Update README.md

README.md

@@ -1,15 +1,30 @@
 
 <div align="center">
 
-# COVID-19 - Intrepertable Forecasting for COVID-19 Economy
+# DemandNet: A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
 
 [![Conference](http://img.shields.io/badge/HICSS-2022-4b44ce.svg)](https://arxiv.org/abs/2203.04383)
 </div>
 
 
-## Star History
 
-[![Star History Chart](https://api.star-history.com/svg?repos=ashfarhangi/COVID-19&type=Date)](https://star-history.com/#ashfarhangi/COVID-19&Date)
+## Overview
+
+The COVID-19 pandemic has significantly impacted the tourism and hospitality sector, with public policies such as travel restrictions and stay-at-home orders affecting tourist activities and business operations. To address this, we developed DemandNet, a novel deep learning framework for predicting time series data under the influence of the COVID-19 pandemic. DemandNet aims to support managerial and organizational decision-making by providing accurate and interpretable forecasts.
+
+## Key Features
+
+- **Feature Selection**: A mechanism to select the top static and dynamic features embedded in the time series data.
+- **Nonlinear Modeling**: A multilayer neural network that provides interpretable insights into previously seen data.
+- **Robust Predictions**: A prediction model leveraging selected features and nonlinear models to make robust long-term forecasts.
+- **Dynamic Dropout Optimization**: Minimizes prediction uncertainties and provides optimal confidence in forecasts.
+
+## Contributions
+
+1. **Feature Selection Mechanism**: Selects the top static and dynamic features of a time series, enhancing the ability to capture complex critical features.
+2. **Multilayer Neural Network**: Derives the nonlinear relationship of selected features to the predictor, providing interpretable insights.
+3. **Novel Prediction Model**: Leverages a dynamic dropout optimization mechanism for robust multi-step time series prediction.
+4. **Capability for New Data**: Capable of predicting newly added time series data without previous training.
 
 
 A repository for COVID-19 factors and impacts on US economy.
@@ -25,10 +40,12 @@ Gathered State-level data:
 loc: data/COVID19_state.xlsx
 
 
+
+[![Star History Chart](https://api.star-history.com/svg?repos=ashfarhangi/COVID-19&type=Date)](https://star-history.com/#ashfarhangi/COVID-19&Date)
+
 ### Prerequisites
 
 - Tensorflow 2.0.2
-- Nvidia GPU 
 
 
 ### Installation
@@ -48,20 +65,14 @@ loc: data/COVID19_state.xlsx
 3. Run model.py 
 
 
-## Contributing
-
-Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are **greatly appreciated**.
-
-Citation for code, data, or paper is as below: 
-
-
-Farhangi, A., Huang, A. and Guo, Z., A Novel Deep Learning Model For Hotel Demand and Revenue Prediction amid COVID-19. Proceedings of the 55th Hawaii International Conference on System Sciences (HICSS), 2022
+# Citation 
 
-```@article{farhanginovel,
+```bibtex
+@inproceedings{farhangidemand,
   title={A Novel Deep Learning Model For Hotel Demand and Revenue Prediction amid COVID-19},
-  author={Farhangi, Ashkan and Huang, Arthur and Guo, Zhishan}
+  author={Farhangi, Ashkan and Huang, Arthur and Guo, Zhishan},
   booktitle={Proceedings of the 55th Hawaii International Conference on System Sciences (HICSS 2022)},
   year={2022},
   organization={HICSS-55}
 }
-```
+```