Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

Forecast daily sales for the next 28 days By Using the hierarchical sales data from Walmart. We utilized one-hot and integer encoding for catergorical variables. To capture the short-term and long-term memory of sales trends, we applied moving and expanding averages. Through consistent model training, we achieved an impressive RMSE of 0.1903.

[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"

MOMENT: A Family of Open Time-series Foundation Models

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

Machine Learning Projects on Time Series Forecasting

Learning-Based Atk: a black box adversarial attack method for TSF.

EzStacking: From data to Kubernetes thru Scikit-Learn, FastAPI and Docker in a few clicks and command lines!

Machine Learning and Deep learning-based time series forecasting of Bitcoin stock prices using TensorFlow

Official implementation of "Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting" (https://arxiv.org/abs/2405.06419)

This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods (PVLDB 2024) https://arxiv.org/pdf/2403.20150.pdf

Python Client and Toolkit for DataFrames, Big Data, Machine Learning and ETL in Elasticsearch

Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).

[ICLR 2024] Official Implementation of "Diffusion-TS: Interpretable Diffusion for General Time Series Generation"

Unified Training of Universal Time Series Forecasting Transformers

Traveling Ionospheric Disturbances Forecasting System, funded by the European Community, Horizon Europe

list of papers, code, and other resources

Time series methods for transit ridership forecasting.

A demonstration application for LSTM based time series forecasting with NOAA temperature data. Dataset organized with MongoDB, model performance analyzed with SQL (MySQL), REST API created with FastAPI, and application containerized with Docker