Flight delay prediction - Difficulty: MEDIUM

Problem Description

✈️ Flight Delay Prediction 🕒

🇺🇸 Context

The Federal Aviation Administration wants to develop a system capable of predicting flight arrival delays (in minutes) based on historical information about airlines, airports, and operational conditions.

For this purpose, you are provided with a dataset aggregated at the level of:
(year, month, airline, airport).

📦 Available Features

Name	Description
`sample_id`	Unique sample ID (e.g., `0194048`)
`year`	Reporting year
`month`	Reporting month
`carrier`	Airline code
`carrier_name`	Full airline name
`airport`	Airport code (IATA)
`airport_name`	Airport name
`arr_flights`	Total number of arrived flights
`arr_del15`	Number of arrivals delayed >15 minutes
`carrier_ct`	Delays attributed to the carrier
`weather_ct`	Delays caused by weather conditions
`nas_ct`	Delays caused by the national air system (NAS)
`security_ct`	Security-related delays
`late_aircraft_ct`	Delays caused by late-arriving aircraft
`arr_cancelled`	Cancelled flights
`arr_diverted`	Diverted flights
`delay`	Target variable — total arrival delay (minutes, available only in `train.csv`)

Note: In test.csv, the delay column is absent and needs to be predicted.

🎯 Problem Objective

Train a model to predict delay (in minutes) using the features listed above.

The final result should be submitted as a submission.csv file.

📝 Submission Format

The file should be:

Python
1sample_id,delay20194048,13230194049,040194050,215

where:

sample_id must match the values in test.csv
delay represents an integer, the model's predicted delay

📊 Evaluation

Evaluation is performed using MAE (Mean Absolute Error):

$MAE$

🏆 Final Score

MAE ≤ 400 → 100 points
MAE ≥ 600 → 0 points
Intermediate values receive proportional scores between 0 and 100.

🔎 Notes

You are free to use any ML technique.
Preprocessing, encoding, and feature engineering are allowed.

Good luck and smooth flying! ✨

Files

Download problem files

Submit Solution

Upload the result file manually. You can also attach source code.100 MB maximum in total

Submission File

Click to upload or drag and drop

CSV, ZIP, etc. (MAX. 100MB)

Source Code File (optional)

Click to upload or drag and drop

Archive, notebook or code file

Work and submit from Google Colab

Open the notebook prepared for this problem. The first cell downloads the data; when you are done, submit your solution for evaluation directly from the notebook.

Colab submissions use the same evaluator and limits. Track the result in My Submissions.

MLCompete can access only the notebook it creates in Drive, not your other files.

Doesn’t open? Use a temporary code

Generate the code here, open the public notebook, and enter it when the first cell asks.

Open the public notebook in Colab

Paste the workspace code only when the notebook asks for it. Never share it with someone else.