PatchTST-based stock ranking model trained with LambdaRank loss on KRX data. Crafted by 🍡 DungiBomi
-
Updated
May 1, 2025 - Jupyter Notebook
#
patchtst
Here are 25 public repositories matching this topic...
Benchmarking time-series foundation models (Chronos-Bolt, zero-shot) vs. supervised (PatchTST) and classical (seasonal-naive, Croston) baselines on the M5 Walmart dataset, scored with MASE and WQL. No single model dominates: foundation/deep models win on dense SKUs, classical methods win on the intermittent tail.
benchmark time-series pytorch forecasting retail chronos demand-forecasting quantile-regression m5 intermittent-demand foundation-models patchtst
-
Updated
Jul 19, 2026 - Python
Tokenization Matters: A Fair Ablation of Point-wise, and Variate-wise Transformers for Financial Time Series. (includes PatchTST, iTransformer, Crossformer, Autoformer, Fedformer, Informer, TimeNet, and non-stationarity extensions.
-
Updated
Sep 27, 2025 - Python
SOTA time-series models for industrial sensor streams · ETT, SWaT · IEEE TII
-
Updated
Mar 22, 2026 - Python
Comparison of Return Forecasting Methods for Markowitz Portfolio Optimization: Historical Mean, AutoARIMA, PatchTST Transformer
-
Updated
Aug 8, 2026 - Python
Heuristics-free self-supervised representation learning for time series with SIGReg (LeJEPA). Disentangles time-axis collapse, positional structure, and representation richness across PatchTST, TCN, and bag-of-patches encoders. Reproducible, seeded, significance-tested.
machine-learning research deep-learning time-series pytorch transformer hydra representation-learning anomaly-detection tcn time-series-forecasting self-supervised-learning financial-time-series jepa dimensional-collapse patchtst representation-collapse lejepa sigreg
-
Updated
Jun 18, 2026 - Python
chatbot designed to allow users to interact with transformer models
-
Updated
Jun 15, 2025 - Python
Probabilistic building load forecasting (Q10/Q50/Q90) + risk-aware supervisory control using Patch Transformer (QR-PatchTST)
time-series tensorflow keras uncertainty transformer quantile-regression building-energy load-forecasting patchtst smart-buildings
-
Updated
Aug 11, 2025 - Jupyter Notebook
Autonomous Multi-Asset Quantitative Trading System powered by Patch Time-Series Transformers (PatchTST), PyTorch Lightning, and MetaTrader 5 (MT5) with institutional risk controllers.
finance reinforcement-learning deep-learning transformers survival-analysis quantitative-finance risk-management soc2 metatrader5 mt5 time-series-forecasting shap pytorch-lightning patchtst trading-bot-monitoring algorithmic-trading-quantitative
-
Updated
Sep 3, 2026 - Python
Time-series foundation model fine-tuning toolkit with GPU acceleration
-
Updated
Jun 6, 2026 - Python
Geospatial time-series deep learning comparing PatchTST, Temporal Fusion Transformers (TFT), and RNNs on satellite NDVI imagery.
-
Updated
Sep 4, 2026 - Python
Electricity load forecasting pipeline for Turkish EPİAŞ consumption data with LightGBM, XGBoost, PatchTST, and weather features.
python time-series xgboost forecasting lightgbm energy-data electricity-load-forecasting epias patchtst
-
Updated
Jul 2, 2026 - Jupyter Notebook
Leakage-aware time-series evaluation, conformal anomaly detection, and online replay
-
Updated
Aug 13, 2026 - Python
Disease Forecasting in a Tropical Context: A Comparative Evaluation of Model Performance and Generalizability for Dengue Fever and Influenza in Vietnam
deep-learning time-series mapping data-visualization mse transformer lstm forecasting mlp linear-models forecasting-models rmse mae disease-prediction scinet modelevaluation patchtst
-
Updated
Sep 11, 2025 - Python
Stock price prediction comparing PatchTST transformer vs baseline models (MLP, CNN, LSTM) on S&P 500 data
finance deep-learning time-series cnn pytorch transformer lstm forecasting technical-analysis stock-prediction sp500 financial-forecasting revin patchtst
-
Updated
Jan 9, 2026 - Jupyter Notebook
From-scratch CUDA implementation of memory-efficient transformer attention with up to 9.5x speedup over a naive baseline, deployed end-to-end to Raspberry Pi 4.
raspberry-pi time-series cuda pytorch transformer attention-mechanism edge-computing patchtst flashattention
-
Updated
May 28, 2026 - Jupyter Notebook
Comparison of LSTM and PatchTST models for hourly energy consumption forecasting using TensorFlow
python machine-learning deep-learning time-series tensorflow keras transformers lstm energy-forecasting patchtst
-
Updated
Apr 27, 2026 - Jupyter Notebook
Benchmark and reproducibility code for CDC-aligned influenza forecasting with time series foundation models, PatchTST, iTransformer, Chronos, TimeLLM, and MultiFoundationCore.
public-health chronos influenza time-series-forecasting mixture-of-experts multi-horizon-forecasting foundation-models itransformer patchtst epidemic-forecasting timellm multifoundationcore
-
Updated
May 14, 2026 - Jupyter Notebook
Advanced multivariate macroeconomic forecasting using AutoPatchTST and AutoML on the FRED-MD dataset, comparing feature selection strategies and hyperparameter optimization.
-
Updated
Jan 31, 2026
Add this topic to your repo
To associate your repository with the patchtst topic, visit your repo's landing page and select "manage topics."