ET News & Sponsor Info
General Topics
Markets
Technical Topics
Brokerage Firms
Company Specific
Tools of the Trade
Trading for a Living
Community Lounge
Site Support

# What kind of R^2 (or other metrics) do you see for your ML algos?

Discussion in 'Automated Trading' started by nooby_mcnoob, Mar 31, 2019.

1. ### sle

Hmm. My approach has been to normalize any signal I use against it's standard deviation (cross-sectional or longitudinal), fit a sigmoid to clip the extremes and then use a hysteresis band to reduce trading. That removes the necessity for forecasting, but I am now actually starting to think that forecasting the returns has it's merits.

#11     Apr 1, 2019
nooby_mcnoob likes this.
2. ### nooby_mcnoob

Sadly I need pictures to understand wtf you're talking about.

#12     Apr 1, 2019
3. ### Kevin Schmit

Since most sigmoid functions map the interval -inf,+inf to the interval 0,1 (or -1,1), you might be able to skip the nomalizaton by standard deviation step, and just adjust the gain or slope parameter of your sigmoid to compensate.

That would serve the same function of the "filter out signals near zero" method I mention above.

I often use the term "forecast" pretty broadly. I more or less consider any numeric signal that gets you in or out of a trade a forecast of something.

Last edited: Apr 2, 2019
#13     Apr 1, 2019
4. ### sle

Yeah, true. Normalization allows me to avoid calibrating/fitting almost completely by taking a sigmoid of a z-score and assuming some reasonable window like +/- 2 stdevs to clip by. Fitting a sigmid directly would require running iterative backtests. I feel, possibly incorrectly, that as a process it reduces the possibility of curve fitting, especially for low quality signals (which describes almost all of my universe, sadly).

Hmm, not sure about that, I think your way is superior especially when you have decent predictive power. In my method, I apply the same band for going from 0 to say 0.5 as for going from 2 to 2.5 (if you think in standard deviations, as I do). In your case (let's call it "hollowing the signal out") you actually ignore the signal where it counts - i.e. when the signal is weak.

I've been historically thinking in terms of "signals" and it worked for me more or less. I.e. "if X I want to buy Q, the bigger the X the more I want it". But now I am thinking that using "E(Q) = f(X)" as a proper forecast allows for a lot of niftier things like transaction optimization, for example.

#14     Apr 2, 2019
ET IS FREE FOR TRADERS BECAUSE OF THE FINANCIAL SUPPORT FROM THESE SPONSORS:
 Alpaca Commission Free Stock Trading API AMP Global Clearing Futures and FX Trading Bookmap Visual Trading Platform Earn2Trade Trading Education and Funding Challenge Interactive Brokers Gateway to World Markets Jigsaw Trading Advanced Trading Tools KJ Trading Systems Trader Education Services Lightspeed Equities & Options Trading MotiveWave Full-Featured Trading Software MultiBank Group Financial Derivatives Providers NinjaTrader Trading Software & Brokerage Optimus Futures Futures Trading Platforms and Order Routing ORATS Option Data & Backtesting Polygon.io Real-Time & Historic Data Raltin Finance Research Tools Rithmic Futures Trade Execution Platform SpreadProfessor Spread Trading Instruction TD Ameritrade Free Futures Education and Specialists TopstepTrader We Fund Traders TraderDock Your Path to Professional Trading TradersStudio System Development Platform TradeZero America Commission Free Trading Trading Technologies Trading Software Provider Tradovate Commision-Free Futures Trading TrendSpider Automated TA Software