> In my 3 minutes of reading it looks like the Kalman filter is designed to > better approximate the actual state of a system from a series of (erroneous) > inputs. It sounds like the system needs to have a model, for instance... a > rocket. A rocket is a well defined system, using the basic Newton equations > of motion. For the stock market, you would first need a model, and then > this technique would help you to better curve fit to that model. > > Am I correct on this point? > > What would you use as your model.. some kind of momentum trading approach? > This isn't exactly newtonian physics here... >
The description of the Kalman filter may look intimidating in Wikipedia, but there is really not much mystery there. JBT gets a stream of prices and balances. These are notoriously noisy observations. The simplest filter is a SMA, which just averages the last N observations. A little more interesting filter is EMA. The Kalman filter is just another filter, it's just a little more complex one. If you apply it to the stream of prices, it would come up with what it considers a "true" price, i.e. a fancy interpolation of the previously observed prices. The same goes for balances. Once we have these filtered prices and balances, we can use them in the indicators, such as the Tension indicator in JBT. That's how I envision the use of the Kalman filter in JBT. -- You received this message because you are subscribed to the Google Groups "JBookTrader" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/jbooktrader?hl=en.
