Claim Missing Document
Check
Articles

Prediksi Fenomena Ekonomi Indonesia Berdasarkan Berita Online Menggunakan Random Forest Khairani, Fitri; Kurnia, Anang; Aidi, Muhammad Nur; Pramana, Setia
Sinkron : jurnal dan penelitian teknik informatika Vol. 6 No. 2 (2022): Articles Research Volume 6 Issue 2, April 2022
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v7i2.11401

Abstract

Economic growth in the first quarter of 2021 based on YoY (Year on Year) is around -0.74%. This figure caused the Indonesian economy to recession after contracting four times since the second quarter of 2020. With positive and negative growth in the value of GDP for each category based on the business sector each quarter, can do future economic growth modelling. The prediction results can be used as an early warning for the government on factors that can maximize and factors that must improve. This study aims to predict the state of economic growth in the next quarter using Random Forest classification. Random Forest combines tree classification and bagging by resampling the data, which reduces the variance of the final model, which is for low variance overfitting. The data used in this study was scrapped from January 2021 to March 2021 on 5 Indonesian online news portals, namely Kompas, Antara, Okezone, Detik, and Bisnis. The independent variable is online news based on GDP category. The dependent variable results from data labelling on each news, up or down, carried out by the Directorate of Balance Sheet of BPS. Based on the calculations with cross-validation of 10, the modelling results obtained 96.51% accuracy, 97% precision, and 97% recall. The random forest method is good for predicting economic growth in the next quarter, namely the second quarter of 2021. Incorrectly predicted only three categories of GDP were: the construction category, the transportation and warehousing category, and the company service category
A comparative assessment on gene expression classification methods of RNA-seq data generated using next-generation sequencing (NGS) Pramana, Setia; Hardiyanta, I Komang Y.; Hidayat, Farhan Y.; Mariyah, Siti
Narra J Vol. 2 No. 1 (2022): April 2022
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narra.v2i1.60

Abstract

Next-generation sequencing or massively parallel sequencing have revolutionized genomic research. RNA sequencing (RNA-Seq) can profile the gene-expression used for molecular diagnosis, disease classification and providing potential markers of diseases. For classification of gene expressions, several methods that have been proposed are based on microarray data which is a continuous scale or require a normal distribution assumption. As the RNA-Seq data do not meet those requirements, these methods cannot be applied directly. In this study, we compare several classifiers including Logistic Regression, Support Vector Machine, Classification and Regression Trees and Random Forest. A simulation study with different parameters such as over dispersion, differential expression rate is conducted and the results are compared with two mRNA experimental datasets. To measure predictive accuracy six performance indicators are used: Percentage Correctly Classified, Area Under Receiver Operating Characteristic (ROC) Curve, Kolmogorov Smirnov Statistics, Partial Gini Index, H-measure and Brier Score. The result shows that Random Forest outperforms the other classification algorithms.
Big Data Analytics for Forecasting Tourism Recovery in Bali Island Using Multivariate Time Series Astrinariswari Rahmadian Prasetyo; Wahyu Calvin Frans Mariel; Geri Yesa Ermawan; Setia Pramana
Jurnal Kepariwisataan Indonesia: Jurnal Penelitian dan Pengembangan Kepariwisataan Indonesia Vol. 18 No. 2 (2024): JKI Edisi Desember 2024
Publisher : Ministry of Tourism and Creative Economy/Tourism and Creative Economy Agency Republic of Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47608/jki.v18i22024.331-350

Abstract

Bali is a famous tourist area and can significantly contribute to the Indonesian tourism sector. The COVID-19 pandemic has made Indonesian tourism, including Bali tourism, experience a decline. In March 2022, COVID-19 cases decreased, and the government began to relax some policies. The tourism sector is vital in economic recovery efforts after the COVID-19 pandemic. Therefore, it is necessary to identify tourism recovery to determine strategies and policies related to Indonesian tourism, especially in Bali. Multivariate time series forecasting of tourism demand can be used to identify tourism recovery using several significant data sources. The methods used are Vector Autoregressive (VAR), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The data used are the monthly official number of tourists, room occupancy rate, Google Trends, number of booking.com user reviews, and nighttime light intensity in Bali Province from January 2019 to December 2022. The results show that the best forecasting method is VAR, and modeling with multivariate time series forecasting can improve the performance of forecasting results. In addition, big data can be used as a source of supporting data that can provide better forecasting results, and the size of the dataset affects the selection of the best model. Furthermore, the descriptive and forecasting analysis results show that Bali tourism has experienced post-pandemic tourism recovery. The strategies and policies of the Bali government to restore Bali tourism faster are good enough.
Analisis Teks untuk Official Statistics: Systematic Literature Review Rahmaniar, Masna Novita; Pramana, Setia
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 12, No 4 (2024)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v12i4.83426

