New Strategy
Sign up

LSTM model

1. Node overview

LSTM (Long Short-Term Memory) is a recurrent neural-network architecture designed specifically to learn long-term dependencies in time-series data. Its gating mechanism addresses the vanishing-gradient problem found in conventional RNNs and retains information over long time spans. The LSTM model node performs sequence modelling on factor data from the data-processing node and outputs predictions for the strategy node.

Position in the data flow
Data source→Data processing→AI model→Strategy type→Position management→Risk control→Trading engine
✓ Strengths

Captures long-term temporal dependencies

Learns time-series features automatically

Handles variable-length sequence inputs

Can be trained without a GPU

Use cases

Price-trend forecasting

Trend recognition and classification

Sequence-pattern learning

Time-series factor extraction

⚠ Limitations

Moderate training and inference speed

Sensitive to hyperparameter tuning

Requires substantial historical data

2. Interactive configuration

The panel below is the actual LSTM model node configuration. Use it to explore every setting: prediction column name, task type, and parameter configuration mode (adaptive or advanced).

LSTM model configuration

Only A-Z, a-z, 0-9, - and _ are supported; other characters are replaced with _.

Name of the model prediction output column.

2.1 Prediction column name

Set the name of the column that stores model predictions
What is the prediction column name?
After training, the model adds a column containing its predictions. A downstream strategy node references model output through this name. The default is pred.
Tip: when a workflow contains several AI model nodes, assign each one a different prediction column, such as pred_lstm and pred_lgb, so the strategy can distinguish them.

2.2 Task type

Select the model's training objective and loss function
What is a task type?
The task type determines how the model learns and how it produces predictions. Different task types use different loss functions, so choosing the appropriate task is essential to model performance. The system supports Ranking, Binary, and Regression. LightGBM, LSTM, and Transformer default to Binary; switch explicitly to Ranking only for cross-sectional selection across multiple instruments.
⚡ Quick selection guide
DimensionRankingBinary ⭐Regression
Primary objectiveLearn relative orderClassify upward or downward directionPredict an exact return
Noise robustness⭐⭐⭐⭐⭐⭐⭐⭐⭐
Generalization⭐⭐⭐⭐⭐⭐⭐⭐⭐
Sensitivity to outliersMediumLow (inherently resistant)High
Fit for cryptocurrencyMulti-asset selectionBest for single-asset timingPosition-management support
Typical strategyLong/short hedge or ranked selectionTrend timing or enhanced gridDynamic positions or risk control
Recommendation: cryptocurrency markets are highly volatile and contain many extreme moves. Binary classification collapses continuous returns into direction, naturally filtering tail noise. Directional accuracy matters more than return-magnitude precision, so Binary is the default recommendation.

2.2.1 Ranking

Learn relative order among samples; suitable for multi-factor asset selection

Ranking does not optimize the absolute prediction value. It learns relative order among samples, placing higher-return samples ahead of lower-return samples. In multi-asset cryptocurrency strategies, it can select the instruments with the greatest upside potential from dozens of pairs and is the primary driver of cross-sectional selection strategies.

PropertyDescription
Label requirementA continuous value such as return: shift(close, -5) / shift(open, -1) - 1
Output rangeAny real number; a larger score ranks higher
Use casesMulti-factor selection, cross-sectional ranking, and long/short hedging
Frontend fieldtaskType: "ranking"
Ranking mode (rankingMode)

Selecting Ranking reveals the ranking-mode option, which determines where optimization is concentrated:

Balanced (balanced)
Optimize both the head and tail
→ Long/short hedging
Head (head)
Prioritize the top-ranked samples
→ Long-only strategies
Tail (tail)
Prioritize the bottom-ranked samples
→ Short-only strategies
💡 Cryptocurrency note: Ranking requires cross-sectional data for several trading pairs, such as BTC, ETH, and SOL features at the same time. The model compares their relative strength within each time slice. For a single instrument, choose Binary instead.

