msikorski93 / Hybrid-Time-Series-Modeling Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Time series prediction with hybridization approachs, combining LSTM and XGBoost.

0 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
README.md		README.md
best_lags.ipynb		best_lags.ipynb
hybridization_time_series.ipynb		hybridization_time_series.ipynb
lstm_sales.h5		lstm_sales.h5

Repository files navigation

Hybrid-Time-Series-Modeling

Time series prediction with hybridization approachs, combining LSTM and XGBoost.

	RMSE	R²
LSTM (Baseline)	301.7562	0.9280
Feature Stacking	102.2692	0.9917
Residual Learning	70.4254	0.9961
Ensemble Averaging	140.3238	0.9844

About

Time series prediction with hybridization approachs, combining LSTM and XGBoost.

lstm xgboost residual-learning hybridization time-series-analysis time-series-prediction ensemble-averages feature-stacking

Report repository

Releases

No releases published

Packages

No packages published

Languages

Jupyter Notebook 100.0%