Over the last quarter-century, the opening range breakout has been one of the most powerful and successful trading tools employed by active traders. 24-hour electronic markets have all but eliminated the opening range breakout trading, a new outlook on an old indicator may give this favorite new life.
Last month we discussed the complexity required in testing and optimizing Arima-Garch trading models (see “Arima-Garch Out of the Lab, Into Trading,” Modern Trader, January 2018). We backtested our Arima-Garch hybrid model discussed last month to the S&P 500. Here is how it did.
In this first of two parts, we develop a hybrid autoregressive moving average model combining machine learning and advance modeling methods to classic backtesting.
Artificial intelligence and machine learning is complex and extremely expensive, but understanding how to use the
R Programming Language can help bring it into focus.
Back in the 1990s, approaching markets from a scientific viewpoint was anathema to trading practitioners, who tended to be bold personalities willing to take on risk.
During the past year, we have covered many different machine learning methods and discussed how they can be used in trading. Now it’s time to discuss real trading applications.
Supervised learning methods include back propagation neural networks, support vector machines and machine induction algorithms such as C.4.5 and rough sets.
