I just started using Cycle Highligher. I like the approach taken here because it uses correlation to determine if the results represent a true cyclic component that is representative of the prices.
My understanding is that it is valid only for the last data. This limitation of course that means that it can not be used in a backtest. Wondering if anyone has modified it so it can be used in a backtest. It would be very slow, but that's OK. Ara
