KimSam Ai trading system on ninjatrader

[Liwulong]

On 4/1/2026 at 12:50 PM, kimsam said:

ML = brain   LLM= agents  

Can you share full screenshots?

 

[Liwulong]

4 hours ago, kimsam said:

Never got the files  .. do u have last updated  ? 8.4.9 ?

i think i have the EDU versions already. Will share it tomorrow

[⭐ ajeet]

Anyone can experiment with a lightweight yet relatively robust architecture of TCN-Attention for financial market prediction (primarily trend direction and next-bar price estimation). we can sharpen the setup  on potential overfitting, validation strategies, and feature engineering.

Dataset:
60,000+ rows of 1h OHLCV data (any scrip, but the framework is generic).
Train / val / test split: 70/15/15 (chronological, no shuffle).

Architecture can be:
Input (lookback=128)  
→ Conv1D (filters=64, kernel=8, dilation=1)  
→ TCN block (dilations=1,2,4,8,16, residual)  
→ Multi-head Attention (query from last timestep, key/value from full sequence)  
→ Global Avg Pooling (or flatten)  
→ Dense(32, dropout=0.3)  
→ Output:  
    - Regression: price change % (tanh scaled)  
    - Classification: direction (up/down, sigmoid)  

Loss: combined MSE + binary crossentropy (weighted).

Results that are achievable:
Directional accuracy: ~54–56% (varies by pair/period, not great but above coin flip).
Regression MAE (price change %): ~0.32% for crypto, 0.09% for forex.
Sharpe of strategy based on model signals (backtest): ~1.1 (after 0.1% slippage).

Go and google similar ML models...