scholarly journals TD 2590 - Aplicação de Modelos Dinâmicos Bayesianos para Projeção de Arrecadação Tributária

2020 ◽  
Keyword(s):  
Time Series ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Structural Time Series ◽  
Absolute Percentage Error ◽  
Structural Time

Neste estudo, empreende-se uma análise econométrica, com vistas à projeção das séries desagregadas do Imposto sobre Operações Relativas à Circulação de Mercadorias e Prestação de Serviços de Transporte Interestadual e Intermunicipal e de Comunicação (ICMS), administradas pelo Conselho Nacional de Política Fazendária do Ministério da Economia (Confaz/ME). Três metodologias foram aplicadas: i) o modelo estrutural dinâmico (MED) – por meio da bayesian structural time series (BSTS); ii) o modelo linear dinâmico (MLD); e iii) o modelo fatorial dinâmico (MFD), todos estes estimados com base na prática bayesiana. Os exercícios econométricos objetivaram três tipos de resultados: i) a avaliação da projeção; ii) a elasticidade do tributo em relação ao fato gerador; e iii) a projeção sessenta meses à frente fora da amostra. Nossa base de dados é composta de dados no período entre janeiro de 2006 a dezembro de 2019. Tendo-se em vista a dificuldade para tratar as séries do Confaz devido à falta de regularidade, os exercícios feitos para validação da projeção apresentaram performance bastante razoável. De cerca de vinte séries para cada estado, aproximadamente 80% registram um erro percentual médio absoluto (Mape – em inglês, mean absolute percentage error) abaixo de 15%.

Towards optimal ATM cash replenishment using time series analysis

2021 ◽  
pp. 1-13
Author(s):  
Muhammad Rafi ◽  
Mohammad Taha Wahab ◽  
Muhammad Bilal Khan ◽  
Hani Raza
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Arima Model ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Absolute Percentage Error ◽  
Automatic Teller Machine ◽  
Proposed Model ◽  
Auto Regressive ◽  
Specific Amount

Automatic Teller Machine (ATM) are still largely used to dispense cash to the customers. ATM cash replenishment is a process of refilling ATM machine with a specific amount of cash. Due to vacillating users demands and seasonal patterns, it is a very challenging problem for the financial institutions to keep the optimal amount of cash for each ATM. In this paper, we present a time series model based on Auto Regressive Integrated Moving Average (ARIMA) technique called Time Series ARIMA Model for ATM (TASM4ATM). This study used ATM back-end refilling historical data from 6 different financial organizations in Pakistan. There are 2040 distinct ATMs and 18 month of replenishment data from these ATMs are used to train the proposed model. The model is compared with the state-of- the-art models like Recurrent Neural Network (RNN) and Amazon’s DeepAR model. Two approaches are used for forecasting (i) Single ATM and (ii) clusters of ATMs (In which ATMs are clustered with similar cash-demands). The Mean Absolute Percentage Error (MAPE) and Symmetric Mean Absolute Percentage Error (SMAPE) are used to evaluate the models. The suggested model produces far better forecasting as compared to the models in comparison and produced an average of 7.86/7.99 values for MAPE/SMAPE errors on individual ATMs and average of 6.57/6.64 values for MAPE/SMAPE errors on clusters of ATMs.

scholarly journals SISTEM PENDUKUNG KEPUTUSAN DALAM PEMILIHAN MODEL DENGAN MENGGUNAKAN METODE TIME SERIES

2018 ◽  
Vol 2 (1) ◽  
Author(s):  
Noer Chamid ◽  
Muhammad Ainul Yaqin ◽  
Nailul Izzah
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Mean Absolute Deviation ◽  
Absolute Deviation ◽  
Trend Line ◽  
Absolute Percentage Error

