Travis — Machine Learning freelancer in Midrand

This trading bot makes heavy use of vectorbtpro to backtest all defined strategies at various timeframes for each symbol in a portfolio that matches certain criteria. Different symbols usually perform quite differently to different strategies and different parameters. So the bot tests a symbol against all strategies, decides which the best is for each symbol based on the results of vectorbtpro backtesting and then generates signals accordingly using vectorbtpro's newest simulated order from those backtests. Strategies are defined by as little code as possible to make it easy to create different strategies at will while still inheriting (OOP) from a more complex 'Strategy' class to quickly enable all functions related to strategies such as cross validation, custom graph plotting, custom scoring etc. Graphs related to the indicators of strategies are dynamically built on top of a few important vectorbtpro graphs so that we don't have to manually define different graphing functions to visualize each different strategy.