Garuda - Garba Rujukan Digital

OPTIMASI RANDOM FOREST DENGAN TEKNIK PRUNING UNTUK PREDIKSI DATA NASABAH BMT AL-HIKMAH PERMATA Faturrahman, Kharis; Sucipto, Adi; Sarwido, Sarwido
Jurnal Informatika Teknologi dan Sains (Jinteks) Vol 6 No 3 (2024): EDISI 21
Publisher : Program Studi Informatika Universitas Teknologi Sumbawa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51401/jinteks.v6i3.4715

The development of information technology and artificial intelligence has brought significant changes to the Islamic microfinance industry. Baitul Maal wat Tamwil (BMT) faces challenges in managing and analyzing increasingly complex customer data. This study aims to optimize customer data prediction at BMT Al-Hikmah Permata using the Random Forest algorithm with pruning techniques. The methodology includes customer data collection from 2021 to 2024, data pre-processing, modeling using Random Forest with and without pruning, and model evaluation. Results show that applying pruning techniques significantly improves model performance, with increases of 3.9% in accuracy, 5% in precision, 3.9% in recall, and 4.5% in F1-score. Model complexity is also reduced, with an 81% decrease in node count and a 59% reduction in tree depth. In conclusion, pruning techniques prove effective in enhancing prediction accuracy and efficiency of the Random Forest model for BMT customer data analysis, which can support better decision-making in Islamic microfinance services

SISTEM INFORMASI GEOGRAFIS PEMETAAN FASILITAS KESEHATAN BPJS DI KABUPATEN JEPARA DENGAN ALGORITMA DIJKSTRA BERBASIS WEB Musyarraf, Fajrul Fahry; Sarwido, Sarwido; Kusumodestoni, R. Hadapiningradja
Jurnal Informatika Teknologi dan Sains (Jinteks) Vol 6 No 4 (2024): EDISI 22
Publisher : Program Studi Informatika Universitas Teknologi Sumbawa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51401/jinteks.v6i4.4787

Mapping BPJS health facilities in Jepara Regency is an important step to improve health accessibility. To support this effort, a web-based geographic information system was developed that is designed to map BPJS health facilities and determine the shortest route using Dijkstra's algorithm. This application was built with the Laravel 9 PHP framework and utilizes Leaflet for interactive map display. The results show that this system is effective in presenting complete information about BPJS health facilities in Jepara Regency. The main feature of this application is its ability to calculate and display the shortest route from the user's location to the selected health facility using Dijkstra's algorithm. With this feature, users can easily find the fastest path to the health facility, thus improving the efficiency and accessibility of health care in the region

Training on Tunnel Technology to Increase Salt Production in Jepara Regency Prihatmoko, Dias; Mustofa, Arif; Sarwido, Sarwido; Wijaya, Akhmad Pandhu
Amalee: Indonesian Journal of Community Research and Engagement Vol 5 No 2 (2024): Amalee: Indonesian Journal of Community Research and Engagement
Publisher : LP2M INSURI Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/amalee.v5i2.6019

Rainwater is one of the factors that can affect salt production in Jepara Regency. Salt tunnel technology can retain rainwater so that salt farmers can produce salt even during the rainy season. However, salt farmers have not yet fully utilized this technology. So that assistance is needed to them about the application of salt tunnel technology. This program is conducted to increase the knowledge and skills of salt farmers about salt tunnel technology. The community service partner is UKM Rumah Garam in Surodadi Village, Kedung District, Jepara Regency. The activity was carried out in August 2024. The flow of implementing activities includes preparation, provision of tools and materials, implementation of training, partner assistance and evaluation. The training was attended by partner members with training material on Sustainable Salt Production Technology. The next stage is the field practice of making salt tunnel construction in the salt field owned by one of the participants. The construction is made of bamboo and the soil is coated with geoisolator while the cover uses UV plastic. The community service activity was able to increase the knowledge and skills of the participants about salt tunnel technology which is expected to increase the amount of salt production.

