Member-only story
One of my favorite quote from Steve Jobs, “That’s been one of my mantras - focus and simplicity. Simple can be harder than complex; you have to work hard to get your thinking clean to make it simple.”… After one year of machine / deep learning study, I’m realized simplicity is importance to make successful machine / deep learning projects.
Recently, I found there are interesting machine learning powered API from Microsoft Azure Cloud, Anomaly Detector [Preview]. This API help you easily to figure out abnormal points from your time series data without any machine learning coding based on their pre-trained machine learning model. It can be applied into various practical use cases like system performance / behavior abnormal detection / monitoring, fraud detection, etc…
There are 2 detection modes in Anomaly Detector API, 1st is Batch Detection and 2nd is Steaming Detection.
- Batch detection - By sending your time series data at once, the API will generate a model using the entire series, and analyze each data point with it.
- Streaming detection - By sending new data points as you generate them, you can monitor your data in real time. A model will be generated with the data points you send, and the API will determine if the latest point in the time series is an anomaly.
You can refer to their official product page and API definition page to understand more.
