Widyasari, Dessyana Ratna (2021) Penerapan Model ARIMA, Support Vector Regression (SVR), dan Genetic Algortihm – Support Vector Regression (GA-SVR) untuk Meramalkan Penjualan Mobil Toyota di Indonesia. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211940005008-Undergraduate_Thesis.pdf - Accepted Version Download (2MB) | Preview |
Abstract
Penjualan mobil Toyota menduduki peringkat teratas di pasar mobil Indonesia dengan share lebih dari 30% selama beberapa tahun terakhir. Hingga tahun 2019, penjualan mobil Toyota cenderung meningkat, namun mulai tahun 2020, penjualan mobil Toyota merosot tajam dibandingkan tahun-tahun sebelumnya. Hal ini merupakan dampak dari pandemi COVID-19 yang menyebar pada kuartal pertama tahun 2020. Data penjualan mobil umumnya bersifat non linier, sehingga peramalan menggunakan ARIMA akan menghasilkan error yang cukup besar. Penggunaan model SVR (Support Vector Regression) dalam peramalan memiliki performansi yang baik dalam mengatasi permasalahan time series dan data non linier. Pada penelitian ini digunakan model ARIMA dan SVR untuk meramalkan penjualan mobil Toyota. Dalam pemilihan parameter SVR, digunakan metode GA agar diperoleh hasil ramalan yang lebih baik. Berdasarkan hasil analisis yang telah dilakukan, model yang menghasilkan prediksi terbaik adalah SVR dengan optimasi algoritma genetika (GA-SVR) karena memiliki nilai RMSE in sample, RMSE out sample, dan SMAPE out sample yang paling kecil dibandingkan model lainnya. Sehingga, metode ini sudah tepat digunakan untuk meramalkan penjualan mobil Toyota.
====================================================================================================
Toyota has occupied the highest rank regarding car selling within Indonesian car market with percentage of share passes beyond 30% in the past few years. The selling rate had increased gradually until the year of 2019, but it was dramatically declined in 2020. COVID-19 outbreak emergence in the first quartile of 2020 became the pivotal cause of the Toyota’s falling rate. Generally, car selling data is non-linear, and thus the employment of ARIMA would meet fair amount of forecasting errors. The usage of SVR (Support Vector Regression) in forecasting contains excellent performance to solve trouble in time series and non-linear data. This research employed ARIMA model and SVR for forecasting Toyota car selling. In terms of SVR parameter selection, GA method was utilized in order to obtain more reasonable result. According to analysis, the best prediction is resulted from SVR model with genetic algorithm optimization (GA-SVR) as it resulted the smallest value in RMSE in sample, RMSE out sample, and SMAPE out sample compared to other models. Hence, this method is appropriate for forecasting Toyota car selling.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | ARIMA, Genetic Algorithm, Support Vector Regression (SVR), Sales Forecasting, Toyota, ARIMA, Genetic Algorithm, Peramalan Penjualan, Support Vector Regression (SVR), Toyota |
| Subjects: | H Social Sciences > HA Statistics > HA31.3 Regression. Correlation Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA402.5 Genetic algorithms. Interior-point methods. |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Dessyana Ratna Widyasari |
| Date Deposited: | 10 Aug 2021 08:57 |
| Last Modified: | 10 Sep 2024 06:55 |
| URI: | http://repository.its.ac.id/id/eprint/85612 |
Actions (login required)
 |
View Item |