Short-Term Cryptocurrency Price Prediction Using Bi-LSTM Method with Interactive Web Andriansyach, Dimas Jordy; Sarwido, Sarwido; Mulyo, Harminto
Jurnal Teknologi Dan Sistem Informasi Bisnis Vol 6 No 4 (2024): Oktober 2024
Publisher : Prodi Sistem Informasi Universitas Dharma Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jteksis.v6i4.1645

Short-term Bitcoin price prediction is a crucial aspect of transaction decision-making, especially for investors. In this study, a Bidirectional Long Short-Term Memory (Bi-LSTM) model was developed for short-term Bitcoin price prediction. The Bidirectional LSTM is designed to capture temporal context in both directions, allowing the model to process information from past and future time steps simultaneously. The model was validated using real-world data, including Bitcoin stock price datasets. The results show that the model achieved high accuracy, with a Root Mean Square Error (RMSE) of 56.90 on the training data and 157.35 on the test data, along with a Mean Absolute Error (MAE) of 366.40 and 486.63, respectively. The Bidirectional Least Square Memory model accurately predicted Bitcoin prices over a specific time period. This application integrates the model into a web application, enabling users to obtain real-time Bitcoin price predictions through a user-friendly interface.

SISTEM INFORMASI IDENTIFIKASI KAIN TENUN BERBASIS MOBILE PADA KAWASAN INDUSTRI TENUN IKAT JEPARA Sarwido, Sarwido; Widiastuti, Nur Aeni; Reviyandi, Riky
Jurnal Disprotek Vol 15, No 2 (2024)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v15i2.6772

Tenun Ikat Troso atau Kain Ikat Troso adalah kriya tenun Jepara tepatnya dari Desa Troso. Tenun Ikat Troso berupa kain yang ditenun dari helaian benang pakan atau benang lungsin yang sebelumnya diikat dan dicelupkan ke dalam zat pewarna alami. Di Sentra Tenun Ikat ini pengunjung tidak hanya berwisata atau sekedar membeli sepotong kain saja, tetapi juga dapat mempelajari Kain-kain juga, sayangnya informasi yang ada hanya melalui deskripsi yang diberikan oleh penjaga toko yang sedang menjaga. Sayangnya kalau pengunjung toko tiba-tiba melonjak, penjaga kewalahan kalau dicecar pertanyaan oleh banyak pengunjung. Oleh sebab itu dengan dibuatkannya aplikasi ini diharapkan nantinya akan mempermudahkan tugas penjaga yang sedang dalam bertugas. Metode yang digunakan dalam perancangan ini menggunakan metodeÂ prototype, yang dapat digunakan untuk menghubungkan ketidakpahamanÂ client.Â Pengunjung bisa melakukan scan ke Qr code yang sudah disediakan dengan menggunakan smartphone masing-masing dan bisa mendapatkan informasi tentang deskripsi kain. Penelitian ini menghasilkan sebuah Sistem Informasi Identifikasi Kain Tenun Berbasis Mobile yang menyediakan layanan berupa informasi jenis dan motif kain yang jelas di Kawasan Industri Tenun Ikat Jepara.MOBILE-BASED WOVEN FABRIC IDENTIFICATION INFORMATION SYSTEM IN THE JEPARA IKATE WEANING INDUSTRIAL AREAIkat Weaving from Troso or Troso Ikat Fabric is a weaving craft from Jepara, precisely from Troso Village. Troso Ikat is a fabric woven from strands of weft yarn or lungsin yarn that have been tied and dipped into natural dyes. In this Ikat Weaving Center, visitors can not only enjoy tourism or simply buy a piece of fabric but also learn about the fabrics. Unfortunately, the available information is only provided through descriptions given by the shopkeepers on duty. Regrettably, when the number of shop visitors suddenly increases, the shopkeepers are overwhelmed with questions from many visitors. Therefore, with the creation of this application, it is hoped that it will facilitate the duties of the shopkeepers on duty. The method used in this design uses the prototype method, which can be used to bridge the gap of understanding with the clients. Visitors can scan the provided QR code using their smartphones and get information about the fabric's description. This research resulted in a Mobile-Based Woven Fabric Identification Information System that provides services in the form of clear information about the types and patterns of fabric in the Jepara Ikat Weaving Industrial Area.Â