Analisis time series antara lain memahami dan menjelaskan mekanisme tertentu, meramalkan suatu nilai di masa depan dan mengoptimalkan sistem kendali. Dalam pengambilan keputusan yang menggunakan analisis time series tersebut perlu menggunakan software yang prabayar seperti Minitab, SPSS dan SAS sehingga perlu pembuatan sistem informasi yang mendukung keputusan dalam analisis tersebut. Sistem informasi yang dibuat tersebut akan dilakukan uji coba terhadap kehandalan dan diimplementasikan dalam pengambilan keputusan untuk menentukan penyusunan target pendapatan asli daerah di pemerintah daerah atau data lainnya. Model yang digunakan dalam menduga adalah dengan menggunakan 4 (empat) metode, yaitu : Metode Moving Average, Metode Eksponential Smooting, Metode Linier Trend Line dan Seasonal Adjusment. Dari 4 (empat) metode tersebut, dapat dipilih model yang terbaik dengan menggunakan kriteria menentukan nilai Mean Absolute Deviation (MAD) dan Mean Absolute Percentage Error (MAPE) yang terkecil. Sistem informasi yang dibuat tersebut sudah dilakukan uji coba terhadap kehandalan dan diimplementasikan dalam pengambilan keputusan untuk menentukan penyusunan target pendapatan asli daerah di pemerintah daerah. Sistem Pendukung Keputusan ini dapat dijadikan sebagai tool dalam membuat rekomendasi sebuah keputusan.Kata Kunci: Time Series, Sistem Pendukung Keputusan, Pendapatan Asli Daerah                                                                       

scholarly journals Predicting drought using Bayesian structural time series model

2021 ◽  
Vol 10 (3) ◽  
Author(s):  
Sophia Wang ◽  
Connor Lee ◽  
XL Pang
Keyword(s):  
Time Series ◽  
Well Being ◽  
The United States ◽  
Fire Season ◽  
Series Data ◽  
Percentage Error ◽  
Structural Time Series ◽  
Structural Time ◽  
Model Training ◽  
The Impact

The western U.S. has been experiencing a mega-scale drought since 2000. By killing trees and drying out forests, the drought triggers widespread wildfire activities. In the 2020 California fire season alone, more than 10.3 million acres of land were burned and over 10000 structures were damaged. The estimated cost is over $12 billion. Drought also devastates agriculture and drains the social and emotional well-being of impacted communities.  This work aims at predicting the occurrence and severity of drought, and thus helping mitigate drought related adversaries. A machine learning based framework was developed, including time series data collection, model training, forecast and visualization. The data source is from the National Drought Monitor center with FIPS (Federal Information Processing Standards) geographic identification codes. For model training and forecasting, a Bayesian structural time series (BSTS) based statistical model was employed for a time-series forecasting of drought spatially and temporally. In the model, a time-series component captures the general trend and seasonal patterns in the data; a regression component captures the impact of the drought in measurements such as severity of drought, temperature, etc. The statistical measure, Mean Absolute Percentage Error, was used as the model accuracy metric. The last 10 years of drought data up to 2020-09-01 was used for model training and validation. Back-testing was implemented to validate the model . Afterwards, the drought forecast was generated for the upcoming 3 weeks of the United States based on the unit of county level. 2-D heat maps were also integrated for visual reference.   

scholarly journals Research on Combined Model Based on Multi-Objective Optimization and Application in Wind Speed Forecast

2019 ◽  
Vol 9 (3) ◽  
pp. 423 ◽  
Author(s):  
Shenghui Zhang ◽  
Yuewei Liu ◽  
Jianzhou Wang ◽  
Chen Wang
Keyword(s):  
Time Series ◽  
Wind Speed ◽  
Linear Models ◽  
Time Series Data ◽  
Mean Absolute Percentage Error ◽  
Series Data ◽  
Percentage Error ◽  
Combined Model ◽  
Absolute Percentage Error ◽  
Model Based