Abstract

Big data menghasilkan berbagai jenis data, termasuk data teks yang memiliki keunggulan dan berpotensi untuk meningkatkan kualitas official statistics. Belum tersedianya literatur yang membahas khusus tentang pemanfaatan analisis teks untuk official statistics mendorong dilakukannya penelitian dengan pendekatan Systematic Literature Review (SLR) guna mengidentifikasi tren penelitian, konsep dasar dan pemanfaatan, serta temuan dan tantangan analisis teks untuk official statistics. Tahapan SLR meliputi planning, data collection, analysis, dan discussion. Pada tahap planning, dirumuskan tiga pertanyaan penelitian sesuai tujuan penelitian. Data collection dilakukan dengan scraping untuk identifikasi tren literatur dan pencarian konvensional pada Google Scholar untuk mendapatkan publikasi relevan terkait pemanfaatan analisis teks. Tahap analysis memvisualisasikan tren penelitian menggunakan diagram batang, jaringan, dan word cloud, dilanjutkan dengan pembahasan pemanfaatan yang dibagi berdasarkan sektor ekonomi, sosial, dan lingkungan. Pada tahap discussion, dilakukan integrasi pembahasan untuk melihat temuan dan tantangan penerapan analisis teks untuk official statistics.   Hasil penelitian menunjukkan bahwa secara keseluruhan, tren literatur yang sering dibahas pada kata kunci official statistics adalah klasifikasi teks untuk literatur berbahasa Indonesia, dan pemodelan topik untuk literatur berbahasa Inggris. Temuan yang diperoleh adalah analisis teks berpotensi memperkaya official statistics melalui prediksi ekonomi, analisis tren sosial, dan pemantauan lingkungan, analisis teks dapat digunakan untuk analisis tunggal maupun variabel pelengkap dalam penelitian. Tantangan utama terletak pada sifat teks yang tidak terstruktur dan fleksibilitasnya dalam berbagai penggunaan, sehingga diperlukan standar pemrosesan, jaminan kerahasiaan, regulasi yang memadai, serta kolaborasi nasional dan internasional agar analisis teks dapat terintegrasi secara efektif sesuai dengan prinsip-prinsip official statistics.
Analisis Spasial Pengaruh Faktor Sosial dan Lingkungan terhadap Prevalensi Hipertensi Zen, Rizqi Annisa; Pramana, Setia
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.1979

Abstract

Hypertension is one of the most common cardiovascular diseases suffered by people in the world. In Indonesia, around 34.1 percent of the population aged 18 years and over suffers from hypertension. Factors that cause hypertension are always associated with genetic and lifestyle factors, even though environmental and social factors also contribute to the occurrence of hypertension. This research was conducted to identify the influence of social and environmental factors on hypertension. The data used comes from Basic Health Research (Riskesdas) in 2018, publications by the Central Statistics Agency (BPS), as well as satellite image data. Satellite imagery is able to provide an accurate and up to date picture of air quality, surface temperature and vegetation distribution. The research was carried out with a spatial approach using the Spatial Autoregressive Model (SAR) method. The results of the analysis show that the lag parameter has a significant effect on the prevalence of hypertension. Meanwhile, the only variable that has a significant influence is Land Surface Temperature (LST), while the variables are GRDP per capita, RLS, TPT, Nitrogen Dioxide (NO2), Carbon Monoxide (CO), Sulfur Dioxide (SO2), and Normalized Difference Vegetation Index (NDVI) has no significant effect on the prevalence of hypertension.
Pemanfaatan Data Citra Satelit Multi Sumber dalam Analisis Spasial Jumlah Kasus Demam Berdarah Dengue (DBD) di Pulau Jawa Tahun 2022 Magfirah, Deanty Fatihatul; Pramana, Setia
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2120

