### Can you build a model to predict the amount of water in each waterbody to help preserve this natural resource? 

This is an Analytics competition where your task is to create a Notebook that best addresses the Evaluation criteria below. Submissions should be shared directly with host and will be judged by the Acea Group based on how well they address:
**Methodology/Completeness (min 0 points, max 5 points)**
-   Are the statistical models appropriate given the data? 
-   Did the author develop one or more machine learning models?
-   Did the author provide a way of assessing the performance and accuracy of their solution?
-   What is the Mean Absolute Error (MAE) of the models?
-   What is the Root Mean Square Error (RMSE) of the models?
    

**Presentation (min 0 points, max 5 points)**
-   Does the notebook have a compelling and coherent narrative?
-   Does the notebook contain data visualizations that help to communicate the author’s main points?
-   Did the author include a thorough discussion on the intersection between features and their prediction? For example between rainfall and amount/level of water. 
-   Was there discussion of automated insight generation, demonstrating what factors to take into account?
-   Is the code documented in a way that makes it easy to understand and reproduce?
-   Were all external sources of data made public and cited appropriately?
    

**Application (min 0 points, max 5 points)**
-   Is the provided model useful/able to forecast water availability in terms of level or water flow in a time interval of the year?
-   Is the provided methodology applicable also on new datasets belong to another waterbody?     


###Examples of Winning Notebooks from other Analytics Competitions: 

-   [Luca Basanisi](https://www.kaggle.com/lucabasa) - [Luca's submission](https://www.kaggle.com/lucabasa/quantify-the-madness-a-study-of-competitiveness) created a unique metric to label how competitive a game is.
    
-   [DS4G: Spatial Panel Data Modeling](https://www.kaggle.com/katemelianova/ds4g-spatial-panel-data-modeling).    [@katemelianova](https://www.kaggle.com/katemelianova) and [@artvolgin](https://www.kaggle.com/artvolgin) An excellent submission with comprehensive correction and accounting for confounding factors, with a well reasoned and explained solution and recommendation.