optimize

To optimize VectorBT strategy parameters, this skill exhaustively tests parameter grid combinations and scores results using metrics like total_return, sharpe_ratio, and max_drawdown to identify high-performing configurations.

You can backtest EMA crossover strategies on Indian and US market data by loading data via dotenv, DuckDB, or OpenAlgo, applying TA-Lib indicators, and modeling delivery fees to generate benchmark comparisons.

Yes, you can generate heatmaps for backtesting parameter tuning results. The skill outputs Plotly visualizations and CSV files containing performance metrics to visually map optimal parameter combinations.

VectorBT parameter optimization works with OpenAlgo data. The skill optionally uses OpenAlgo to load market data, compute trades, and evaluate strategy performance against market benchmarks.

During VectorBT backtesting, the skill calculates total_return, sharpe_ratio, max_drawdown, and total trades. These metrics are output to CSV files alongside Plotly visualizations for comprehensive performance evaluation.

The best way to find optimal TA-Lib indicator parameters is through exhaustive parameter grid search. This skill systematically tests combinations to produce heatmaps and benchmark comparisons for balanced risk and return.