out-of-sample Archives - アルゴリズムと機械の外国為替戦略

脂肪質の利益のための機会のため、多くのトレーダー、外国為替に魅了されて, 株と比較すると特に. まだ, when trading forex the inherent leverage can affect traders’ emotions, leading to over-trading, loss-chasing and second-guessing. A mechanical trading system can provide the winning solution.

Why build a trading system?

Manual trading works well for many stock traders, especially those using buy-and-hold strategies for a limited number of favorite picks, yet forex traders need better tools and stronger discipline in order to be profitable.

In any industry, a well-built machine is more efficient than any human

A well-built mechanical trading system offers a trader the best of both worlds: technology and math give the trader the ability to spot and take advantage of market inefficiencies and harvest gains in a busy, cluttered environment, while freeing him or her from the emotional roller-coaster ride of trading.

Find your own niche

There are plenty of trading systems available nowadays; the key to forex trading success lies in finding or adapting the “right” system for your own needs and style. Once you’ve decided the parameters for success, including your overall goals and objectives for trading, personal tolerance for risk, and the amount of capital to be devoted to trading, a system can be built to fit you like a glove.

When building a system, there’s plenty of room for specialization and individualization – If everyone were trading the same way, spreads would soon disappear. Like fast-moving mosquitoes buzzing around a lumbering elephant, many traders earn an excellent living by capitalizing on opportunities inevitably created by the movements of much-larger players in the marketplace; the key is to gather an actionable set of patterns and indicators that fits your personal style.

If a pattern is noticeable, then it’s probably actionable

The first step is to search through past trading data in order to identify patterns and conditions which appear to consistently offer profitable trading opportunities. Historical price and volume charts often show patterns which appear to signal upcoming price moves, and technical indicators will help clarify an otherwise-fuzzy picture.

Try looking at different combinations of indicators over different historical time periods to see if they may give predictive power in spotting market turns or changes in trend. A “caveman-style” approach to quickly testing your hunches can be as simple as finding a noticeable pattern on a printed chart, then holding a sheet of paper over the upcoming section and “guessing” what will happen next; when you’re right, you may have found a winning pattern.

テスト & 最適化

Once you’ve identified a fairly-predictable pattern by looking at charts, it’s time to think about how to trade it profitably. You should consider how it fits with your personal trading style, including risk management. The patterns and indicators upon which your system is based can be simple or complex, as long as they work in the marketplace and fit your circumstances.

The next step is to translate these patterns and scenarios into mathematical coding, to form a set of trading rules which can be fully tested. You can do this yourself, or you can rely on the services of a coding expert to help accomplish this. After you’ve created the foundation for a system, it can be tested objectively by changing the inputs to find the optimal conditions for trading, such as the best combinations of currency pairs, 停止, and other variables.

You can use software to quickly test multiple combinations of indicators. The key is to identify predictable patterns which will give you the confidence to trade when you see them appear, 長いか短いかどうか, then fine-tune them to maximize your gains. It’s important to realize that more complexity isn’t necessarily better – A super-complex system probably won’t fatten your wallet if it only signals a trade once every ten years and your computer happens to be offline when that finally occurs.

Don’t become married to your system

最も重要なこと, if your indicators aren’t working out during testing as you had hoped, don’t become emotionally invested in “proving” that they work. 代わりに, step back and take a broader look – Perhaps it’s time to use a different combination of indicators, or change your approach altogether.

During testing and optimization, it’s important to leave untouched some of your historical market data as untested “out-of-sample” data while you work through testing your system using in-sample data. For statistical purposes during testing, you can only use data once before modifying your system; then of course it becomes part of your in-sample data. If you contaminate your test data, それです, if you rely on a certain date range of data to first develop and test your system, then later re-test your modified system with the same data, the results may be skewed. だから, use your out-of-sample data only for final testing and tweaking 後 you’ve built your system, so you can be sure that such data is “pure” and not already accounted for in the system.

Be sure to back-test any prospective new system over reasonably long periods, so you’ll have an idea how it performs long-term. と, check the results when using different lengths for your moving averages. また, it’s worthwhile to test your system widely across different forex pairs, even those you don’t typically trade – You may be surprised to find that your system does especially well in a market that you haven’t tried before.

Implementation

Even though testing and minor tweaking should be thought of as an evolutionary process that continues during the life of your trading, at this point you’re ready to implement your system by using it to trade with real money. If you’ve done your homework well, and you stick to the rules that your testing has proved will work under specific conditions, then you’ll be confident in proceeding forward.

Stick to the proven rules and you’ll be successful

Societies rely on laws to govern the behavior of their citizens because they’ve learned over time (tested and optimized) what works. 同様に, in order to be successful with forex you should adhere to the consistent trading rules that you’ve established in a scientific manner. If you stick to the rules, your mechanical trading system can help you win the forex game.

Earlier this month, we looked at an article from Forex Crunch that covered the first three steps for building a new quantitative Forex strategy. Those first three steps covered brainstorming strategy ideas, defining the rules, and optimizing the parameters.

At that point we had a strategy that we had reason to believe would perform well in a trading situation. The next steps would involve properly testing our strategy in order to prove its value.

After brainstorming, defining rules, and optimizing a new Forex strategy, the next steps involve rigorous testing.

Forex Crunch has since published the second three steps for creating a robust Forex system. This post focuses on testing the system that was created with the first three steps. It suggests starting with in-sample testing, then moving to out-of-sample testing, and then suggests some even deeper methods of testing.

The Most Important Point Regarding Testing

While there is plenty of great information in the article about the different types of testing that should be performed on a new Forex strategy, the most significant point that the article makes is actually stated in the introduction:

Relying on the CAR (compound annual return) figure is not always a good idea because this metric does not take into account the risk that was involved in producing those gains.

This point is extremely basic, which makes it easy to overlook. While a strong compound annual return is the end goal of every trader, we all know that there are many ways to arrive at a strong compound annual return, and some of them aren’t worth the effort.

In addition to compound annual return, we also need to be concerned with how the strategy performs from a risk perspective. Looking at statistics like maximum drawdown, プロフィットファクター, Sharpe ratio, and winning percentage gives us a better idea of how the strategy arrives at its compound annual return.

This bigger picture view will give us a more qualified overview of what trading the strategy will feel like. We can use that to determine if the amount of risk the strategy exposes our capital to is in our tolerable range.

Testing Forex Strategies

Testing on in-sample data is where we can fine tune our strategies in order to get the return and risk statistics into the desired range. From there, we move to out-of-sample testing where we attempt to replicate those statistics on a fresh data set.

There are also testing methods like Walk-Forward Optimization and Monte Carlo Simulations that can shed even more light onto how our new system can be expected to perform in live trading. The important thing to watch for during this testing phase is consistency. The strategy should perform similarly across all of these different types of testing.

If the strategy produces solid returns through a wide range of testing, it can be expected to produce similar results in live trading.

勝利の取引システムを作成するには、方法

あなた自身の外国為替の戦略を作成するための青写真, Part 2

The Most Important Point Regarding Testing

Testing Forex Strategies