Analisis Time Series Forecasting berdasarkan Pattern Sequence Similarity pada Studi Kasus Data Kas BRI

Ramadhan, Bima Satria (2021) Analisis Time Series Forecasting berdasarkan Pattern Sequence Similarity pada Studi Kasus Data Kas BRI. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 05111740000081-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy

Abstract

Bank BRI merupakan bank yang sejak berdiri didasarkan pelayanan pada masyarakat kecil. Khusus untuk unit BRI lebih memfokuskan pada segmen UMKM. Bagi perusahaan jasa seperti bank BRI hampir 80% pendapatan operasional perusahaan jasa berasal dari kas. Namun, karena kurangnya efisiensi dalam pengelolaan kas yang beredar di unit kerja menyebabkan meningkatnya biaya operasional dan hilangnya potensi penggunaan uang tunai untuk bisnis perbankan BRI. Untuk efisiensi ketersediaan kas bank BRI diperlukan metode yang dapat memprediksi data kas dengan menggunakan data time series. Sehingga pengelolaan data kas dapat menjadi lebih optimal dan efisien. Sebuah model time series akan dibangun dengan menggunakan algoritme Pattern Sequence based Forecasting (PSF) untuk memprediksi data kas ke depannya sehingga diharapkan mampu menekan biaya operasional dan meningkatkan pengelolaan uang kas dengan efisien. Kemudian hasil model dibandingkan dengan algoritme time series lain seperti ARIMA, Prophet dan LSTM. Berdasarkan eksperimen performa model time series PSF menunjukkan hasil tingkatan error dari data kas yang diujikan memiliki hasil dengan nilai NRMSE rata-rata 0,59 dan nilai MAPE rata-rata 53,67%.
========================================================================================================
Bank BRI is a bank that since its inception has been based on services to small communities. Specifically for BRI units, it is more focused on the MSME segment. For service companies such as bank BRI, almost 80% of the company's operating income comes from cash. However, due to the lack of efficiency in the utilization of cash circulating in the work unit, it causes operational costs and potential use of money for BRI's banking business. For efficiency of BRI bank cash availability, a method is needed that can predict cash data using time series data. So that cash management can be more optimal and efficient. A time series model will be built using the Pattern Sequence based Forecasting (PSF) algorithm to predict the data will save so that it is expected to be able to reduce operational costs and improve cash management efficiently. Then the model results are compared with other time series algorithms such as ARIMA, Prophet and LSTM. Based on the experimental performance of the PSF time series model, the error rate results from the cash data tested have results with an average NRMSE value of 0.59 and an average MAPE value of 53.67%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	bank bri, kas, model, psf, time series, bank bri, cash, model, psf, time series
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T385 Visualization--Technique T Technology > T Technology (General) > T57.5 Data Processing
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Bima Satria Ramadhan
Date Deposited:	14 Aug 2021 00:14
Last Modified:	14 Aug 2021 00:14
URI:	http://repository.its.ac.id/id/eprint/86349

Actions (login required)

View Item