Iron-Kaggle---Sales-Prediction

IRON Kaggle project done while doing IRONHACK Bootcamp where we had to analyze and use a Machine Learning Project to predict future sales.

Despite having tried to use models like KNN Regressor, Decision Tree and two other models, we ended up using XGBoost because it was the one with a higher score (96.4%) and less overfitting (<0.02).

We normalized the data using MinMaxScaler in order to keep all the used columns as features in the same level. Sales column was the one with higher value compared to the others. One hot encoded date in order to get better results.