Automating Data Science for the IOT

The big challenge with machine data is the weak signal to noise ratio. The patterns are too tiny and too many spread over a large amount of data. Also patterns change frequently. All these variability makes it extremely challenging to dig insights/signals out by the traditional approach of generating models manually. This requires applying machine automation and machine intelligence to even finding the patterns on a continuous basis. In this talk we will demonstrate how we have applied this to solve problems of predictive maintenance for Fortune 500s.