NAB

Part of the streaming anomaly detection benchmark dataset NAB has keyboard typing data (amongst other interesting sources) [1]. Comparing the algorithms would be quite interesting; the algorithm in [2] is unsupervised and doesn't need training data. The benchmark dataset and algorithms are open-source. https://github.com/numenta/NAB/tree/master/data#real-data Ahmad & Lavin, Neurocomputing 2016, https://www.sciencedirect.com/science/article/pii/S092523121...

Would be interested to see the results on a benchmark dataset for online anomaly detection, comparing to those approaches used in practice: https://github.com/numenta/NAB#the-numenta-anomaly-benchmark...

Jeff Hawkins gets shit on a lot in ML because his theories haven’t produced models with results as good as the mainstream approach, but I’m glad they keep working at it and keep coming up with interesting ideas. I just ran across a paper [1] from Numenta on Time Series Anomaly Detection using HTM last night which provide a benchmark[2] with some existing approachs. (But it seems to me there is no NN based approach in them. ) [1] Unsupervised real-time anomaly detection for streaming data http://www.sciencedirect.com/science/article/pii/S0925231217... [2] https://github.com/numenta/NAB

And more on research-level techniques: Ahmad et al. "Unsupervised real-time anomaly detection for streaming data": http://www.sciencedirect.com/science/article/pii/S0925231217... Anomaly detection benchmark (dataset and evaluation): https://github.com/numenta/NAB

See https://github.com/numenta/nab for anomaly detection results on real-world data, with comparisons to Twitter and Etsy Skyline.

Has anyone played with Anomalyzer yet? I'd like to get the anomaly probability for every data instance of a CSV but it's unclear to me if this is possible. I want to run it on the Numenta Anomaly Benchmark dataset (https://github.com/numenta/NAB) to see how it compares to other anomaly detection algorithms.

NuPIC, the Open Source project upon which Grok (Numenta's commercial product) is built has an active community at http://numenta.org/lists/. We had a workshop and hackathon a few weeks ago, more details can be found at http://numenta.com/learn/ and http://numenta.org/blog/2014/10/30/2014-fall-hackathon-outco..., respectively. See, also, https://github.com/numenta/nupic.research for the latest research efforts, https://github.com/numenta/NAB for forthcoming benchmarks, and of course http://numenta.org/ for overall details about NuPIC and http://numenta.com/ for Numenta, the company.