A unified framework for machine learning with time series
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
A toolkit for time series machine learning and deep learning
DEPRECATED, now in sktime - companion package for deep learning based on TensorFlow
PyTorch code for Learning Deep Time-index Models for Time Series Forecasting (ICML 2023)
A fast canonical-correlation-based search algorithm for feature selection, system identification, data pruning, etc.
A Standardized Benchmark for Skeleton-Based Rehabilitation Assessment Using Deep Learning
Predict the trajectory of the vehicles in HCM city streets with YOLOv7 + DeepSORT + CNN-LSTM/CNN-GRU.
Time series analysis with LLM-ABBA: A symbolic approach
A toolkit for time series machine learning algorithms that don't fit in aeon. Use aeon instead if you can!
Collection of my Time series Analysis Projects
NARX Pytorch implementation
This repository contains files and scripts to build a sales forecasting Telegram Bot for a pharmacy chain. The purpose of this project is to quickly and easily provide a revenue estimate in order to assist the CEO in decision making. (Project Data Science in Production / DS Community)
Early cycle-life prediction of Li-ion batteries on the MIT–Stanford 124-cell fast-charging dataset. Transformer vs Ridge/RF/LSTM, 5-fold CV R²=0.83 (MAPE 14.5%), with Integrated Gradients / permutation / attention-rollout explainability.
MarketSent is an AI-driven platform that analyzes financial sentiment from news headlines, social media posts, and market data. It uses Natural Language Processing (NLP) and machine learning to detect investor mood, predict market volatility, and visualize sentiment over time.
Time Series Regression Models
This project analyses the effect of one-year momentum factor on stock returns by computing CAPM, the Fama-French 3-factor model, and a 4-factor model accounting for momentum. The persistence of the momentum effect through the cross-sectional Fama/MacBeth regression is tested to assess whether this factor can explain test asset returns.
Generalization of the Prais Winsten estimator for AR time series of arbitrary order
Predictive modeling system for seasonal bulb removal timing using Growing Degree Days (GDD) and Easter date regression.
To associate your repository with the time-series-regression topic, visit your repo's landing page and select "manage topics."