training dataset: train.csv
testing dataset to generate results: test.csv
submission of results example: sample_solutions.csv
-
we made a report: dataset_reporting.ipynb
-
we tried a classification XGBoost: first_model_xgboostclassifier.ipynb
-
started regression XGBoost (Main notebook): first_model_xgboostRegressor.ipynb
hackathon source files: Hackathon Amber.zip
We have heard about a feature generation tool: "tsfresh" https://tsfresh.readthedocs.io/en/latest/text/introduction.html
The model was trained using XGBoost by Itility with RMSE =~ 1,5 (if all "1" then 2,25)
customers have to reserve a car 2h upfront to have 100% guarantee of a car.
The cars would be driven by young people to refill the hubs with cars for customers, like a taxi service.