The participants are asked to develop an algorithm that forecasts the data from the `test.csv` file. The forecast error which is used to determine the accuracy of the model is the **Root Mean Square Error (RMSE)**. The RMSE is also used to determine the scores in the leaderboard as well as to assess the accuracy of your solution in the end. Note that only parts of the data from your submission are used to score your submission in the leaderboard. Once the challenge is over we will use all the data from your submission to determine the best-performing algorithm. So don't waste your time trying to overfit the leaderboard ;-)