Back to Community
Strategy Advice using SVR

Experimenting with a modified SVR algorithm where I've artificially limited the leverage to 2.5 to meet the contest rules. Any advice for better performance? Short backtests generate positive returns but longer backtests always lose money.

Clone Algorithm
11
Loading...
Backtest from to with initial capital
Total Returns
--
Alpha
--
Beta
--
Sharpe
--
Sortino
--
Max Drawdown
--
Benchmark Returns
--
Volatility
--
Returns 1 Month 3 Month 6 Month 12 Month
Alpha 1 Month 3 Month 6 Month 12 Month
Beta 1 Month 3 Month 6 Month 12 Month
Sharpe 1 Month 3 Month 6 Month 12 Month
Sortino 1 Month 3 Month 6 Month 12 Month
Volatility 1 Month 3 Month 6 Month 12 Month
Max Drawdown 1 Month 3 Month 6 Month 12 Month
# Backtest ID: 55baa9870e25310c58872a49
There was a runtime error.
2 responses

I guess using machine learning approach to process the minute level date is not a good approach. The machine just endup learning the "noise" instead of any thing meaning full

After more backtests I agree my friend. Using daily data does generate some useful results but with trading costs the algorithm loses money overall. I've switched to developing other strategies for now.