Large scale traffic forecasting with gradient boosting, Traffic4cast 2022 challenge

October 31, 2022 · Entered Twilight · 🏛 arXiv.org

Repo contents: .gitignore, LICENSE, README.MD, apply_nb_matrixes.ipynb, calculate_neighbour_features.ipynb, conf.py, core_create_target_encodings.ipynb, core_final.ipynb, core_generate_submission.py, extended_final.ipynb, extended_generate_supersegment_speed_feats.ipynb, generate_principal_components.py, precompute_volume_features.py, preprocess_all.sh, requirements.txt, utils.py

Authors Martin Lumiste, Andrei Ilie arXiv ID 2211.00157 Category cs.LG: Machine Learning Citations 3 Venue arXiv.org Repository https://github.com/skandium/t4c22 ⭐ 9 Last Checked 3 months ago

Abstract

Accurate traffic forecasting is of the utmost importance for optimal travel planning and for efficient city mobility. IARAI (The Institute of Advanced Research in Artificial Intelligence) organizes Traffic4cast, a yearly traffic prediction competition based on real-life data [https://www.iarai.ac.at/traffic4cast/], aiming to leverage artificial intelligence advances for producing accurate traffic estimates. We present our solution to the IARAI Traffic4cast 2022 competition, in which the goal is to develop algorithms for predicting road graph edge congestion classes and supersegment-level travel times. In contrast to the previous years, this year's competition focuses on modelling graph edge level behaviour, rather than more coarse aggregated grid-based traffic movies. Due to this, we leverage a method familiar from tabular data modelling -- gradient-boosted decision tree ensembles. We reduce the dimensionality of the input data representing traffic counters with the help of the classic PCA method and feed it as input to a LightGBM model. This simple, fast, and scalable technique allowed us to win second place in the core competition. The source code and references to trained model files and submissions are available at https://github.com/skandium/t4c22 .