3

I have recently completed an MSc in Control Systems from a top university. It seems to me that control theory must have an application within data science. I would like to apply my degree within this domain, but I want to be sure that it is relevant to the role of a data scientist.

The topics which I have particular interest and experience in are State Space Control, Systems Identification, Model Predictive Control and Optimal Control. I imagine that effective management of any large dataset must involve modelling of the system in terms of transfer functions/state space models (based on large sets of historical input/output data). These models could then be used to predict the evolution of a market/variable over time, and therefore optimise a given cost function such as profit, risk etc.

If this kind of role exists within data science/ other areas, can you please give me more information/ ideas of job roles/ industries to research.

Mark Roche
  • 31
  • 2
  • I think this is a very broad question. Can you narrow it down to a particular example problem and how much you know about how control theory applies already? – Sean Owen May 18 '15 at 07:34

1 Answers1

2

Have you tried the Internet search? The results should be able to answer most, if not all, of your questions. The topics of your interest sound like rather general or high-level. I'm sure that they can, in one form or another, be applied in the data science context. In my opinion, those topics are more related to operations research (OR), therefore, I would recommend you to perform some research on the Internet on the intersections between control systems (theory) and data science.

Having said that, first thing that comes to my mind is that the most likely candidate for use of control theory concepts and methods in data science context would be distributed systems and algorithms for data analysis, such as MapReduce (Hadoop, etc.), as well as other parallel processing systems. If there exist an intersection between OR's area of optimization and control theory, then it very well could be used for big data algorithms optimization, among other tasks.

Aleksandr Blekh
  • 6,518
  • 4
  • 28
  • 54