Abstract

Dengue Hemorrhagic Fever (DHF) is one of the world's dangerous infectious diseases, especially in tropical areas, such as Indonesia. The spread of dengue virus is generally caused by an environment that supports the development of DHF vectors, including temperature, rainfall, humidity, surface water, population density, and urbanization. The purpose of this study was to obtain environmental factors that significantly influence the number of DHF cases in Java and to group districts/cities according to the same characteristics by utilizing Sentinel-2, Sentinel-5P, Landsat-8 and CHIRPS satellite imagery. Descriptive analysis and inferential analysis were carried out with Mixed Geographically Weighted Regression (MGWR) spatial modeling for spatial regression analysis of the characteristics of each region. Environmental factors obtained from the analysis results describe each characteristic of the district/city area according to their respective local conditions and six groups are formed with the same regional characteristics and are located close to each other.
Pemodelan Spasial RTH dan Faktor Ekologi Sosial Ekonomi Terhadap Kriminalitas Kota Medan Tahun 2022 Fitriyyah, Nur Retno; Pramana, Setia
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2240

Abstract

Urban crime is an ecological problem due to the interaction of various ecological, social and economic factors. Factors that are thought to trigger crime rates include the availability of green open space (RTH), extreme poverty, population density, light at night, relative wealth, and the number of security services and worship facilities. The green open space identification process utilizes Sentinel-2 Multi Spectral Instrument Level 2A by measuring the Enhanced Vegetation Index (EVI). Spatial regression analysis with Queen Contiguity weighting was used to see the influence of these factors on crime rates between regions. The Ordinary Least Squares model is better than spatial regression because the data does not show spatial autocorrelation between regions, so Ordinary Least Squares can be used as a simpler model. The number of extreme poor people significantly affects the crime rate in Medan City. Policy implications include increased night light in vulnerable areas, access to green spaces, poverty alleviation, and improved security services to create a safer urban environment.
Pemetaan Daerah Aktivitas Perikanan Berbasis Data AIS Busaina, Ladisa; Utami, Nandya Rezky; Pramana, Setia; Krismawati, Dewi
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2299

Abstract

Digital development brings significant changes in data collection and processing, with big data becoming the main source of official statistics. BPS has been using big data since 2015 for more accurate analysis and statistics. Automatic Identification System (AIS) data, an automated ship navigation system, effectively monitors ship movements and is used for official statistics, improving accuracy and reducing human error. However, monitoring of Indonesia's marine activities is still not optimal, as seen from the low contribution of the fisheries sector to GDP and indications of overfishing due to illegal fishing activities (IUU). The use of AIS is important for monitoring illegal activities, but data quality is often low. Data quality assurance through preprocessing is needed. This research will map fisheries activity areas in the waters around Papua Island using AIS data and the DBSCAN algorithm to cluster fishing vessels, in order to improve monitoring of fisheries activities in Indonesia.
MULTICLASS CLASSIFICATION OF MARKETPLACE PRODUCTS WITH MACHINE LEARNING Aditama, Farhan Satria; Krismawati, Dewi; Pramana, Setia
MEDIA STATISTIKA Vol 17, No 1 (2024): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/medstat.17.1.25-35

Abstract

The use of marketplace data and machine learning in the collection of commodity data can provide an opportunity for Statistics Indonesia to complete the commodity directories for various surveys. This research adopts machine learning to train a product classification model based on existing datasets to predict whether a new dataset falls into which KBKI category. The dataset contains more than 32,000 products from 26 classes consisting of product data from two biggest marketplaces in Indonesia. Algorithms used for classification include Random Forests (RF), Support Vector Machines (SVM), and Multinomial Naive Bayes (MNB). Results indicate that MNB is the most effective algorithm when considering the trade-off between accuracy and processing time. MNB achieved the highest micro-average F1 scores, with 91.8% for Tokopedia and 95.4% for Shopee, and has the fastest execution time approximately 5 seconds.
Tourism Resilience Process During Pandemic with Big Data Insight Paramartha, Dede Yoga; Deli, Nensi Fitria; Fitriyani, Ana Lailatul; Pramana, Setia
Jurnal Ikatan Sarjana Ekonomi Indonesia Vol 10 No 3 (2021): December
Publisher : Jurnal Ekonomi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52813/jei.v10i3.184

