Skripsi

IMPLEMENTASI ALGORITMA LIGHT GRADIENT BOOSTING MACHINE UNTUK PREDIKSI WAKTU PEMBALAP PADA SESI KUALIFIKASI FORMULA 1

---

Formula 1 qualifying sessions play a crucial role in determining race outcomes, as grid position strongly influences competitive advantage, particularly on circuits with limited overtaking opportunities. This study aims to implement the Light Gradient Boosting Machine (LightGBM) algorithm to predict drivers’ qualifying lap times in Formula 1 using historical time-series data from the 2018–2024 seasons obtained through the FastF1 Python library. The prediction model integrates data from multiple session types, including free practice, qualifying, sprint sessions, and race results, along with contextual features such as circuit characteristics and team performance. The system is developed using the Rational Unified Process (RUP) methodology, covering the Inception, Elaboration, Construction, and Transition phases. Model evaluation is conducted using the 2025 Formula 1 season as unseen data, with performance assessed based on time accuracy, Mean Absolute Error (MAE) of grid position, and MAE of time gap to pole position. Experimental results show that the proposed LightGBM-based model achieves an average time prediction accuracy of 97.55%, with an average MAE of 3.80 positions and an average MAE gap of 0.54 seconds across all circuits. These results indicate that the developed LightGBM model is capable of modeling Formula 1 qualifying data.

---

Availability

Detail Information

Series Title

-

Call Number

T1951182026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xxi, IV-16 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Formula 1

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment