アルゴリズムと機械の外国為替戦略 | OneStepRemoved

  • Articles
  • Sophisticated Web Sites
  • Automated Trading
  • お客様の声
  • お問い合わせ

One line of code makes all the difference

2 月 9, 2017 によって ショーンオバートン 4 コメント

I was really excited about my Pilum strategy two months ago. The research looked great and everything was ready to rock and roll. Demo testing began and then… not much happened.

The Quantilator is (mostly) finished, which finally gave me time to circle back and review what happened with Pilum.

Live demo trading of Pilum

Live demo trading of Pilum. 12月 9, 2016 to Feb 7, 2017

The expected outcome was that I would win 75% 時間の. Trades were infrequent, so I thought maybe I’m just having bad luck. But then my win rate remained stuck around 50%. Simple statistical tests told me this was unlikely to be bad luck.

I used the research time to pour over my research code and to compare it with live trades. What I found was that a single line of code (AHHHHHHHHHHHHHHH!) was incorrectly calculating my entry price, dramatically overstating the profits.

、 flawed code produced this equity curve from a single combination of settings:
Flawed Pilum backtest

When the actual, correct result looks like this with those same settings:

The accurate backtest of Pilum

The accurate backtest of Pilum

I’ll be honest… I like the flawed backtest a lot more!

The new, single-setting backtest isn’t as good, but it’s still trade-worthy. There are some characteristics that I dislike and features that I love. Let’s dig into those.

What I dislike

The frequency of trades is very low. Out of 19 months there were a total of 43 取引. 43 trades to comprise a backtest on 40+ instruments is a very small number.

If it weren’t for the statistical pattern backing up the frequency, I would not consider the test. しかし, there are 20,000 bars each on the 44 instruments. あります。 880,000 total bars used to analyze whether my Pilum pattern offers any predictive value.

The most valuable predictions, しかし, are also exceptionally rare. That’s why I’m not able to get the trading frequency higher, which would potentially smooth the returns.

What I love

My previous systems like QB Pro and Dominari traded actively for relatively small wins. Trading costs exercised a massive impact on the overall performance.

The accurate backtest of Pilum

The accurate backtest of Pilum

Now look again at the correct equity curve (the image to the right). Do you see the final profit of roughly 0.14? That’s a 14% unleveraged return over a 19 ヶ月の期間.

Allocating 2:1 または 3:1 leverage on this strategy could average annual returns of 15-25%.

Detecting hidden risk

A key measure of risk is skewness. You may not use that term yourself, but it’s something most of you already understand. The biggest complaint about people trading Dominari was that the average winner relative to the average loser was heavily skewed towards the losers.

Dominari wins on most months, but when it lost in December it was devastating. I implemented what I thought was a portfolio stop after the December 9th aftermath. Then I had a smaller, but still very painful, loss in January. The portfolio level stop loss of 3% should prevent future blowouts now that I know what goes wrong.

I still believe in Dominari. しかし, I obviously lost the work of most of the year due to those events.

Knowing that skewness is a good measure of blowout risk (even if you’ve never seen it in a backtest, like happened with Dominari), Pilum looks extremely encouraging.

This is a histogram of profit and loss by days. You should notice a few things.

The tallest bar is to the right of 0. That means that the most frequent outcome is winning.

worst and best days

The biggest winning day is dramatically better than the worst losing day. The worst outcome was a loss of 2%. The best outcome is gains near 10% in a single day (unleveraged!).

This is the statistical profile of an idea that’s much more likely to grab an avalanche of profits than it is to get blown out.

It gets even better

low correlation

Would you say that the blue and red equity curves are highly or loosely correlated? Look closely.

Writing this blog post made me think carefully about the Pilum strategy. I decided that maybe I should see if all of the profits are coming from different settings at the same time. There’s very little risk of overfitting the data as my strategy only has 1 degree of freedom.

The blue bars are the equity curve of Setting 1.

The red bars are for Setting 2.

Do you think these are tightly or loosely correlated?

If you said loosely correlated, then you are correct. Notice how each equity curve shows large jumps of profit. Did you notice how those profit jumps occur on different days?

The blue setting skyrockets on a single day in November 2016. It leaves the red equity curve choking in its dust.

