# Time Series Forecasting

## LSTM for Time Series Forecasting

Univariate LSTM Models : one observation time-series data, predict the next value in the sequence

Multivariate LSTM Models : two or more observation time-series data, predict the next value in the sequence

Multiple Input Series : two or more parallel input time series and an output time series that is dependent on the input time series

Multiple Parallel Series : multiple parallel time series and a value must be predicted for each

Univariate Multi-Step LSTM Models : one observation time-series data, predict the multi step value in the sequence prediction.

Multivariate Multi-Step LSTM Models : two or more observation time-series data, predict the multi step value in the sequence prediction.

Multiple Input Multi-Step Output.

Multiple Parallel Input and Multi-Step Output.

## Machine Learning for Multivariate Input

dafrie/lstm-load-forecasting: Electricity load forecasting with LSTM (Recurrent Neural Network) Dataset : Electricity Load ENTSO, Model : LSTM, Type: Multivariate

AIStream-Peelout/flow-forecast: Deep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting)., Dataset: river flow FlowDB Dataset - Flow Forecast - Flow Forecast, flood severity, Model: LSTM, Transformer, Simple Multi-Head Attention, Transformer with a linear decoder, DA-RNN, Transformer XL, Informer, DeepAR

## Statistical Method for Multivariate Input

## Machine Learning for Univariate Input

rishikksh20/LSTM-Time-Series-Analysis: Using LSTM network for time series forecasting Dataset: Sunspot Zurich, Model: LSTM

sagarmk/Forecasting-on-Air-pollution-with-RNN-LSTM: Time Series Forecasting using LSTM in Keras. Dataset: Air Pollution, Model: LSTM

pushpendughosh/Stock-market-forecasting: Forecasting directional movements of stock prices for intraday trading using LSTM and random forest Dataset: Stock Market, Model: LSTM, RF

demmojo/lstm-electric-load-forecast: Electric load forecast using Long-Short-Term-Memory (LSTM) recurrent neural network Dataset: Electric Consumption Model: LSTM

Yongyao/enso-forcasting: Improving the forecasting accuracy of ENSO through deep learning Dataset: ENSO El Nino, Model: LSTM

CynthiaKoopman/Forecasting-Solar-Energy: Forecasting Solar Power: Analysis of using a LSTM Neural Network Dataset: Solar power, Model: LSTM

3springs/attentive-neural-processes: implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout) Dataset: English power consumption, Model: ANP-RNN "Recurrent Attentive Neural Process for Sequential Data", ANP: Attentive Neural Processes, NP: Neural Processes, LSTM

Housiadas/forecasting-energy-consumption-LSTM: Development of a machine learning application for IoT platform to predict electric energy consumption in smart building environment in real time., Dataset: Kaggle energy consuption, Model: LSTM, Seq2Seq

## Statistical Method for Univariate Input

Time Series Forecasting—ARIMA, LSTM, Prophet with Python - by Caner Dabakoglu - Medium : LSTM, ARIMA, Prophet

pyaf/load_forecasting: Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models Dataset: Electricity, Model: Feed forward Neural Network FFNN, Simple Moving Average SMA, Weighted Moving Average WMA, Simple Exponential Smoothing SES, Holts Winters HW, Autoregressive Integrated Moving Average ARIMA, Recurrent Neural Networks RNN, Long Short Term Memory cells LSTM, Gated Recurrent Unit cells GRU, Type: Univariate

jiegzhan/time-series-forecasting-rnn-tensorflow: Time series forecasting Dataset: Daily Temperature, Model: LSTM

zhangxu0307/time_series_forecasting_pytorch: time series forecasting using pytorch，including ANN,RNN,LSTM,GRU and TSR-RNN，experimental code Dataset: Pollution, Solar Energy, Traffic data etec. Model MLP,RNN,LSTM,GRU, ARIMA, SVR, RF and TSR-RNN

