-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Signed-off-by: pelinkeskin <86728061+pelinkeskin@users.noreply.github.com>
- Loading branch information
1 parent
fd88a5d
commit bc4b4de
Showing
1 changed file
with
1 addition
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1 @@ | ||
This submission for the Kaggle Store Sales - Time Series Forecasting competition showcases a comprehensive approach to predicting store sales using Corporación Favorita's Ecuadorian grocery retail data. Leveraging TensorFlow's DNN capabilities, the project centers on refining time series forecasting skills. Beginning with extensive Exploratory Data Analysis (EDA) and meticulous data preparation, the initial phase established a foundational XGBoost model for feature importance and performance benchmarking. Subsequently, the focus shifted to univariate time series forecasting, adapting the data for deep learning models incorporating LSTM and CNN layers within Tensor. The highlight emerged with a hybrid DNN model, where the LSTM-CNN architecture showcased superiority over the XGBoost model. This hybrid model achieved 0.087 RMSLE and 0.86 R-squared on the global validation set and 0.9 RMSLE on the competition's leaderboard. The results underscore the efficacy of the LSTM CNN hybrid model in forecasting time series. | ||
This submission for the [Kaggle Store Sales - Time Series Forecasting](https://www.kaggle.com/competitions/store-sales-time-series-forecasting) competition showcases a comprehensive approach to predicting store sales using Corporación Favorita's Ecuadorian grocery retail data. Leveraging TensorFlow's DNN capabilities, the project centers on refining time series forecasting skills. Beginning with extensive Exploratory Data Analysis (EDA) and meticulous data preparation, the initial phase established a foundational XGBoost model for feature importance and performance benchmarking. Subsequently, the focus shifted to univariate time series forecasting, adapting the data for deep learning models incorporating LSTM and CNN layers within Tensor. The highlight emerged with a hybrid DNN model, where the LSTM-CNN architecture showcased superiority over the XGBoost model. This hybrid model achieved 0.087 RMSLE and 0.86 R-squared on the global validation set and 0.9 RMSLE on the competition's leaderboard. The results underscore the efficacy of the LSTM CNN hybrid model in forecasting time series. I am pleased to share that this notebook is publicly accessible on [Kaggle](https://www.kaggle.com/code/pelinkeskin/time-series-forecasting-with-tensorflow-lstm-cnn) and welcomes comments and feedback from the community. |