But then, look what happens as I advance into December. The red curve dramatically catches up to the blue curve and even overtakes it.

The correlation between the 2 strategies is only 57%.

Combine multiple settings into 1 portfolio

Combined settings Pilum equity curve

This is a much nicer equity curve!

Loose correlations are a GIFT. Combining two bumpy equity curves into a single strategy makes the performance much, much smoother.

The percentages of days that are profitable also increases. Setting 1 is profitable on 58.0% of days. Setting 2 is profitable on 53.5% of days.

しかし… combining them makes Pilum profitable on 68.2% of days. 素晴らしい!

That also provides more data, which puts me in a stronger position to analyze the strategy’s skewness. Look at the frequency histograms below. They’re the same type of histograms that I showed you in the first section of this blog post. As you’ll notice, they look a lot different.

Pilum most probable daily profit and loss

The most probable outcome for any given day is a small winner

The tall green bar is the most probable trading outcome for any given day with filled orders. The average day is a positive return of 0-1%.

The small red bar is the worst trading day of the combined strategy.

The small green bars are the best trading days of the combined strategy.

Look how far to the right the green bars go. The largest winner is more than 3x the biggest loss. と, there are so many more large winners compared to losers.

Giant winners are far more likely than comparable losses.

The Plan

I immediately pushed Pilum into live trading this combination of two strategies. I expect that adding a second degree of freedom and running about 30 different versions of the strategy – all with different settings – will add to the performance and smooth the returns even further.

Dominari hasn’t been working on my FXCM account, which is very difficult to accept because the lacking performance seems to be a buried execution issue. Pilum, しかし, trades very infrequently. It’s unlikely that execution quality will make a dramatic difference in the long term outcomes.

だから, I’m going to convert the FXCM account to trading Pilum exclusively. That will be offered as a strategy on Collective2 within the next few weeks, a company with whom I’ve been working closely. Their users are more investor rather than trading oriented – they’re far more likely to view low trading frequency as a good thing. I suspect that most people here have a different opinion and want to see a lot of market action.

I’ll write an update on Dominari shortly.

以下の下でファイルさ: Pilum, 戦略の取引のアイデア タグが付いて: 相関関係, カーブフィッティング, 自由度, ルール, equity curve, 周波数, FXCM, histogram, レバレッジ, QB プロ, リスク, スキュー, 統計情報

The guy that bet on Leicester City every year

9 月 5, 2016 によって ショーンオバートン Leave a Comment

Leicester City Football Club

Leicester City started the 2015 season with terrible odds of winning the Premier League Championship. Bookmakers only game them odds of 5,000:1 of winning.

To put that in context, you are more likely to die riding a bicycle than you were to win a bet on Leicester City. または, you can think of betting on Leicester City every year. If you bet on them every single year for 5,000 年, you would expect them to win a grand total of… once.

2014 was hardly an indicator of their pending success. They were nearly relegated to a lower division (すなわち, kicked out of the Premier League). And yet, they did win the championship last year.

Leicester City’s Biggest Fan

John Micklethwait

Meet John Michklethwait. He’s the former editor-in-cheif at The Economist and he’s currently editor-in-chief for Bloomberg. 明らかに, he’s a very smart man. And yet, despite the odds and repeated disappointments, John bet on his old love, Leicester City, every single year dating back to the 1980s. That’s roughly 30 years of nonstop losing.

It wasn’t a lot of money each year: just £20. We all have our indulgences. I see the value of having skin in the game. £20 on a season is enough to make one care, but not so much that he’s upset about losing it.

Then something disruptive happened. John moved to the US last year for his position at Bloomberg. The chaos of the move threw him out of sorts, and he accidentally forgot to bet on Leicester City in 2015. He bet on them every single year dating back nearly 30 年. And yet the one year that he forgets to bet, not only did Leicester City win, but the bet paid out 5,000:1.

Let’s step back and calculate the cost of that oversight for Mr. Micklethwait.

£20 * 5,000 = £100,000.

A hundred… thousand… pounds. That kind of winning would put a nice dent in your mortgage, wouldn’t it?

