Qathrunnada, Ira Zulfa (2024) Analisis Peramalan Angka Penjualan PT Kilang Pertamina Internasional Refinery Unit III Plaju Menggunakan Metode Autoregressive Integrated Moving Average. Project Report. [s.n.], [s.l.]. (Unpublished)
![[thumbnail of 5006211099-Project_Report.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5006211099-Project_Report.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy |
Abstract
Penelitian ini dilakukan dalam rangka kerja praktik di PT Kilang Pertamina Internasional Refinery Unit III Plaju, dengan tujuan untuk menganalisis dan memprediksi angka penjualan harian menggunakan metode Autoregressive Integrated Moving Average (ARIMA). Data yang digunakan merupakan data penjualan harian dari Januari hingga Juni 2024, yang berjumlah 182 observasi. Proses analisis dimulai dengan melakukan analisis statistik deskriptif untuk memahami karakteristik data, diikuti oleh pengujian kestasioneran data menggunakan transformasi Box-Cox dan uji Augmented Dickey-Fuller. Model ARIMA kemudian diidentifikasi melalui analisis plot ACF dan PACF, serta dilakukan pengujian parameter, uji asumsi residual white noise dan normalitas dengan Kolmogorov-Smirnov. Hasil menunjukkan bahwa model terbaik yang memenuhi seluruh asumsi adalah ARIMA(2,0,2) dengan nilai AIC terkecil, yaitu 3130,17. Model ini mampu menghasilkan peramalan penjualan selama tujuh hari ke depan dengan nilai yang fluktuatif, antara Rp4.853.108 hingga Rp12.480.144. Hasil peramalan ini memberikan wawasan penting bagi perusahaan dalam menyusun strategi bisnis dan mengelola risiko keuangan akibat fluktuasi penjualan. Oleh karena itu, disarankan agar perusahaan mempertimbangkan strategi hedging dan pembentukan cadangan risiko keuangan sebagai langkah antisipatif. Selain itu, untuk penelitian selanjutnya dapat digunakan rentang data yang lebih panjang dan metode peramalan lain untuk meningkatkan akurasi prediksi.
=====================================================================================================================================
This study was conducted as part of an internship program at PT Kilang Pertamina Internasional Refinery Unit III Plaju, aiming to analyze and forecast daily sales figures using the Autoregressive Integrated Moving Average (ARIMA) method. The dataset consisted of daily sales data from January to June 2024, with a total of 182 observations. The analysis began with descriptive statistics to understand the data characteristics, followed by stationarity tests using Box-Cox transformation and the Augmented Dickey-Fuller test. ARIMA models were identified through ACF and PACF plots and further evaluated using parameter significance tests, white noise residual tests, and the Kolmogorov-Smirnov normality test. The results showed that the best-fitting model was ARIMA(2,0,2), which had the lowest AIC value of 3130.17 and fulfilled all model assumptions. This model provided a seven-day forecast with fluctuating sales values ranging from IDR 4,853,108 to IDR 12,480,144. The forecasting results offer valuable insights for the company in planning business strategies and managing financial risks due to sales fluctuations. Therefore, it is recommended that the company consider implementing hedging strategies and establishing financial risk reserves as precautionary measures. For future studies, using a longer data period and comparing alternative forecasting methods could improve prediction accuracy.
| Item Type: | Monograph (Project Report) |
|---|---|
| Uncontrolled Keywords: | peramalan penjualan, ARIMA, time series, kestasioneran, manajemen risiko, sales forecasting, ARIMA, time series, stationarity, risk management |
| Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis |
| Depositing User: | Ira Zulfa Qathrunnada |
| Date Deposited: | 18 Jul 2025 06:06 |
| Last Modified: | 18 Jul 2025 06:06 |
| URI: | http://repository.its.ac.id/id/eprint/120079 |
Actions (login required)
 |
View Item |