Pemberdayaan Masyarakat Desa Dudakawu Menuju Mandiri dan Berdaya Saing melalui Program Desa Wirausaha: indonesia Febriansyah, Ahmad Diva; Bayu, Muhammad Bayu Nugroho; Sarwido, Sarwido; Septiarani, Diva Herninda; Prasetyo, Doni Agung; Akhis, Muhammad Ilma Akhis; Maknun, Muhammad Jauharul; Almajid, Ahmad Afan; Zahira, Tiara; Raffi, Muhamad Faizal; Putra, Fadhil Athalah; Pangestu, Binar Ageng Raganta; Haq, Muhammad Izzul; Hartoyo, Nindiya Ika Nugraha; Agustina, Hera Khilya; Ilma, Safira Putri Zidni
Jurnal Abdimas Madani dan Lestari (JAMALI) Volume 07, Issue 02, September 2025
Publisher : UII

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20885/jamali.vol7.iss2.art9

Located in Kembang Subdistrict, Jepara Regency, Dudakawu Village possesses significant economic potential. However, its development is hindered by challenges such as inadequate entrepreneurial skills, ineffective marketing strategies, and limited access to digital technology. To overcome these issues, the PPK Ormawa Team of the Student Executive Board from the Faculty of Science and Technology at Unisnu Jepara initiated the "Entrepreneurial Village" program as a community service project. The program aims to improve entrepreneurial skills, enhance the competitiveness of local products, and broaden market access through digital transformation. This initiative utilized several strategies, including entrepreneurship workshops, the establishment of UMKM (Micro, Small, and Medium Enterprises) groups, product branding training, digital marketing education, and the development of innovative products. Activities were carried out through a collaborative approach involving academics, students, local authorities, and the community. Periodic evaluations were conducted using pre- and post-activity questionnaires, interviews, and direct observations to measure the program’s effectiveness in enhancing community skills and business activities. The findings reveal that more than 70% of participants improved their knowledge of entrepreneurship and digital marketing. The UMKM community established during the program served as a collaborative platform for local entrepreneurs, while products such as banana stem chips and the village’s specialty coffee gained added value and greater competitiveness in regional markets through branding and digital marketing efforts. This program has contributed significantly to sustainable, community-driven economic empowerment and offers a replicable model for other villages.

Training on Tunnel Technology to Increase Salt Production in Jepara Regency Prihatmoko, Dias; Mustofa, Arif; Sarwido, Sarwido; Wijaya, Akhmad Pandhu
Amalee: Indonesian Journal of Community Research and Engagement Vol. 5 No. 2 (2024): Amalee: Indonesian Journal of Community Research and Engagement
Publisher : LP2M INSURI Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37680/amalee.v5i2.6019

Rainwater is one of the factors that can affect salt production in Jepara Regency. Salt tunnel technology can retain rainwater so that salt farmers can produce salt even during the rainy season. However, salt farmers have not yet fully utilized this technology. So that assistance is needed to them about the application of salt tunnel technology. This program is conducted to increase the knowledge and skills of salt farmers about salt tunnel technology. The community service partner is UKM Rumah Garam in Surodadi Village, Kedung District, Jepara Regency. The activity was carried out in August 2024. The flow of implementing activities includes preparation, provision of tools and materials, implementation of training, partner assistance and evaluation. The training was attended by partner members with training material on Sustainable Salt Production Technology. The next stage is the field practice of making salt tunnel construction in the salt field owned by one of the participants. The construction is made of bamboo and the soil is coated with geoisolator while the cover uses UV plastic. The community service activity was able to increase the knowledge and skills of the participants about salt tunnel technology which is expected to increase the amount of salt production.

