planning such as stock market predictions, marketing and inventory predictions are done using LSTM time series.

— Reply to this email directly, view it on GitHub https://github.com/BLarzalere/LSTM-Autoencoder-for-Anomaly-Detection/issues/3#issuecomment-999653122, or unsubscribe https://github.com/notifications/unsubscribe-auth/AR3TPC4VA7WXT3HKSSPQB5LUSHT7NANCNFSM5KSAO2DA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you authored the thread.Message ID: <BLarzalere/LSTM-Autoencoder-for-Anomaly-Detection/issues/3/999653122@ github.com>