Wind power is an important part of a power system, and its use has been rapidly increasing as compared with fossil energy. However, due to the intermittence and randomness of wind speed, system operators and researchers urgently need to find more reliable wind-speed prediction methods. It was found that the time series of wind speed not only has linear characteristics, but also nonlinear. In addition, most methods only consider one criterion or rule (stability or accuracy), or one objective function, which can lead to poor forecasting results. So, wind-speed forecasting is still a difficult and challenging problem. The existing forecasting models based on combination-model theory can adapt to some time-series data and overcome the shortcomings of the single model, which achieves poor accuracy and instability. In this paper, a combined forecasting model based on data preprocessing, a nondominated sorting genetic algorithm (NSGA-III) with three objective functions and four models (two hybrid nonlinear models and two linear models) is proposed and was successfully applied to forecasting wind speed, which not only overcomes the issue of forecasting accuracy, but also solves the difficulties of forecasting stability. The experimental results show that the stability and accuracy of the proposed combined model are better than the single models, improving the mean absolute percentage error (MAPE) range from 0.007% to 2.31%, and the standard deviation mean absolute percentage error (STDMAPE) range from 0.0044 to 0.3497.

Tourism Time Series Forecast

2015 ◽  
pp. 72-87 ◽  
Author(s):  
João Paulo Teixeira ◽  
Paula Odete Fernandes
Keyword(s):  
Time Series ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Test Set ◽  
Time Series Forecast ◽  
Absolute Percentage Error ◽  
Ann Models ◽  
Test Sets

In this chapter four combinations of input features and the feedforward, cascade forward and recurrent architectures are compared for the task of forecast tourism time series. The input features of the ANNs consist in the combination of the previous 12 months, the index time modeled by two nodes used to the year and month and one input with the daily hours of sunshine (insolation duration). The index time features associated to the previous twelve values of the time series proved its relevance in this forecast task. The insolation variable can improved results with some architectures, namely the cascade forward architecture. Finally, the experimented ANN models/architectures produced a mean absolute percentage error between 4 and 6%, proving the ability of the ANN models based to forecast this time series. Besides, the feedforward architecture behaved better considering validation and test sets, with 4.2% percentage error in test set.

scholarly journals PERBANDINGAN METODE FUZZY TIME SERIES DAN HOLT DOUBLE EXPONENTIAL SMOOTHING PADA PERAMALAN JUMLAH MAHASISWA BARU INSTITUT PERTANIAN BOGOR

2013 ◽  
Vol 12 (2) ◽  
pp. 25
Author(s):  
S. STEVEN ◽  
S. NURDIATI ◽  
F. BUKHARI
Keyword(s):  
Time Series ◽  
Exponential Smoothing ◽  
Mean Absolute Percentage Error ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Absolute Percentage Error ◽  
Double Exponential ◽  
Double Exponential Smoothing

Peramalan merupakan kegiatan memprediksi nilai suatu variabel di masa yang akan datang. Tujuan penelitian ini adalah memprediksi jumlah mahasiswa baru Institut Pertanian Bogor dengan menggunakan metode fuzzy time series dan metode pemulusan eksponensial ganda dari Holt serta membandingkan kedua metode tersebut dengan cara melihat tingkat ketepatan peramalan Mean Absolute Percentage Error (MAPE). Metode fuzzy time series menggunakan himpunan fuzzy dalam proses peramalannya sedangkan metode pemulusan eksponensial ganda dari Holt menggunakan pemulusan nilai dari serentetan data dengan cara menguranginya secara eksponensial. Dalam meramalkan jumlah mahasiswa baru Institut Pertanian Bogor, metode fuzzy time series menghasilkan tingkat ketepatan peramalan yang lebih baik dengan nilai MAPE sebesar 6.41 % dibandingkan dengan metode pemulusan eksponensial ganda dari Holt dengan nilai MAPE sebesar 7.75 %. Setelah dilakukan studi kasus, metode pemulusan eksponensial ganda dari Holt akan lebih akurat hasil peramalannya jika data yang digunakan lebih banyak.