IMPLEMENTASI DATA MINING MENGGUNAKAN METODE LEAST SQUARE UNTUK MEMPREDIKSI JUMLAH PENJUALAN MEBEL DI UD. MEBEL JATI Sarwido, Sarwido; Shofi'in, Faiz Ali; Saputro, Heru
Jurnal Disprotek Vol 14, No 1 (2023)
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jdpt.v14i1.3850

UD Mebel Teak is one of the many shops that provide furniture or household items such as chairs, sideboards, cupboards and so on. The amount of sales transaction data at UD Mebel Jati Stores is currently only used to make sales reports and stock items. In fact, from this sales data mining, it can be searched for an estimate of the amount of sales of an item for a certain month using a calculation method. From here, it can be seen the forecasting of the number of sales for a certain month so that the UD Teak Furniture Store can estimate the supply of furniture. The author will design a data mining implementation system to predict furniture sales using the least squares method to make better use of existing sales transaction data. The design will be implemented using the PHP programming language and MySql database. PHP is a programming language that integrates with HTML to create attractive web pages. This research is expected to produce a datamining implementation system to predict furniture sales using the website-based least squares method. This system is expected to be able to provide information about which furniture is in great demand by consumers in order to provide stock for that furniture. the results of the validation carried out by material experts on sales forecasting decision support systems contained 7 instruments, an ideal score of 63 with an expert score of 63 and a presentation of 100% was declared feasible. And from the verification of media experts from 9 instruments, it was declared feasible with an ideal score of 77 from an expert score of 79 and a presentation of 96.2%.

Peningkatan Akurasi Prediksi Stok Bahan Baku Furnitur Menggunakan Algoritma Random Forest Regressor Berbasis Web Nafi’uzzahidi, Ahmad; Wibowo, Gentur Wahyu Nyipto; Sarwido, Sarwido
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9095

This study aims to address the uncertainty of raw material inventory in the furniture industry through the implementation of the Random Forest Regressor machine learning algorithm. The primary problem addressed is demand fluctuation, which frequently leads to stock management inefficiencies, including overstocking or material shortages that disrupt production processes. The research method employs a quantitative approach with an experimental design, developing a web-based system using the Flask framework and MySQL database. The data sample includes historical sales transaction records and Bill of Materials (BOM) data for furniture products, such as dining tables and minimalist chairs. Prior to modeling, the data underwent a preprocessing stage comprising data cleaning, handling missing values, and normalization to minimize the impact of noise on transaction data. Data collection was conducted through the extraction of internal databases, which were then processed through feature engineering stages based on temporal trends. The results demonstrate that the Random Forest model can predict future raw material requirements with high accuracy, evidenced by a coefficient of determination ($R^2$) of 0.84 and a Mean Absolute Error (MAE) of 5.4.5 These findings prove that a data-driven approach provides more precise stock requirement estimations than conventional methods. In conclusion, the integration of this predictive technology offers practical contributions to accelerating managerial decision-making and optimizing operational efficiency in the medium-scale manufacturing sector. The implications of this study support the theoretical development of artificial intelligence-based decision support systems in supply chain management.

Analisis Data Penjualan Sepatu pada Toko MNNZR.ID Menggunakan Algoritma Apriori dan FP-Growth Nizar, Mohammad Nabil; Sarwido, Sarwido; Sucipto, Adi
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 10 No 4 (2026): OCTOBER 2026
Publisher : Lembaga Otonom Lembaga Informasi dan Riset Indonesia (KITA INFO dan RISET) - Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jtik.v10i4.7014

This study aims to analyze consumer purchasing patterns and compare the performance of Apriori and FP-Growth algorithms using sales transaction data from MNNZR.ID shoe store. A quantitative comparative approach was applied to 520 transaction records collected between June 2023 and January 2025. The data were preprocessed and transformed into a market basket format using one-hot encoding, followed by association rule mining with variations in minimum support and confidence. The results indicate that both algorithms generate identical association rules with similar values of support, confidence, and lift. The strongest rule found is (NB, Adidas, Puma) to Nike, with a confidence of 52.63% and a lift value greater than 1, indicating a positive correlation. However, FP-Growth demonstrates better computational efficiency compared to Apriori. These findings show that association rule mining can effectively support data-driven marketing strategies such as product bundling and cross-selling in retail businesses.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search