Solve Xporters traffic volume problem

Organized by xporters - Current server time: Oct. 27, 2020, 12:01 p.m. UTC

Current

Development Phase
Nov. 15, 2018, midnight UTC

Next

Final Phase
April 30, 2050, midnight UTC

End

Competition Ends
Never

Solve Xporters traffic volume problem

lemonade stand

Context

As a young and disruptive entrepreuneur, you have just acquired a small lemonade stand located next to an highway. The previous owner of the stand told you: "I noticed that, on average, 1 car out of 100 stops at my stand".

Hopefully, during the last years, he also kept track of the hourly number cars that used this highway, and he gladly accepted to give you his precious records.

Since lemons rot fast and you want to avoid waste, you would like to use this data to train a model that predicts the traffic volume. You also found the hourly meteo records of the last years.

Your mission, should you decide to accept it, is to predict the number of cars that will pass by at a given date, hour, and additional meteorological informations.

The dataset contains 59 features and the solution is the number of cars registred in an hour ranging from 0 to 7280.

Contact

This project was set up by:

  • Florian Bertelli
  • Ghassen Chaabane
  • Moez Ezzeddine
  • Gérémy Hutin
  • Ziheng Li
  • Gaspard Vidal

If you have any question, feel free to contact us.

Evaluation

The problem is a regression problem where you have to define a prediction of a highway traffic volume. Each sample is about a specific day and hour and is characterized by 58 features (including specification about time and different weather descriptions). The target variable is the number of vehicles travelling on the highway during this hour.
You are given for training a data matrix X_train of dimension num_training_samples x num_features and an array y_train of labels of dimension num_training_samples. You must train a model which predicts the labels for two test matrices X_valid and X_test.

There are 2 phases:

  • Phase 1: development phase. We provide you with labeled training data and unlabeled validation and test data. Make predictions for both datasets. However, you will receive feed-back on your performance on the validation set only. The performance of your LAST submission will be displayed on the leaderboard.
  • Phase 2: final phase. You do not need to do anything. Your last submission of phase 1 will be automatically forwarded. Your performance on the test set will appear on the leaderboard when the organizers finish checking the submissions.

Metric

The submissions are evaluated using the R2 metric defined as:

r2 metric

Rules

Submissions must be made before the end of phase 1. You may submit 15 submissions every day and 500 in total.

This challenge is governed by the general ChaLearn contest rules.

Development Phase

Start: Nov. 15, 2018, midnight

Description: Development phase: tune your models and submit prediction results, trained model, or untrained model.

Final Phase

Start: April 30, 2050, midnight

Description: Final phase (no submission, your last submission from the previous phase is automatically forwarded).

Competition Ends

Never

You must be logged in to participate in competitions.

Sign In
# Username Score
1 MOTO 0.9593
2 Caravan 0.9570
3 Velo-Xporters 0.9563