scholarly journals Metode Automatic clustering-fuzzy logical relationships pada Peramalan Jumlah Penduduk di Kota Makassar

2019 ◽  
Vol 1 (2) ◽  
pp. 193
Author(s):  
Muhammad Abdy ◽  
Rahmat Syam ◽  
Elfira Haryanensi
Keyword(s):  
Time Series ◽  
Fuzzy Theory ◽  
Secondary Data ◽  
Mean Absolute Percentage Error ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Absolute Percentage Error ◽  
Automatic Clustering ◽  
Forecasting Method ◽  
Fuzzy Logical

Abstrak. Penelitian ini merupakan penerapan metode automatic clustering-fuzzy logical relationships unruk meramalkan jumlah penduduk di Kota Makassar menggunakan data sekunder BPS Kota Makassar yang bertujuan memprediksi jumlah penduduk  tahun 2017-2021. Penelitian diawali dengan penentuan panjang interval, nilai tengah panjang interval, membuat relasi logika fuzzy, fuzzifikasi, defuzzifikasi, dan menghitung nilai error hasil ramalan dengan metode Mean Absolute Percentage Error. Hasil penelitian ini menunjukkan bahwa ramalan jumlah penduduk di Kota Makassar dari tahun 2016 ke 2017 meningkat, tahun 2017 sampai tahun 2019 menurun, dan pada tahun 2019-2021 meningkat dengan keakuratan yang sangat bagus.Kata kunci:Automatic clustering-fuzzy logical relationships, Fuzzy Time Series,TeoriFuzzyAbstract.This research is the application of the forecasting method of fuzzy time series which is the method of automatic clustering fuzzy-logical relationships in forecasting the population of Makassar City using secondary data from BPS Makassar city which aims to predicting the population in year 2017-2021. The discussion starting from the determination of the length of the interval, determining the value of the middle length interval, making relations of fuzzy logic, fuzzification, defuzzification, and calculating the error value of the forecasting result by using the method of Mean Absolute Percentage Error. The result of this research shows that the predictions of the population of Makassar City from 2016 to 2017 increased, from 2017 to 2019 decreased, and in 2019-2021 increased with the very good accuracy. Keywords:Automatic Clustering-Fuzzy Logical Relationships, Fuzzy Time Series,Fuzzy Theory

scholarly journals PERAMALAN INDEKS HARGA SAHAM GABUNGAN DENGAN METODE LOGISTIC SMOOTH TRANSITION AUTOREGRESSIVE (LSTAR)

2018 ◽  
Vol 7 (1) ◽  
pp. 84-95
Author(s):  
Gayuh Kresnawati ◽  
Budi Warsito ◽  
Abdul Hoyyi
Keyword(s):  
Time Series ◽  
Transition Function ◽  
Mean Absolute Percentage Error ◽  
Ar Model ◽  
Smooth Transition ◽  
Percentage Error ◽  
Star Model ◽  
Significance Level ◽  
Absolute Percentage Error ◽  
Smooth Transition Autoregressive

Smooth Transition Autoregressive (STAR) Model is one of time series model used in case of data that has nonlinear tendency. STAR is an expansion of Autoregressive (AR) Model and can be used if the nonlinear test is accepted. If the transition function G(st,γ,c) is logistic, the method used is Logistic Smooth Transition Autoregressive (LSTAR). Weekly IHSG data in period of 3 January 2010 until 24 December 2017 has nonlinier tend and logistic transition function so it can be modeled with LSTAR . The result of this research with significance level of 5% is the LSTAR(1,1) model. The forecast of IHSG data for the next 15 period has Mean Absolute Percentage Error (MAPE) 2,932612%. Keywords : autoregressive, LSTAR, nonlinier, time series

scholarly journals Peramalan Data Ekspor Nonmigas Provinsi Kalimantan Timur Menggunakan Metode Weighted Fuzzy Time Series Lee

