Downloads · 30 days
0
mag7-tcn-sequence-model
kyLELEng/mag7-tcn-sequence-model
mag7-tcn-sequence-model is a machine learning model from kyLELEng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
Public Temporal Convolutional Network classifier trained on a private MAG7 daily ML dataset.
Access
Public
Updated Apr 30, 2026
Repo size
1.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt1.1 MB · 91%
At a glance
- Library
- pytorch
- License
- other
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026
- SHA
- 8f2fed20
Model card
From the Hugging Face model README
MAG7 TCN Sequence Model
Public Temporal Convolutional Network classifier trained on a private MAG7 daily ML dataset.
Data Access
The model is public. The dataset remains private and is not distributed in this repository.
- Private training dataset:
kyLELEng/mag7-ml-daily-dataset-5y - Dataset file used internally:
mag7_ml_daily_dataset_5y.csv - No raw dataset rows, target labels, or future-return columns are included here.
Training Setup
- Task: binary classification
- Target:
target_next_10d_outperform_qqq - Architecture: TCN sequence model
- Lookback window: 60 daily bars
- Feature count: 187 selected numeric features plus ticker dummies
- Split: chronological train / validation / test
- Train end: 2024-03-06
- Validation end: 2025-02-19
- Test start: 2025-02-20
- Hardware: Hugging Face Jobs,
a10g-large - Device used: CUDA
Results
Validation was used for hyperparameter selection. Test metrics are out-of-sample on the final chronological holdout.
| Metric | Value |
|---|---|
| Best validation AUC | 0.5440 |
| Test AUC | 0.5051 |
| Test accuracy | 0.5087 |
| Test precision | 0.5013 |
| Test recall | 0.4612 |
| Top 20 pct avg future return | 0.0098 |
| Bottom 20 pct avg future return | 0.0243 |
| Top minus bottom future return | -0.0145 |
The holdout edge is weak. Treat this as a research artifact, not as a production trading signal.
Best Trial
- Hidden channels: 96
- Levels: 4
- Kernel size: 3
- Dropout: 0.1381
- Learning rate: 0.000118
- Weight decay: 0.0000688
- Epochs: 27
Files
model.ptscaler.joblibfeature_columns.jsonmetrics.jsontraining_log.csvtrial_results.csvtest_scores_public.csv
test_scores_public.csv contains dates, tickers, and model scores only. It intentionally excludes labels and future returns.
Intended Use
This model is for personal research and model comparison on MAG7 daily technical features. It is not investment advice and should not be used for live trading without separate validation, walk-forward testing, slippage assumptions, and risk controls.
- Library
- pytorch
- License
- other
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026