The final project for "How to win a data science competition" Coursera course.
In this project, I used some tricks and created some new features. I also find some data leakages and used them to make the model better. For the last part of the project, I wrote some cells for ensembling. I used stacking as an ensembling technic. For this technic, I created four different models(using lightGBM, CatBoost, RandomForest, and linear regression) in the first level and in the 2nd level in used a linear regression model.
The competition was on Kaggle. If you want to try it yourself you can download the dataset on the competition page.