Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Strategies & Market Trends : Neural Nets - A tool for the 90's -- Ignore unavailable to you. Want to Upgrade?

To: LastShadow who wrote (648)	9/1/1999 9:25:00 AM
From: Optim	Read Replies (3) \| Respond to of 871

Hi Lastshadow, Hope you don't mind a quick question that may have relevance to the thread. Have you ever used Wavelets to filter your data? I have been experimenting with them in filtering my data to be used as an input to my neural networks. The only thing I am unsure about is how one 'tunes' the Wavelet to extract the correct information and eliminate the unwanted noise. Would it be wise to try and determine the underlying cycles in the series (ie. Fourier or spectral analysis) and then tune the wavelet to those frequencies? Or is it more of a trial and error approach whereby you measure the impact on the nets profitability? Also, have you ever experimented with applying techincal indicators (momentum, spreads, etc.) to the filtered data? Is it better to normalize the wavelets output, such as a percent change? In the past I have used related issues as a lead or lag to my predicted output. What I have found is that quite often the lead/lag relationship terminates during the out-of-sample period, making the input useless in the real world. A great example is the spread between the Bonds and the S&P. They switch from positive to negative correlation and back over the short-term, although long term they have remained positively correlated. BTW, if anyone else has experiemented with wavelets feel free to join in. Thanks for any advice you can offer! Optim