Update README.md

Signed-off-by: pelinkeskin <86728061+pelinkeskin@users.noreply.github.com>

Kaggle_StoreSales_TimeSeries_TensorFlow_LSTM-CNN/README.md

@@ -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.