Penerapan Metode Fuzzy Time Series Markov - Chain Untuk Peramalan Jumlah Pembayaran Pajak Kendaraan Bermotor

Anisyah, Farach Izmi (2025) Penerapan Metode Fuzzy Time Series Markov - Chain Untuk Peramalan Jumlah Pembayaran Pajak Kendaraan Bermotor. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5002211160-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Peningkatan jumlah kendaraan bermotor yang diikuti dengan adanya fluktuasi pada pembayaran pajak kendaraan bermotor pada Badan Pendapatan Daerah Surabaya Timur menimbulkan tantangan dalam memprediksi pendapatan pajak. Metode peramalan tradisional seperti regresi linier sederhana kurang akurat dalam menangani data dengan tingkat fluktuasi yang tinggi. Sementara itu, Fuzzy time series Markov – Chain merupakan penggabungan fuzzy logic, time series, dan Markov – Chain, dapat digunakan sebagai metode untuk meramalkan jumlah pembayaran pajak kendaraan bermotor. Metode fuzzy time series Markov – chain dapat mengatasi fluktuasi dalam data. Oleh karena itu digunakan penerapan metode fuzzy time series Markov – Chain dalam meramalkan jumlah pembayaran pajak kendaraan bermotor. Hasil dari penggunaan metode Fuzzy Time Series Markov – Chain dengan data berjumlah 77, dengan rincian dibagi menjadi 60% data training dan 40% data testing masing – masing berjumlah 46 dan 31 dikatakan optimal pada penerapan peramalan jumlah pembayaran pajak kendaraan bermotor dikarenakan pada akurasi MAPE menujukkan nilai 2.1% dan nilai akurasi RMSE sebesar 0.01 yang menunjukkan bahwa penerapan metode Fuzzy Time Series Markov – Chain efektif dalam memprediksi pembayaran pajak kendaraan bermotor pada wilayah Surabaya Timur.
==============================================================================================================================
The increase in the number of motor vehicles, followed by fluctuations in motor vehicle tax payments at the Regional Revenue Agency of East Surabaya, presents a challenge in forecasting tax revenue. Traditional forecasting methods such as simple linear regression are less accurate in handling data with high levels of fluctuation. Meanwhile, the Fuzzy Time Series Markov–Chain method, which integrates fuzzy logic, time series, and Markov Chain approaches, can be utilized to forecast the amount of motor vehicle tax payments. This method is capable of addressing fluctuations in the data. Therefore, the Fuzzy Time Series Markov–Chain method is applied in forecasting motor vehicle tax payments. The results obtained from using the Fuzzy Time Series Markov–Chain method with a dataset of 77 entries, divided into 60% training data and 40% testing data—consisting of 46 and 31 data points respectively—show optimal performance in forecasting motor vehicle tax payments. This is evidenced by the forecasting accuracy, where the MAPE value is 2.1% and the RMSE value is 0.01, indicating that the application of the Fuzzy Time Series Markov–Chain method is effective in predicting motor vehicle tax payments in the East Surabaya region.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	fuzzy time series Markov – Chain, Pajak Kendaraan Bermotor, Fuzzy Time Series Markov – Chain, Motor Vehicle Tax
Subjects:	Q Science Q Science > QA Mathematics Q Science > QA Mathematics > QA274.7 Markov processes--Mathematical models. Q Science > QA Mathematics > QA248_Fuzzy Sets T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL440 Motorcycles.
Divisions:	Faculty of Mathematics, Computation, and Data Science > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Farach Izmi Anisyah
Date Deposited:	01 Aug 2025 07:46
Last Modified:	01 Aug 2025 07:46
URI:	http://repository.its.ac.id/id/eprint/125945

Actions (login required)

View Item