Momentum Optimisation

 02/01/25    10:21

Been working on the momentum code most of the day today and looks good now.  The functionality is mostly there.  From a small test this morning:

  1. The momentum system is working:
  • When momentum is high, we see larger reductions in MinLineDifference:
Required Difference: 0.036626 (Base: 0.046000 reduced by 20.4%)
Momentum Factor: 20.4%

vs. low momentum:

Required Difference: 0.043217 (Base: 0.046000 reduced by 6.0%)
Momentum Factor: 6.0%


So it is working but needs to be optimised again with the other key momentum parameters, which is where I am at right now.  Currently doing a 4 property optimisation with the new code to find the best configuration.  The properties are:

Property                        Description                                                                             Range
MinLineDifference        (Distance between lines before opening trade                         0.02 - 0.1     )
AngleBarsToCheck        (Number of bars to look back at to determine momentum     1-3                )
AngleWeight                  (Weighting % given to angle in the calculation                      0.5 - 1.0        )
MaxAngleDegrees         (Maximum angle used in the calculation                                0.15 - 0.45    )

MT4 is currently testing every possible cofiguration of these 4 parameters and is currently on test number 5750 and looks to be about a quarter of the way through..... could be a while.....

This was from the the AI after I requested to do an audit on the previous test:

Let me reorganize this analysis by directly looking at the trade log data you provided. Here are the key findings from analyzing all 128 trade records (64 positions open/close):

  1. Big Picture Issues:
  • Starting Balance: 10,000
  • Final Balance: 8,279.21
  • Total Loss: 1,720.79 (17.21%)
  1. Best Performing Trades:
  • Trade #122: +987.40 (Dec 19 05:00-21:00 Buy)
  • Trade #20: +691.64 (Nov 7-Nov 11 Sell)
  • Trade #96: +549.05 (Dec 9 Buy)
  1. Worst Performing Trades:
  • Trade #100: -353.07 (Dec 11 Sell - Stop Loss hit)
  • Trade #81: -268.44 (Dec 4 Buy)
  • Trade #60: -271.62 (Nov 27 Buy)
  1. Pattern Analysis: a) Stop Loss Hits:
  • Most stop losses occur during shorter-term trades (< 4 hours)
  • Often happen during trend reversals

b) Winning Trades:

  • Longest duration trades tend to be most profitable
  • Strong correlation between momentum and profit
  • Best trades typically last > 12 hours

c) Time-Based Patterns:

  • Most profitable trades start in early Asian session
  • Most losses occur during session transitions

  1. Key Loss Patterns:
  2. Quick Reversals:
    • Many losses come from trades that reverse shortly after entry
    • Often missing initial momentum confirmation
  3. Premature Stop Losses:
    • Several trades hit stop loss then move in intended direction
    • Current stop loss might be too tight
  4. Late Entries:
    • Some losses come from entering after major move already happened
    • Need better entry timing based on momentum


So I then asked......  

(it also should be 'action' #100 not 'trade #100 but the AI understands)

Let's target trade #100. Assess the factors associated with this loss and make addressing them the priority

Let me analyze trade #100 in detail:

98	2024.12.10 13:00	close	49	1.00	88.340	89.181	0.000	169.66	7911.21
99	2024.12.11 10:00	sell	50	1.00	87.451	88.006	0.000	0.00	7911.21
100	2024.12.11 11:30	s/l	50	1.00	88.006	88.006	0.000	-353.07	7558.14
101	2024.12.11 12:00	buy	51	1.00	88.146	87.591	0.000	0.00	7558.14

Key Observations:

  1. Trade was a SELL entry at 87.451
  2. Hit stop loss at 88.006 (555 pips move against position)
  3. Immediately after stop loss, EA opened a BUY position
  4. Entry to stop loss time was only 1.5 hours

Critical Issues:

  1. Direction Change Validation:
  • The quick flip from SELL to BUY suggests the white/red line cross may have been too marginal
  • Need to see actual momentum values at entry/exit
  1. Trade Timing:
  • 10:00 entry during transition from Asian to London session
  • Stop loss hit at 11:30 during peak London volatility
  1. Risk Management:
  • 555 pip loss is significantly larger than our typical losses
  • Position might have been opened with insufficient momentum confirmation

Let me analyze the indicator values around this trade: === Trade #100 Analysis === Entry to SL Movement: 0.5550 pips Time in Trade: 1.5 hours Post-SL Movement: 0.1400 pips Price Range: 0.6950 pips Average Movement per Hour: 0.3475 pips/hour Risk/Reward Ratio: 1.23


Proposed Solutions:
Add Session-Based Entry Filters:
Enhanced Momentum Validation:
Dynamic Stop Loss Adjustment:


But instead I've opted to do the full optimisation to see where we are once optimised. 

Comments

Post a Comment

Popular posts from this blog

Stops and line based entry validation

 22/12/24      12:55pm Now that the robot is buying and selling at relatively the right time, this morning has been about working on parameters for the minimum line difference setting.  This is what is being used to determine trend.  There are still a lot of small intermediate trades that I am trying to eliminate with this setting.  Initally starting at 0.00025 this has been increased greatly to 0.04 then 0.05 on the advice of the AI after feeding it the logs and trade results from all the tests.  A lot of small trades are still hitting stop loss early so working on that by implementing what you suggested - raising stops only after certain level of profit has been reached and by increasing the size of the trailing stop.  I know you said not to have a trailing stop but after discussion with the AI it said not having one was practically the same as just increasing the size of it so it doesn't interfere with trades but still has protection from ...
Read more

Momentum

 01/01/25     12:38 As per our discussion I altered the way the lines were being identified by using the 0 or 1 reference built in to MT4 and this seemed to eliminate many of the clusters of bad sell trades that were losing money and consequently after the optimisation took the profit up to over $2400.  And now I will be working on adding momentum detection to the lines crossover to allow the trades to initialise earlier.  With strong momentum the line difference criteria for trade entry can be smaller and therefore closer to the crossover point. The primary indicator is the angle of the lines - closer to a 45 degree the more likely to continue and separate into a larger trend.  The AI suggested factor is magnitude , which is how many bars the direction has been consistent for.  So combining these will give an industry standard indication of momentum that can then be used to reduce the minLineDifference and open trades earlier.  I'm thinking that...
Read more

Strip back to core functionality

 18/12/24     10:40 am Universality for any chart added. 7:41 pm Stripped out all excess entry filters and parameters to focus solely on the White above red functionality and line difference and still wasn't trading properly.  Deactivated the line difference also so the single parameter of white above or below red was the only determining factor for entering trades which revealed issues with how the code is interpreting the data from the White/Red buffers (values) so currently isolating and exploring this code to get it to open a buy when white is above red and then close the buy and open a sell when white crosses below.  So not including the line difference or any other parameters to get this core functionality perfect.  As it is the robot is putting a ton of excess trades on in large clusters and when zooming in looks like it is affected  by spikes in the data or in the price data which it should not be looking at. Obviously there are no spikes in th...
Read more