After learning about the delta-neutral trading algorithm applied by the trading club of our college, we wondered whether we could create a profitable, intuitive, and easy-to-understand trading algorithm without heavy math.
Trading using the Bollinger Bands is one of the most basic trading algorithms out there. Even though the performance of Bollinger Band-based algorithms more often than not losses to simple buy and hold strategies, we think that moving average curves are significant to the movement of the stocks’ prices. We added volume, the slope of moving averages, and the stocks’ relative strength. We think that by adding these parameters, we would be able to find the “momentum” that pushes the stock’s price higher.
By manually finding out the first coefficients, we got a decent annualized return (29%) by backtesting all Russel 3000 and S&P 500 stocks. We are now already maintaining a portfolio using this algorithm. We would now proceed to try to apply machine learning algorithms to find the optimal coefficients.
Log in or sign up for Devpost to join the conversation.