Pemodelan Prediksi Performa Pemain Penyerang Muda Sepak Bola dengan Pendekatan AHP dan Machine Learning

Perwita, Budi Surya (2025) Pemodelan Prediksi Performa Pemain Penyerang Muda Sepak Bola dengan Pendekatan AHP dan Machine Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5002211127_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Permainan sepak bola merupakan olahraga kompleks yang memiliki banyak variabel dalam menilai performa pemain, khususnya pada posisi penyerang. Minimnya pengalaman dan sulitnya menentukan tolok ukur pemain muda membuat tim kesulitan dalam melakukan prediksi performa para pemain. Sehingga penelitian ini membuat sebuah model prediksi performa pemain penyerang muda sepak bola dengan pendekatan Analytical Hierarchy Process (AHP) dan machine learning. Metode AHP digunakan untuk menentukan pembobotan dari sembilan variabel dalam sepak bola yang diperoleh melalui 15 kuesioner dari para pengamat bola dan menghasilkan tiga variabel utama, yaitu goals dengan bobot 0,208, shots dengan bobot 0,186, dan create chance dengan bobot 0,157. Metode machine learning seperti decision tree, random forest, dan Extreme Gradient Boosting (XGBoost) digunakan untuk membangun model prediksi performa pemain penyerang secara jangka panjang berdasarkan data statistik pemain selama tiga musim terakhir Liga 1 Indonesia. Hasil menunjukkan bahwa model XGBoost memberikan performa terbaik berdasarkan nilai Root Mean Squred Error (RMSE) sebesar 0,000011. Selanjutnya, model XGBoost digunakan untuk memprediksi pemain penyerang muda yang memiliki performa paling menjanjikan yaitu Muhammad Ramadhan Sananta, dengan prediksi 32 goals, 87 shots, dan 20 create chance dalam tiga musim kedepan. Penelitian ini diharapkan dapat membantu klub dalam pengambilan keputusan yang strategis dalam berinvestasi pada pemain muda di posisi penyerang
===================================================================================================================================
Football is a complex sport with many variables in assessing player performance, especially in the attacking position. The lack of experience and difficulty in determining benchmarks for young players makes it difficult for teams to predict their performance. Therefore, this study creates a prediction model for the performance of young attacking football players using the Analytical Hierarchy Process (AHP) and machine learning approaches. The AHP method is used to determine the weighting of nine variables in football obtained through 15 questionnaires from football observers and produces three main variables: goals with a weighting of 0.208, shots with a weighting of 0.186, and created chances with a weighting of 0.157. Machine learning methods such as decision trees, random forests, and Extreme Gradient Boosting (XGBoost) are used to build a long-term prediction model for attacking player performance based on player statistics data from the last three seasons of the Indonesian League 1. The results show that the XGBoost model provides the best performance based on the Root Mean Squared Error (RMSE) value of 0.000011. Furthermore, the XGBoost model was used to predict the most promising young striker, Muhammad Ramadhan Sananta, with a predicted 32 goals, 87 shots, and 20 created chances over the next three seasons. This research is expected to assist clubs in making strategic decisions regarding investments in young strikers

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Prediksi Performa, Pemain Penyerang, Analytical Hierarchy Process (AHP), Machine Learning, Sepak Bola Performance Prediction, Attacking Players, Analytical Hierarchy Process (AHP), Machine Learning, Indonesian League 1
Subjects:	Q Science > QA Mathematics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA401 Mathematical models.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Budi Surya Perwita
Date Deposited:	04 Dec 2025 05:02
Last Modified:	04 Dec 2025 05:02
URI:	http://repository.its.ac.id/id/eprint/128866

Actions (login required)

View Item