rakshita95/DeepLearning-time-series: LSTM for time series forecasting Dataset: ?? Model: ARIMA, VAR, LSTM

mborysiak/Time-Series-Forecasting-with-ARIMA-and-LSTM Dataset: Olypic, LeBron, Zika, Model: ARIMA dan LSTM

stxupengyu/load-forecasting-algorithms: 使用多种算法（线性回归、随机森林、支持向量机、BP神经网络、GRU、LSTM）进行电力系统负荷预测/电力预测。通过一个简单的例子。A variety of algorithms (linear regression, random forest, support vector machine, BP neural network, GRU, LSTM) are used for power system load forecasting / power forecasting. Dataset: Power usage, Model: linear regression, random forest, support vector machine, BP neural network, GRU, LSTM

Abhishekmamidi123/Time-Series-Forecasting: Rainfall analysis of Maharashtra - Season/Month wise forecasting. Different methods have been used. The main goal of this project is to increase the performance of forecasted results during rainy seasons. Dataset: precipitation, Model: ARIMA, LSTM, FNN(Feed forward Neural Networks), TLNN(Time lagged Neural Networks), SANN(Seasonal Artificial Neural Networks

## Jupyter Notebook Examples

### Univariate ARIMA

`import statsmodels`

### Univariate LSTM

`import keras`

### Multivariate VAR

(Note: VAR should only for Stationary process - Wikipedia)

### Multivariate LSTM

## Prophet and Kats from Facebook

## Note on Multivariate and Univariate

## Software

## Other Time Series

Kats - Kats One stop shop for time series analysis in Python

## Precipitation Forecasting

Nowcasting, Upsampling, Interpolation, Super resolution

## Deep Learning for Forecasting

top open source deep learning for time series forecasting frameworks.

Gluon This framework by Amazon remains one of the top DL based time series forecasting frameworks on GitHub. However, there are some down sides including lock-in to MXNet (a rather obscure architecture). The repository also doesn’t seem to be quick at adding new research.

Flow Forecast This is an upcoming PyTorch based deep learning for time series forecasting framework. The repository features a lot of recent models out of research conferences along with an easy to use deployment API. The repository is one of the few repos to have new models, coverage tests, and interpretability metrics.

sktime dl This is another time series forecasting repository. Unfortunately it looks like particularly recent activity has diminished on it.

PyTorch-TS Another framework, written in PyTorch, this repository focuses more on probabilistic models. The repository isn’t that active (last commit was in November).

## eBook Forecasting

NIST/SEMATECH e-Handbook of Statistical Methods engineering statistics

## Timeseries Forecasting

## Timeseries Forecasting Book

## Timeseries Forecasting Reading

## Timeseries RNN

## Timeseries Forecasting

## Time-series Forecasting

## VAR

## time Series

## LSTM

## Time Series Toolbox

Prophet Prophet | Forecasting at scale.

XGboost, LGBM, pmdarima, stanpy (for bayesian modelling)

Prophet - seems to be the current 'standard' choice

ARIMA - Classical choice

Exponential Moving Average - dead simple to implement, works well for stuff that's a time series but not very seasonal

Kalman/Statespace model - used by Splunk's predict[1] command (pretty sure I always used LLP5)

Prophet, statsmodels, tf.keras for RNNs.

tensorflow probability's time series package.

PyTorch for recurrent nets

State of the art is 1D convnets, bleeding edge is transformers.

pycaret timeseries

lgbm light gbm

cvxpy

TensorFlow's LSTMCell

LSTMs have been going the way of the dinosaurs since 2018. If you really need a complex neural network (over 1D convolution approaches), transformers are the current SOTA. Demand forecasting with the Temporal Fusion Transformer—pytorch-forecasting documentation

sktime

bssts

statsmodels

## Books

## Forecasting Comparison

statsforecast/experiments/m3 at main · Nixtla/statsforecast # Statistical vs Deep Learning forecasting methods

Last updated