2.2.2 Binary ⭐ Recommended

Predict upward or downward direction; the first choice for cryptocurrency timing

Binary classification turns forecasting into an up-or-down decision. The model outputs signed confidence with a theoretical range of -1 to 1: positive is bullish, negative is bearish, and a greater absolute value means higher confidence. Because cryptocurrency has high volatility and a low signal-to-noise ratio, actual predictions usually cluster around -0.1 to 0.1; theoretical values near ±1 are almost never seen. Begin machine-learning models with entry thresholds around 0.03 / -0.03, inspect the prediction distribution after the first backtest, and recalibrate. Do not start from theoretical thresholds such as 0.2 or 0.5, which may trigger extremely rarely or never. Direction still has a much better signal-to-noise ratio than magnitude, making Binary the most practical task.

PropertyDescription
Label requirementA Boolean value or continuous return; continuous values are converted to 0/1 using > 0
Output rangeTheoretical -1 to 1 confidence; generally -0.1 to 0.1 in practice because financial signal-to-noise is low
Use casesDirection forecasting, timing signals, and trend classification
Frontend fieldtaskType: "binary" (system default)
Label example: label = shift(close, -5) / shift(open, -1) - 1 means buying at the next candlestick's open and selling five periods later. The engine converts returns > 0 to positive class 1 and returns ≤ 0 to negative class 0.
📊 Confidence-to-probability table

Binary output is signed confidence in the range -1 to 1: confidence = 2 × probability - 1.

Probability30%40%50%55%60%
Confidence-0.4-0.200.10.2

Strategy example: pred > 0.2 opens a long position (60% bullish probability), while pred < -0.2 closes it (only 40% bullish probability).

🎯 Why is Binary recommended for cryptocurrency?
• Compressed label space: continuous returns collapse to {0, 1}, so extreme ±20% moves no longer dominate the loss.
• Direction over magnitude: getting direction right can be profitable in a volatile market without predicting the exact return.
• Natural regularization: a classification boundary is smoother than a regression fit and is less likely to overfit isolated abnormal candles.
• Actionable confidence: probabilities can directly represent signal strength for dynamic position sizing.

2.2.3 Regression

Predict an exact return and optimize absolute accuracy

Regression requires the model to predict an exact return value. Unlike Ranking, it minimizes the absolute error between prediction and target. Frequent extreme cryptocurrency moves, such as flash crashes and sudden rallies, can dominate regression training, so generalization is often weaker than Binary. The output nevertheless has a clear physical meaning and is useful as an auxiliary signal for position sizing and risk control.

PropertyDescription
Label requirementA continuous return such as shift(close, -5) / shift(open, -1) - 1
Output rangeAny real number representing predicted return
Use casesPosition sizing, risk assessment, and expected-return calibration
Frontend fieldtaskType: "regression"
✓ Advantage: the output has a clear physical meaning and can be used directly for position calculations and expected-return assessments.

2.3 Parameter configuration mode

Choose system-adaptive or manually configured parameters
What is parameter configuration mode?
The system provides Adaptive mode, which tunes parameters from the data size, and Advanced parameter configuration, which exposes every model parameter. Adaptive mode is the default and is suitable for new users and rapid strategy validation.

2.3.1 Adaptive mode

The system chooses parameters automatically from the data size

The system calculates model parameters from the number of training samples and features. This is suitable for new users and rapid strategy validation and does not require detailed knowledge of LSTM model parameters.

✓ Advantages

No tuning experience required

Start training quickly

Lower overfitting risk

⚠ Limitations

No fine-grained model control

Parameters may not be optimal

Adaptive parameter ranges
The system selects parameters within these ranges: sequence length 7–30, hidden size 32–256, exactly 2 LSTM layers, a learning rate around 0.001, 30–70 epochs, batch size 5–128, sample dropout 0.10–0.25, and feature dropout 0.10–0.25.

2.3.2 Advanced parameter configuration

Configure every parameter manually for fine-grained tuning

Advanced mode displays the full panel in three parts: model architecture, training parameters, and regularization. It is intended for experienced users performing detailed tuning.

