Developing a successful strategy is a process with many steps, described in the Build Better Strategies article series. At some point you have coded a first, raw version of the strategy. At that stage you’re usually experimenting with different functions for market detection or trade signals. The problem: How can you determine which indicator, filter, or machine learning method works best with which markets and which time frames? Manually testing all combinations is very time consuming, close to impossible. Here’s a way to run that process automated with a single mouse click. Continue reading “Build Better Strategies, Part 6: Evaluation”
Tag: Walk forward analysis
Why 90% of Backtests Fail
About 9 out of 10 backtests produce wrong or misleading results. This is the number one reason why carefully developed algorithmic trading systems often fail in live trading. Even with out-of-sample data and even with cross-validation or walk-forward analysis, backtest results are often way off to the optimistic side. The majority of trading systems with a positive backtest are in fact unprofitable. In this article I’ll discuss the cause of this phenomenon, and how to fix it. Continue reading “Why 90% of Backtests Fail”
Better Strategies 5: A Short-Term Machine Learning System
It’s time for the 5th and final part of the Build Better Strategies series. In part 3 we’ve discussed the development process of a model-based system, and consequently we’ll conclude the series with developing a data-mining system. The principles of data mining and machine learning have been the topic of part 4. For our short-term trading example we’ll use a deep learning algorithm, a stacked autoencoder, but it will work in the same way with many other machine learning algorithms. With today’s software tools, only about 20 lines of code are needed for a machine learning strategy. I’ll try to explain all steps in detail. Continue reading “Better Strategies 5: A Short-Term Machine Learning System”
Build Better Strategies! Part 3: The Development Process
This is the third part of the Build Better Strategies series. In the previous part we’ve discussed the 10 most-exploited market inefficiencies and gave some examples of their trading strategies. In this part we’ll analyze the general process of developing a model-based trading system. As almost anything, you can do trading strategies in (at least) two different ways: There’s the ideal way, and there’s the real way. We begin with the ideal development process, broken down to 10 steps. Continue reading “Build Better Strategies! Part 3: The Development Process”
Better Tests with Oversampling
The more data you use for testing or training your strategy, the less bias will affect the test result and the more accurate will be the training. The problem: price data is always in short supply. Even shorter since you must put aside some part for out-of-sample tests. Extending the test or training period far into the past is not always a solution. The markets of the 1990s or 1980s were very different from today, so their price data can cause misleading results.
In this article I’ll describe a simple method to produce more trades for testing and training from the same amount of price data. As a side effect, you’ll get an additional metric for the robustness of your strategy. Continue reading “Better Tests with Oversampling”