run_dl_job

Overview

run_dl_job trains a PyTorch network on features and produces return predictions — the deep-learning alternative to run_ml_job. Optional: only needed when you want neural forecasts as μ. Default QuantLab path stays data → PO → trading.

Parameters

string

required

Blob storage URL pointing to a feature_engine_*.json file.This is the output_url returned by run_feature_worker.

string

required

Blob storage URL pointing to a data_extractor_*.json file.This is the output_url returned by run_data_extraction. Required alongside feature_url for proper train/test date alignment.

object

required

Neural network configuration.

Show config fields

object

required

Top-level container for all neural network settings.

Show NN params fields

object

required

Training and architecture configuration.

Show Dot prediction fields

boolean

Enable or disable this prediction block. Default: true.

string

required

Model architecture to use. Supported values:

Value	Architecture
`"lstm"`	Multi-layer LSTM (per-ticker)
`"cnn"`	1D Convolutional Network (per-ticker)
`"transformer"`	Transformer Encoder (per-ticker)
`"mlp"`	Multi-layer Perceptron (per-ticker)
`"portfolio_lstm"`	LSTM trained across all tickers jointly
`"portfolio_transformer"`	Transformer trained across all tickers jointly

object

Runtime settings.

Show global_settings fields

string

Compute device. "auto" selects CUDA if available, else CPU. Default: "auto".

integer

Random seed for reproducibility. Default: 42.

object

Data preparation settings.

Show data_processing fields

string

Feature scaler. Options: "standard", "minmax", "robust", "maxabs". Default: "robust".

integer

Sequence window length (number of past days fed to the model). Default: 10.

integer

Mini-batch size for training. Default: 64.

object

Optimizer and training loop settings.

Show training_params fields

integer

Maximum number of training epochs. Default: 20.

number

Learning rate. Default: 0.001.

integer

Early stopping patience (epochs without validation improvement). Default: 5.

string

Optimizer. Options: "adam", "sgd", "rmsprop". Default: "adam".

number

L2 regularization coefficient. Default: 0.0.

string

Loss function. Options: "mse", "mae", "huber", "directional", "r2", "mahalanobis". Default: "r2". Unknown values fall back to MSE with a warning.

number

Gradient clipping max-norm. Default: 1.0.

object

Architecture-specific hyperparameters. Only the block matching current option is used.

Show Per-architecture fields

lstm / portfolio_lstm

hidden_dims (int array) — hidden layer sizes, e.g. [64, 32]
dropout (float) — dropout rate, e.g. 0.2

cnn

filters (int array) — number of filters per conv layer, e.g. [32, 64]
kernel_size (int) — convolution kernel size, default 3
dropout (float) — dropout rate
pool_size (int) — max-pool size, default 2

transformer / portfolio_transformer

d_model (int) — model embedding dimension, e.g. 64
nhead (int) — number of attention heads, e.g. 4
num_layers (int) — number of encoder layers, e.g. 2
dim_feedforward (int) — feedforward dimension, e.g. 128
dropout (float) — dropout rate

mlp

hidden_dims (int array) — hidden layer sizes, e.g. [128, 64]
dropout (float) — dropout rate

Dates come from data extraction: sample start and end, with an optional train cut (Learning_end) inside that window for fit vs score. This job does not take its own testing-end calendar.

Returns

{
  "status": "Succeeded",
  "output_url": "https://stqsnpprod.blob.core.windows.net/data/nn_engine_9f8e7d6c5b4a.json",
  "output_name": "nn_engine_9f8e7d6c5b4a.json",
  "execution_name": "dl-job-abc123xyz"
}

Field	Description
`status`	Job terminal status (`Succeeded`)
`output_url`	Full HTTPS URL to the output blob — pass to `run_po_job`
`output_name`	Blob filename
`execution_name`	Job execution ID for audit/debugging

Example — LSTM (per-ticker)

{
  "feature_url": "https://stqsnpprod.blob.core.windows.net/data/feature_engine_a1c3e5f70912.json",
  "data_extractor_url": "https://stqsnpprod.blob.core.windows.net/data/data_extractor_2b510101b9b7.json",
  "config": {
    "NN params": {
      "Dot prediction": {
        "status": true,
        "current option": "lstm",
        "global_settings": { "device": "auto", "seed": 42 },
        "data_processing": { "scaler": "robust", "lookback": 10, "batch_size": 64 },
        "training_params": {
          "epochs": 20,
          "learning_rate": 0.001,
          "patience": 5,
          "optimizer": "adam",
          "weight_decay": 0.0,
          "loss_type": "r2",
          "grad_clip": 1.0
        },
        "models_params": {
          "lstm": { "hidden_dims": [64, 32], "dropout": 0.2 }
        }
      }
    }
  }
}

Example — Portfolio Transformer

{
  "feature_url": "...",
  "data_extractor_url": "...",
  "config": {
    "NN params": {
      "Dot prediction": {
        "status": true,
        "current option": "portfolio_transformer",
        "global_settings": { "device": "auto", "seed": 42 },
        "data_processing": { "scaler": "minmax", "lookback": 12, "batch_size": 64 },
        "training_params": {
          "epochs": 5,
          "learning_rate": 0.0005,
          "patience": 10,
          "optimizer": "sgd",
          "weight_decay": 0.0001,
          "loss_type": "r2",
          "grad_clip": 1.0
        },
        "models_params": {
          "portfolio_transformer": {
            "d_model": 64,
            "nhead": 4,
            "num_layers": 2,
            "dropout": 0.4
          }
        }
      }
    }
  }
}

Resources

Resource	Value
Container Apps Job	`dl-job`
Container name	`dl-job`
Env vars injected	`FEATURE_URL`, `DATA_EXTRACTOR_URL`, `CONFIG`
Output blob prefix	`nn_engine_`

Next Step

Pass output_url to run_po_job as input_url.

If you prefer classical machine learning, use run_ml_job instead — it produces an ml_engine_*.json blob equally compatible with run_po_job.

Overview

How To

Tools description

Overview

Parameters

Returns

Example — LSTM (per-ticker)

Example — Portfolio Transformer

Resources

Next Step

​Overview

​Parameters

​Returns

​Example — LSTM (per-ticker)

​Example — Portfolio Transformer

​Resources

​Next Step

Overview

Parameters

Returns

Example — LSTM (per-ticker)

Example — Portfolio Transformer

Resources

Next Step