2.3.2.1 Model architecture

These parameters control the complexity of the LSTM network. Larger hidden states and more layers produce a more complex model, but also increase the risk of overfitting. Leave a field blank to let the system calculate it adaptively.

ParameterAllowed rangeAdaptive rangeDescription
Sequence length3–3607–30Length of the input time-series window
Hidden size8–51232–256Dimension of the LSTM hidden state
LSTM layers1–6Fixed at 2Number of stacked LSTM layers
Small dataset (<100,000): seqLen: 5–15, hiddenSize: 32–64, nLayers: 1–2
Large dataset (>1,000,000): seqLen: 15–60, hiddenSize: 128–256, nLayers: 2
2.3.2.2 Training parameters

These parameters control model training. A smaller learning rate requires more epochs, but usually produces better results.

ParameterDefaultAllowed rangeDescription
EpochsAdaptive1–500Training iterations; SWA is disabled below 2 epochs
Learning rateAdaptive0.00001–0.01Gradient update step size
Validation split0.20–0.5Used for early stopping; 0 disables validation
Early-stopping patience71–50Stop after N epochs without improvement
Batch sizeAdaptive1–2048Number of samples per batch
Early stopping: training stops automatically when the validation metric has not improved for the configured number of rounds, preventing overfitting. This setting has no effect when the validation split is 0.
2.3.2.3 Regularization

Regularization prevents overfitting. Higher dropout applies stronger regularization and produces a simpler model. Leave a field blank to let the system calculate it adaptively.

ParameterAllowed rangeAdaptive rangeDescription
Sample dropout0–0.60.10–0.25Random dropout ratio along the time dimension
Feature dropout0–0.50.10–0.25Random dropout ratio along the feature dimension
Overfitting: good training but poor validation → increase dropout
Underfitting: both poor → reduce dropout or enlarge the model

3. Output data structure

The LSTM model node adds a prediction column to its input data and returns the following structure:

ColumnTypeSourceDescription
datetimedatetimePassed throughTimestamp
symbolstringPassed throughTrading pair
open/high/low/close/volumefloatPassed throughRaw OHLCV data
[factor columns…]floatPassed throughFactors calculated by the data-processing node
predfloatAddedModel prediction; the name is controlled by predictionColumn
Meaning of predictions by task type
Ranking
Ranking score; a larger value ranks higher
→ Relative selection
Binary
Bullish confidence in the range -1 to 1
→ Direction
Regression
Predicted return, which may be positive or negative
→ Return forecast

4. FAQ

Q: How should I choose between LSTM and LightGBM?
A: LightGBM provides the fastest training and inference and is well suited to rapid iteration and real-time prediction. LSTM is better at capturing temporal dependencies, with moderate training and inference speed. Choose LSTM for temporal patterns such as momentum and trends; choose LightGBM for cross-sectional factor ranking or when fast inference is important.
Q: What sequence length (seqLen) should I use?
A: Sequence length determines how much history the model can see. A value of 10–30 is generally recommended, depending on the candlestick interval and strategy logic. Daily data can use a shorter window of 7–15, while hourly data can use 20–30. Excessively long sequences increase training time and overfitting risk.
Q: How should I tune hidden size and layer count?
A: Hidden size controls model capacity and layer count controls network depth. Start with a small model, such as hiddenSize=64 and nLayers=1, verify the full workflow, and increase the size gradually. If training performance is good but validation performance is poor, reduce the model size or increase regularization.
Q: What can I do if training is too slow?
A: LSTM training is slower than LightGBM. Reduce sequence length and model size, increase batchSize to use the GPU more efficiently, or reduce the maximum number of epochs while retaining early stopping.
Q: What is SWA, and why is it disabled when epochs < 2?
A: SWA (Stochastic Weight Averaging) averages model weights across several late training epochs to improve generalization. It cannot operate with fewer than two epochs, so it is disabled automatically.
    BeeQuant - AI Quantitative Trading Platform