2021 ◽  
Vol 14 (1) ◽  
pp. 1-10
Author(s):  
Muhammad Wahdeni Pramana ◽  
Ika Purnamasari ◽  
Surya Prangga
Keyword(s):  
Time Series ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Mean Absolute Percentage Error ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Mean Square ◽  
Absolute Percentage Error

Ekspor merupakan aktivitas perdagangan atau penjualan barang dari dalam negeri ke luar negeri. Ekspor nonmigas sebagai salah satu komponen pembentuk Produk Domestik Regional Bruto (PDRB) sehingga perlu adanya suatu peramalan nilai di masa mendatang. Fuzzy Time Series (FTS) merupakan metode peramalan dengan berdasarkan teori himpunan fuzzy, logika fuzzy, serta hasil peramalan yang dapat dibahasakan (linguistik). Metode Weighted Fuzzy Time Series (WFTS) Lee merupakan perluasan dari metode FTS dengan penambahan pembobotan pada tiap pola relasi yang terbentuk. Tujuan penelitian ini adalah memperoleh nilai peramalan ekspor nonmigas Provinsi Kalimantan Timur pada bulan November 2020 serta memperoleh nilai akurasi peramalan berdasarkan metode Mean Absolute Percentage Error (MAPE) dan Root Mean Square Error (RMSE). Berdasarkan hasil analisis diperoleh nilai akurasi peramalan untuk data Ekspor Nonmigas Provinsi Kalimantan Timur bulan Januari 2019 – Oktober 2020 dengan konstanta pembobot   menggunakan metode MAPE diperoleh hasil keseluruhan dibawah 10% sehingga diperoleh konstanta pembobot terbaik yaitu  dengan nilai MAPE terminimum yaitu sebesar 3,62% dan RMSE minimum sebesar 50,67. Dari hasil tersebut, diperoleh hasil peramalan untuk bulan November 2020 dengan menggunakan kontanta pembobot terbaik  yaitu sebesar 850,96 juta USD.

scholarly journals PERAMALAN BEBAN LISTRIK JANGKA MENENGAH DI WILAYAH TELUK KUANTAN DENGAN METODE FUZZY TIME SERIES CHENG

2019 ◽  
Vol 8 (2) ◽  
pp. 84
Author(s):  
Lana Fauziah ◽  
Dodi Devianto ◽  
Maiyastri Maiyastri
Keyword(s):  
Time Series ◽  
Mean Absolute Percentage Error ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Absolute Percentage Error

Kebutuhan terhadap energi listrik saat ini semakin meningkat karena sebagian besar aspek kehidupan manusia bergantung pada ketersediaan energi listrik. Akibatnya pihak penyalur listrik harus mempersiapkan kebutuhan energi listrik yang semakin meningkat tersebut. Pihak penyalur listrik harus memiliki perencanaan yang baik dan tepat dalam pendistribusian energi listrik. Salah satu upaya yang dapat dilakukan untuk membantu perencanaan tersebut adalah melakukan peramalan beban listrik untuk waktu yang akan datang. Metode fuzzy time series (FTS) Cheng merupakan salah satu metode yang dapat dilakukan untuk peramalan data time series yang menggunakan prinsip-prinsip fuzzy sebagai dasarnya. Pada penelitian ini dilakukan peramalan beban listrik jangka menengah di wilayah Taluk Kuantan dengan metode FTS Cheng untuk beberapa bulan ke depan. Hasil peramalan yang diperoleh tersebut dihitung tingkat akurasi peramalannya dengan menggunakan Mean Absolute Percentage Error (MAPE) sehingga diperoleh tingkat akurasi sebesar 4.45%, yang artinya hasil peramalan beban listrik jangka menengah di wilayah Taluk Kuantan dengan metode FTS Cheng dikatakan sangat baik karena tingkat akurasi yang kurang dari 10%.Kata Kunci: Time Series, Beban Listrik, Fuzzy Time Series Cheng

Sign in / Sign up

Export Citation Format

Share Document