Peramalan Penjualan Mobil Toyota AUTO2000 Kertajaya Menggunakan XGBoost dan Indikator Ekonomi Makro

Vielita, Femi Nabila (2025) Peramalan Penjualan Mobil Toyota AUTO2000 Kertajaya Menggunakan XGBoost dan Indikator Ekonomi Makro. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026211111-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Pada tahun 2024, Toyota menguasai 30% market share dalam penjualan mobil Indonesia dengan Toyota AUTO2000 Kertajaya sebagai salah satu dealer dengan penjualan tertinggi di Jawa Timur. Saat ini, penjualan mobil Indonesia sedang mengalami penurunan. Hal ini diriingi dengan menurunnya daya beli masyarakat dan perekonomian Indonesia sehingga perlu juga diperhatikan bagaimana keadaan ekonomi dapat berpengaruh agar dapat membuat strategi yang optimal. Untuk memastikan manajemen dapat menyusun strategi yang baik, diperlukan analisis prediktif pada Toyota AUTO2000 Kertajaya. Dengan menggunakan metode Machine Learning XGBoost, penelitian ini bertujuan untuk memberikan solusi yang akurat dan adaptif dalam memprediksi penjualan mobil dan membantu dalam pengambilan keputusan. Model XGBoost dilatih menggunakan dataset penjualan Toyota dan dataset ekonomi makro yang mencakup tingkat inflasi, suku bunga, Produk Domestik Bruto (PDB) per kapita, dan nilai tukar, kemudian model diuji menggunakan Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). Peramalan penjualan mobil terbaik merupakan skenario XGB2-B yang menggunakan pemilihan lag ekonomi makro berdasarkan uji korelasi dengan split 80/20. Melalui manual tuning model dapat mencapai performa yang baik yaitu RMSE 10.89 dan MAPE 6.51%.

====================================================================================================================================

In 2024, Toyota dominated 30% of the market share in Indonesia’s car sales, with Toyota AUTO2000 Kertajaya being one of the top-performing dealers in East Java. Currently, Indonesia is experiencing a decline in car sales figures. This is accompanied by a decrease in people’s purchasing power, which can also be seen in Indonesia’s weakened economy. This highlights the economic effect on car sales in Indonesia. To ensure that management can plan an effective strategy, a predictive analysis is required to predict car sales. Using XGBoost, this study aims to provide an accurate and adaptive solution for car sales forecasting to assist decision-making. The XGBoost model was trained using the AUTO2000 Kertajaya car sales data and the selected macro-economy dataset, which includes inflation, gross domestic product per capita, interest rate, and foreign exchange rate. The performance of the model was evaluated using the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The optimal car sales forecasting was achieved using the XGB2-B scenario, which employs macroeconomic lag selection based on correlation testing with an 80/20 train-test split. Using manual hyperparameter tuning, the model was able to achieve a score of 10.89 RMSE and 6.51% MAPE.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Ekonomi Makro, Permalan penjualan, XGBoost, Sustainable industrialisation, Sales forecasting, XGBoost, Macroeconomics, Sustainable industrialisation
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD30.27 Business forecasting Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Femi Nabila Vielita
Date Deposited:	25 Jul 2025 14:35
Last Modified:	25 Jul 2025 14:35
URI:	http://repository.its.ac.id/id/eprint/121739

Actions (login required)

View Item