# Welcome to the first round of AI/ML Recruitments into GDSC!
**P.S. MAKE SURE TO READ THIS DOCUMENT COMPLETELY**
Welcome to the Googoda.com, the Travel Booking Company, where we aim to help you plan the perfect vacation. As a data scientist in our team, you are tasked with predicting the vacation rate for popular tourist destinations across the globe.

The vacation rate is an essential metric for us as it helps us determine which destinations to promote during specific times of the year. We believe that the vacation rate is dependent on various factors, such as temperature, humidity, and surface pressure.

To help our customers plan their dream vacations, we need to predict the vacation rate accurately. We have collected historical data from a popular tourist destination, and we need your expertise to create a predictive model that can forecast the vacation rate with high accuracy.

Your task is to analyze the provided dataset and use machine learning techniques to predict the vacation rate for the based on temperature, humidity, and surface pressure. You will need to preprocess the data, perform feature engineering, and select an appropriate machine learning algorithm to build a predictive model.

To test the accuracy of your model, we will provide a test dataset with unseen data. The model's performance will be evaluated based on the Root Mean Squared Error (RMSE) between the predicted and actual vacation rates.

We believe that your analysis and predictive model can help us provide more accurate and personalized vacation recommendations for our customers. So, get ready to pack your bags and explore the world of data science with us!

This Kaggle competition challenges participants to use the POWER NASA Temperature Dataset to develop accurate forecasting models. The dataset provides historical Weather readings from various locations around the world, and participants must build models that can predict future temperatures at these locations based on past readings.

# How to join
To enter the competition, participants must first accept the Competition Rules and gain access to the dataset. They can then download the data and begin building models locally or on Kaggle Notebooks. Once they have generated a prediction file, they can upload it as a submission along with the notebook on Kaggle and receive an accuracy score with a position on the public leaderboard.

# Scoreboard
The public leaderboard is calculated based on the RMSE score of the model created and how well it performs on the given test dataset. This allows participants to see how their models rank against those of other Kagglers.

# Submission format
Participants are required to submit the following:

CSV file containing the ID and VACATION_RATE.
Notebook containing EDA and training with reasonings and additional comments **via a google form that will be shared before the end of the competition**
**P.S. This section is important because you will be judged based on your reasoning ability for the choice of model, data pre-processing etc. so feel free to add markdown cells explaining your steps!**

Please note, once submitted, **your model will be tested against new unseen data points** for final evaluation. This will determine your position on the private leaderboard which will be released once the First Round of the Datathon ends!

If you like working with Python, visualizing and understanding large datasets, you’re in the right place. (Psst… also if you took up the Data Analytics course, then brush up on those skills, and this is your time to shine! )

ALL THE BEST AND GOOD LUCK TO ALL PARTICIPANTS :)