The risk of low probability strategies

Everyone hears anecdotes about successful trend traders. Even winning only 30-40% 時間の, they walk away big winners over time.

planet earth

You live HERE. Math isn’t good enough. You also need to wonder if your strategy can handle real-world problems.

What if they took that even lower? They could move their stop losses closer to the market. They’d reduce the size of the average loser, but the winning percentage might also drop to 10-20%.

数学的に, this could work out identically. 30% winners that earn 5x the average loser make for a profit factor of 1.5. A strategy with のみ 10% winners that make 15x the typical loser also have a 1.5 プロフィットファクター.

数学的に, this could work out identically. 30% winners that earn 5x the average loser make for a profit factor of 1.5. A strategy with only 10% winners that make 15x the typical loser also have a 1.5 プロフィットファクター.

They’re the same. Aren’t they?

Planet Earth isn’t the same as planet Math. 現実の世界で, people get sick and miss trades. または, they move across the Atlantic and forget to place a £20 bet.

People move. They get sick. Computers break. Things can and will go wrong with trading.

Richard Dennis once commented that the Turtle Traders would often make their annual returns off of one, single trade. A single trade!

When your performance depends on positive outliers, you’re massively vulnerable to accidents. What happens if you’re sick that day? Or your internet goes down? Or your broker locks you out of your account on the worst possible day?

Life happens, brother. A plan that depends on perfection is no plan at all. You need to make yourself robust to failure. Or even better, you’d make yourself antifragile.

Winning percentages

I mentioned that you can do really well winning 30-40% of time. Why then, does my own trading strategy, ルール, win 68% 時間の?

Because I’m exploiting compound, exponential growth. It’s not just how much you win, but the order in which you win it.

Let’s take two examples:

  1. A ranging strategy with a profit factor of 1.3 that wins 68% 時間の.
  2. A trending strategy with a profit factor of 1.3 that wins 30% 時間の.
Range vs trend outcomes

Look at the red circles. Trending strategies are prone to extreme outcomes, both positive and negative.

Each strategy risks about 1% on any given trade. と, the average of the range and trend strategies are identical in the long run.

しかし… and this is an important “しかし”, the expected worst case scenario with the trending strategy is substantially more likely compared to the range trading strategy. 効果で, the average is more average with a ranging strategy than with a trending strategy.

何故ですか? Because unusual losing streaks are devastating to trending strategies. Have you ever had a losing streak? It happens to everyone.

By using a strategy with a higher winning percentage, you’re making yourself robust to streaks of losers. と, not to mention, your average length of a winning streak is considerably higher.

Even though you’re getting the same mathematical outcome, you’re making things much easier on your trading psychology when you adopt a strategy with a higher winning percentage.

ルール & Exponential Growth

Dominari backtest

You may have thought to yourself, “68%? That’s kind of a strange number to pick.”

You’d be right. The choice of 68% winners was not a coincidence. それは, 実際, the win rate on my Dominari strategy.

Dominari is about more than just buying and selling. Trading is also about managing a portfolio and position sizing. Position sizing is phenomenally important over your trading career.

My backtest results for Dominari show that for every $2,500, the account increased to $17,855.35 後 3 年. That kind of compound growth doesn’t happen by accident. That’s why I’d like to share the good news with you in my webinar this week.

I’m going to show you how to put that exponential awesomeness to work in your trading account. Sound good? ここをクリックしてください。 to register for the FREE webinar.

以下の下でファイルさ: ルール, 外国為替市場のしくみ? タグが付いて: antifragile, ルール, プロフィットファクター, 範囲の取引, sports, トレンド, 勝率

大転換

2 月 1, 2016 によって ショーンオバートン 60 コメント

私は今月Dominariに私の取引資金のすべてを移動しました.

私は開始以来、このシステムについて話してきました ライブデモテスト 戻って11月に. 言うまでもなく, 私はライブの結果に非常に満足してきました.

私の最初のライブ口座を持ち、1月に取引を開始しました 4 で€1,000開始残高と Pepperstone. 私はライブ取引は私の期待と一致したことを見たら、, 私はすぐに€10,000合計にそのアカウント残高を蹴りました.