Abstract

Tourism, which is one of the pillars of the Indonesian economy, has experienced a shock due to the COVID-19 pandemic. This study aims to identify tourism resilience and its relation to the Indonesian economy during the pandemic. Subsequent to this, this study also investigates the competitiveness of tourism in responding to government policies regarding the five national tourism priorities. Descriptive analysis of data sourced from big data is used to support the analysis of tourism resilience in terms of accommodation and accessibility. In addition, Principal Component Analysis is used to build the tourism competitiveness measure of the five priority tourism destinations. The results showed that big data proxy indicators related to tourism generally show recovery signals in the new normal period, even though it hasn’t returned to its pre-pandemic condition and slightly decreased in early 2021. The improvement in this sector was mostly driven by domestic tourist. In terms of the economy, the added value of tourism has decreased considerably during 2020. In addition, based on the measure of tourism competitiveness, Central Java and North Sumatra are provinces that have good support systems for priority tourist destinations in their respective regions.
Co-Authors Achmad Fauzi Bagus Firmansyah Addin Maulana Aditama, Farhan Satria Alifatri, La Ode Ana Lailatul Fitriyani Ana Lailatul Fitriyani Anang Kurnia Arie Wahyu Wijayanto Arif Handoyo Marsuhandi Arkandana, M. Tharif Astrinariswari Rahmadian Prasetyo Astuti, Erni Tri Busaina, Ladisa Cahyono, Bintang Dwitya Charvia Ismi Zahrani Cholifa Fitri Annisa Dandy Adetiar Al Rizki Dede Yoga Paramartha Dede Yoga Paramartha Deli, Nensi Fitria Dewi Krismawati Dewi Krismawati Dhiar Niken Larasati Diory Paulus Pamanik Erni Tri Astuti Erwin Tanur Fajar Fathur Rachman Fajar Fatur Rachman Farakh Khoirotun Nasida Farhan Y. Hidayat Fitriyani, Ana Lailatul Fitriyyah, Nur Retno Geri Yesa Ermawan Hady Suryono Hanafi, Zulfaning Tyas Hardiyanta, I Komang Y. Hendrawan, Daffa Hidayat, Farhan Y. Hizir Sofyan I Komang Y. Hardiyanta I Nyoman Setiawan Imam Habib Pamungkas Jane, Giani Jovita Khairani, Fitri Krismawati, Dewi Ladisa Busaina Linta Ifada Linta Ifada Maftukhatul Qomariyah Virati Magfirah, Deanty Fatihatul Mariel, Wahyu Calvin Frans Maulana Faris Muhammad Farhan Muhammad Nur Aidi Muhammad Tharif Arkandana Munaf, Alfatihah Reno Maulani Nuryaningsih Soekri Putri Nasiya Alifah Utami Nazuli, Muhammad Fachry Nensi Fitria Deli Nora Dzulvawan Novandra, Rio Nur Retno Fitriyyah Nurmalasari, Mieke Nurtia Nurtia Nurwijayanti Oktari, Rina S. Panuntun, Satria Bagus Paramartha, Dede Yoga Putro, Dimas Hutomo Rahmaniar, Masna Novita Rifqi Ramadhan Rimadeni, Yeni Rina S. Oktari Rini Rahani Rutba, Sita Aliya Safrizal Rahman Safrizal Rahman, Safrizal Salim Satriajati Salwa Rizqina Putri Satria Bagus Panuntun Satria Bagus Panuntun Satria Bagus Panuntun Satria Bagus Panuntun Silalahi, Agatha Siswantining, Titin SITI MARIYAH Siti Mariyah Soemarso, Ditoprasetyo Rusharsono Suadaa, Lya Hulliyyatus Sugiri Suhendra Widi Prayoga Takdir Tasriah, Etjih Thosan Girisona Suganda Thosan Girisona Suganda Tigor Nirman Simanjuntak Titin Siswantining Usman Bustaman Usman Bustaman Utami, Nandya Rezky Wahyu Calvin Frans Mariel Wiwin Srimulyani Yuniarti Yuniarti Zen, Rizqi Annisa