Something Interesting - page 56

[Sergey Golubev]

Exploring Advanced Machine Learning Techniques on the Darvas Box Breakout Strategy

The Darvas Box Breakout Strategy, created by Nicolas Darvas, is a technical trading approach that spots potential buy signals when a stock’s price rises above a set "box" range, suggesting strong upward momentum. In this article, we will apply this strategy concept as an example to explore three advanced machine learning techniques. These include using a machine learning model to generate signals rather than to filter trades, employing continuous signals rather than discrete ones, and using models trained on different timeframes to confirm trades. These methods offer fresh perspectives on how machine learning can enhance algorithmic trading beyond traditional practices.

[Aleksandr Slavskii]

Sergey Golubev #:

This sharing is best posted in the Humour topic )))))

I'll explain why. Indicator 10 candles back looks where the price has moved and depending on it puts there a mark up or down, well, and accordingly in the basement also drawn the necessary bars.

Then the indicator records the time when there were "signals" in the file, and then in the tester the Expert Advisor reads these "signals" from the file and opens positions on them.

I'm sure it was written just for laughs.

[Sergey Golubev]

Ind_2 Line+1 - indicator for MetaTrader 5

The indicator has three lines: 

• Green is an averaging line of the first instrument index;
• Blue is an averaging line of the second instrument index;
• Line of the width of the instruments runaway: sky blue is in divergence, red is in convergence.

[Sergey Golubev]

Elevate Your Trading With Smart Money Concepts (SMC): OB, BOS, and FVG

Smart Money Concepts (SMC) provide a structured way to understand market behavior through Order Blocks (OB), Break of Structure (BOS), and Fair Value Gaps (FVG). By combining these into a single EA, traders can simplify their workflow, automate decision-making, and focus on the most powerful price-action signals. Whether using auto mode for seamless execution or selecting individual concepts, this approach reduces guesswork and makes trading more efficient, consistent, and adaptive to changing market conditions.

[Sergey Golubev]

Very interesting indicator - 

----------------------

Kalman filter - with candles or bars - indicator for MetaTrader 5

This one was published long time ago using Kalman filter name (among other publications, you can check this one too : Kalman filter - a version for mt4). Kept the name and made it multi time frame.Multi time frames are having, apart from all the standard multi time frames that can be used in metatrader 5, 3 additional "time frames" :

• first higher time frame (first time frame higher than the current chart time frame)
• second higher time frame (second time frame higher than the current chart time frame)
• third higher time frame (third time frame higher than the current chart time frame)

Also, this version is adding colored bars or candles to the display in order to make it easier to assess the trend. The display is adjusted automatically.

[Sergey Golubev]

Adaptive Smart Money Architecture (ASMA): Merging SMC Logic With Market Sentiment for Dynamic Strategy Switching

Over the last phases of development, we successfully combined Order Blocks (OB), Fair Value Gaps (FVG), and Break of Structure (BOS) into one unified Smart Money Concepts engine—a powerful framework capable of reading institutional price action with precision. Building on that foundation, we also designed a custom market sentiment indicator that interprets trend strength, volatility posture, and momentum alignment to classify the market into bullish, bearish, or neutral states. These two advancements now give us the perfect opportunity to merge structural price action with real-time sentiment into a single adaptive trading system.

[Sergey Golubev]

Sergey Golubev #:

This is very interesting scalping EA: Angry Bird (Scalping) - expert for MetaTrader 4

Some people say that this EA looks like 'modified Ilan1.6' in trading but with more secure features concerning deposit and so on and having the following:

• MaxTrades parameter (how many simultanious trades can be opened), 
  
• LotExponent: this is lot multiplier for martingale (I prefer 1.4 instead of default 2.0 for example),
• TakeProfit in points (in case of 5 digit price which as 1.09635 so TakeProfit = 20 is 2 pips),
• UseEquityStop parameter to stop trading with TotalEquityRisk (TotalEquityRisk = 20 by default),
• UseTimeOut: close all the trades after MaxTradeOpenHours (I prefer to use UseTimeOut - I mean: EA will close all the trades after MaxTradeOpenHours = 5 hours).
  

This is the description from the author:

This is backtesting for 4 days till now with minimal/minimum risk for deposit:

Using Deep Reinforcement Learning to Enhance Ilan Expert Advisor

Our journey will take you through the labyrinths of algorithmic trading, where mathematical rigor meets computational elegance, and classic Martingale techniques take on new life thanks to innovative machine learning approaches. Whether you are an experienced algorithmic trader, a trading architecture developer, or just a financial technology enthusiast, this article offers a unique perspective on the future of automated trading.

Fasten your seat belts — we are embarking on an exciting journey to create Ilan 3.0 AI, where tradition meets innovation, and the past evolves into the future.