PatchTST-based stock ranking model trained with LambdaRank loss on KRX data. Crafted by 🍡 DungiBomi

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.

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.

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.

Probabilistic building load forecasting (Q10/Q50/Q90) + risk-aware supervisory control using Patch Transformer (QR-PatchTST)

chatbot designed to allow users to interact with transformer models

Comparison of Return Forecasting Methods for Markowitz Portfolio Optimization: Historical Mean, AutoARIMA, PatchTST Transformer

Time-series foundation model fine-tuning toolkit with GPU acceleration

SOTA time-series models for industrial sensor streams · ETT, SWaT · IEEE TII

Electricity load forecasting pipeline for Turkish EPİAŞ consumption data with LightGBM, XGBoost, PatchTST, and weather features.

Benchmark and reproducibility code for CDC-aligned influenza forecasting with time series foundation models, PatchTST, iTransformer, Chronos, TimeLLM, and MultiFoundationCore.

Comparison of LSTM and PatchTST models for hourly energy consumption forecasting using TensorFlow

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.

9. PatchTST: Channel-Independent Patching Transformer. Hibridne arhitekture za predikciju koje kombinuju deep learning i klasične time-series modele.

Disease Forecasting in a Tropical Context: A Comparative Evaluation of Model Performance and Generalizability for Dengue Fever and Influenza in Vietnam

Stock price prediction comparing PatchTST transformer vs baseline models (MLP, CNN, LSTM) on S&P 500 data

PatchTST discharge forecasting with conformal prediction bands — Reno river, station 425 (Progea/TOPKAPI)

A comprehensive performance benchmark of the state-of-the-art PatchTST (Patch Time Series Transformer) model across multiple diverse datasets and various forecasting horizons

Advanced multivariate macroeconomic forecasting using AutoPatchTST and AutoML on the FRED-MD dataset, comparing feature selection strategies and hyperparameter optimization.

Agentic multi-strategy hedge fund: PatchTST forecasts, 4-agent LangGraph debate, CPCV-OOS + DSR validation, HRP with Ledoit-Wolf shrinkage. 10-year OOS Sharpe=0.766.