I am building an anomaly detection system of event sequence data (transactions). For each timestep, a transaction can be in any of 76 different stages.

My dataset is therefore a 3D array of size(m,t,N).

m is number of samples (~40 000), t = the length of the longest transaction (I am zero padding all other sequences of shorter length), N is the number of possible events at each timestep. $x_{m,t,N} = \{0,1\}$ where $x_{v,u,w} = 1$ if transaction v is in event w at timestep u otherwise it's 0.

So far I have created an LSTM Variational Auto Encoder in Python with Keras and doing outlier detection by applying Local Outlifer Factor on the latent representations of the transactions. It's based on this paper https://arxiv.org/abs/1906.10896 and following various blogs such as https://blog.keras.io/building-autoencoders-in-keras.html.

I would like to compare the results with other techniques. I was wondering if anyone has any other suggestions on algorithms and techniques for anomaly detection in unlabeled event sequence data?


1 Answer 1


A simple comparison is to use the reconstruction error as the anomaly score. This can be done instead of, or in addition to, the Local Outlier Factor that you have now. You can also try other ways of computing the anomaly score from the latent feature vector. Some popular alternatives are:

  • Mahalanobis distance on the
  • Fitting a Gaussian Mixture Model, and use the probability density function

A completely different approach would be to use a self-supervised training setup instead of the autoencoder. Such as Skip-Gram or predicting future time-frame.

  • $\begingroup$ Hi Jonnor, thank you for the reply, do you have any articles or posts which you can point to with regards to Skip-Gram or predicting future time-frame? I would assume that the Skip-Gram would be similar to NLP technique in order to predict the probability of a word given a context? Predicting future time-frame, would that be applying a sliding window to try and predict the next event? $\endgroup$
    – kspr
    Commented Aug 24, 2020 at 11:20
  • $\begingroup$ Would you check my question to see if LM (BERT) or Skip-Gram or predicting future time-frame make sense for my problem concerning Self-supervised approach? $\endgroup$
    – Mario
    Commented Oct 11, 2023 at 19:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.