Solutions will be ranked by the obtained RMSE value. The data for the **last 3 months in the dataset (period from 1.10.2023 to 1.1.2024, including these dates)** will serve for the purpose of this evaluation. It is necessary to evaluate RMSE for each location. The best solution will be the model that has the smallest RMSE for all 3 locations, cumulatively. I.e. the best solution will be the cumulative RMSE (the sum of 3 RMSE values, one for each location). For each location the same machine learning algorithm should be used, but trained for every location separately. For example, if you want to use Linear regression, the linear regression with same model parameters should be done 3 times, one time for each location. For each location the RMSE should be calculated and summed up.

**Root Mean Squared Error (RMSE)**
RMSE stands for Root Mean Squared Error. Like MSE, it measures the average squared difference between the predicted values and the actual values. However, RMSE takes the square root of the MSE, which makes it easier to interpret because it is in the same units as the dependent variable.
RMSE is calculated as:
![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F20824360%2Fdd3ed02c69c16472dd79667093167d11%2Fformula.PNG?generation=1715587030016492&alt=media)