そして、私はブローカーの選択の効果をテストするため、, 私は別のものを投げました $5,000 FXCM口座に. 、 Pepperstone アカウントはお金の大部分が含まれており、戦略のMT4のバージョンを実行します. FXCM版はシーアを使用しています, スムーズに実行して取得する痛みのより多くなっていました, 私はそれはまだテストのアイデアのための私の好きな​​プラットフォームだと言うことができるものの.

コスト以外の問題

backtested equity curve

から取引コストなしDominariの株式曲線 2013-2015.

戦略のライブはコストが取引された起動についての私の最大の懸念. 封筒の数学のいくつかのバックは、すべてが大丈夫であることが示唆しました. ライブデモテストは、それは大丈夫だろうことを示しました. あなたはライブの取引を開始するまでしかし、あなたは本当に知っていることはありません.

1月の月を通じて、, 私は一貫して利益を基準にコミッションをモニターしました. 私は取引口座で上下に変動します, しかし私は、スプレッド手数料コストが約あると推定しています 20-25% 利益の. それは、比較的高い割合です, それは極端な取引頻度与えることができるようにどこにも近くなど悪いですが、.

Dominariは、約平均値高周波戦略であります 49 一日あたりの取引 28 通貨ペア. すべては私がハード任意の個々の取引を覚えておくことが押されているアカウントで非常に速く起こります. Dominariは以上実行しました 900 単独で1月の月の取引. これは、変動上下株式を見て目のくらむようです. 重要なことは、傾向は左下から右上に移動するということです.

QB プロ?

それは死んでいないのです. 私はまだそれがあなたの取引の偉大な戦略と完全に価値があると信じ. 実際, DominariとQB Proの両方が私の好きな​​指標の一つに大きく依存します, 、 SBスコア.

私はアルゴリズム取引に入った理由は、それが感情的結果に対する責任から私を分離することです. 私は負け月がある場合, それだけの戦略です. そのことについて行うことがあまりありません.

裁量の要素があります場合には, それはランダム成分を分離することは困難です. 時にはあなたが勝ちます, 時にはあなたが失います, しかし、あなたは、一般的にお金を稼ぐことを期待します. アルゴリズムの戦略の裁量があります場合には, それは損失は私のせいか、単純不運であるかどうかを知ることは非常に困難です.

QB Proは手動のポートフォリオ選択に依存します. 驚くことはないです。, ポートフォリオ選択が静的であるので、私は重くDominariを好みます. 私はDominariはブラックボックスであることを私の心の上に私の手を持って言うことができます, 完全アルゴリズムの戦略.

私はまだシーアハブでポートフォリオを渡って更新だし、クライアントのための選択を作り続けます. Pepperstoneで管理アカウントにいクライアントの場合, 私は、月の途中で戦略を切り替えます. 私はクライアントに可能な限り最高のパフォーマンスを提供するために経営者としての責任を感じます. そして、私は自分のお金の〜$ 16,000配置することだところそれはだから, 私は私の顧客のために同じことを行うには忠実義務を感じます. 私は最高の機会の嘘を信じてどこDominariです.

あなたはDominariを取得できますか

私は来月かそこら内のメタトレーダーアカウントで誰にも売買シグナルとしてDominariを提供することを計画します. 多くのハードワークは、戦略の開発に行ってきました. そして、私はの曲に確信しながら、 $16,000 私自身のお金の, 私はより多くの人にDominariをリリースする前に、私はさらに確実なものにしたいです.

あなたは、これまでの結果をどう思いますか? 以下のコメントエリアに自分の考えを残します.

以下の下でファイルさ: ルール タグが付いて: アルゴリズム取引, 委員会, ルール, 資産配分, 自己勘定取引, スプレッド

メールで無料の取引戦略

トレンド分析

申し訳ありませんが. No data so far.

アーカイブ

  • ルール
  • 外国為替市場のしくみ?
  • インジケーター
  • メタト レーダーのヒント
  • MQL (オタクのため)
  • NinjaTrader ヒント
  • Pilum
  • QB プロ
  • お金を失うことを停止します。
  • あなたの概念を歴史的にテストします。
  • 戦略の取引のアイデア
  • 未分類
  • What's happening in the current markets?

翻訳


無料の取引戦略

プライバシー ポリシーRisk Disclosure

著作権 © 2023 OneStepRemoved.com, (株). すべての権利予約.