Peramalan Arus Kas dengan Pendekatan Time Series Menggunakan Support Vector Machine

Bella Audina, Mohamat Fatekurohman, Abduh Riski


Cash flow is a form of financial report that is used as a measure of the company success in the investment world. So that companies need to forecast the cash flow to manage their finances. Statistics can be applied for the forecasting of cash flow using the Support Vector Machine (SVM) method on the time series data. The aim of this research is to determine the optimal parameter pair model of the Radial Basic Function kernel and to obtain the forecasting results of cash flow using the SVM method on the time series data. The independent variable is needed the data on cash flow from operating income, expenditure and investment expenditure, sum of all cash flow. While the dependent variable is the financial condition based on the Free Cash Flow. The result of this research is a model with the best parameter pairs of the SVM tuning results with the greatest accuracy that is 75%, 82%, 88%, 64% and the forecasting financial condition of PT Cakrawala for the next 16 months.

Keywords: cash flow, forecasting, time series, support vector machine.

Full Text:



Chapman and Hall. Time-Series Forecasting. United States of America: CRC Press. 2000.

Montgomery, D. C., C. L. Jennings, dan M. Kulahci. Introduction to Time Series Analysis and Forecasting. New Jersey: John Wiley & Sons, Inc. 2007.

Adhikari, R. An Introductory on Time Series Modeling and Forecasting. Germany: Lambert Academic Publishing. 2013.

Kakani, R. M. and N. Ramachandran. How To Read A Cash Flow Statement. India: Mcgraw Hill Edu Private Limited. 2010.

Han, J., M. Kamber and J. Pei. Data Mining: Concept and Techniques, Third Edition. Waltham: Morgan Kaufmann Publisher. 2012.

Rusdi. Deteksi Stasioneritas Data Runtun Waktu Melalui Uji Akar-Akar Unit. Jurnal Saintek. 3(1): 78-89. 2011.

Karaa dan Krichene. Credit Risk Assessment using Support Vector Machine and Multilayer Neural Network Models: A Comparative Study Case of a Tunisian Bank. Journal of Accounting and Management Information System. 11(4): 587-620. 2012.

Karyadiputra, E. dan N. Hijriana. Analisis Penerapan Algoritma Naive Bayes untuk Klasifikasi Prioritas Pengembangan Jalan di Provinsi Kalimantan Selatan. Jurnal Teknologi. 9(2): 105-108. 2018.

Eka, P. Implementasi Support Vector Machine (SVM) pada Prediksi Harga Saham Gabungan (IHSG). Jurnal Teknologi dan Rekayasa. 25(1): 24-38. 2020.

Andita, A. dan W. Sulistijanti. Perbaikan Peramalan Produksi Padi di Kabupaten Kendal dengan Menggunakan Metode Support Vector Machine (SVM). The 7th URECOL2018. 2018.


  • There are currently no refbacks.