Article Per Year (5 Year)
p-Index From 2020 - 2025
1.116
P-Index
This Author published in this journals
All Journal METIK JURNAL Technologia: Jurnal Ilmiah Jurnal Pengabdian Masyarakat Asia Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS
Syafarina, Gita Ayu
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Social Sciences Other

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Implementasi Framework Streamlit Sebagai Prediksi Harga Jual Rumah Dengan Linear Regresi Syafarina, Gita Ayu; Zaenuddin, Zaenuddin
METIK JURNAL Vol 7 No 2 (2023): METIK Jurnal
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/metik.v7i2.608

Abstract

This research aims to develop an Artificial Intelligence (AI)-based application using the Streamlit framework to predict house sale prices in Banjarmasin City using Linear Regression methodology. The increase in demand and supply of properties in Banjarmasin City poses a complex challenge in determining house sale prices. The Linear Regression method was chosen as the primary analytical tool to identify factors influencing house sale prices. This application utilizes historical data of house sale prices and variables such as land area, building area, number of rooms, proximity to public facilities, and geographical location as inputs for the Linear Regression model. Furthermore, the Streamlit framework is employed to create an interactive and user-friendly interface for end-users. The outcome of this research is an AI application that assists potential buyers or sellers in Banjarmasin City in determining competitive prices. By inputting information about the property being evaluated, users can obtain a more accurate estimated sale price based on factors identified by the Linear Regression model. In testing the application, actual house sale price data from Banjarmasin City was used to assess the model's accuracy. The testing results indicate that the application is capable of providing reasonably accurate price estimates, achieving an accuracy level of 67.8%. Thus, this AI application holds the potential to be a valuable tool in the property industry in Banjarmasin City, aiding stakeholders in more informed and data-driven decision-making regarding house sale prices. Additionally, this application could serve as a foundation for further developments in AI research and property price analysis.
PENGEMBANGAN TEKNOLOGI INFORMASI FOR BETTER LIFE PADA PANTI ASUHAN RAHMAH AL-ASRI Fikri, Ihsanul; Hijriana, Nadiya; Sirajuddin, Haji; Syafarina, Gita Ayu; Rusdina, Rusdina; Wathani, Muhammad Rais
Jurnal Pengabdian Kolaborasi dan Inovasi IPTEKS Vol. 2 No. 6 (2024): Desember
Publisher : CV. Alina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59407/jpki2.v2i6.1460

Abstract

Kegiatan Pengabdian kepada Masyarakat (PPM) yang diadakan oleh dosen Universitas Islam Kalimantan (Uniska) bertujuan untuk meningkatkan keterampilan dan pengetahuan teknologi informasi bagi anak-anak dan pengasuh di Panti Asuhan Rahmah Al-Asri, yang berlokasi di Jl. Tembus Mantuil, Seberang Kantor Camat Banjarmasin Selatan. Teknologi informasi, yang mencakup perangkat keras, perangkat lunak, jaringan, serta media pengolahan dan penyajian informasi, merupakan keterampilan yang sangat penting bagi generasi muda untuk menyongsong masa depan yang serba digital. Selain pelatihan penggunaan teknologi informasi, kegiatan ini juga mengajarkan etika dalam berkomunikasi secara online, termasuk pentingnya menjaga privasi, berbagi informasi secara bijak, dan berinteraksi dengan sopan serta hormat di dunia maya. Metode yang digunakan dalam pengabdian ini adalah ceramah, demonstrasi, dan praktik langsung dalam penggunaan teknologi informasi yang relevan dengan kehidupan sehari-hari. Hasil kegiatan menunjukkan peningkatan pemahaman anak-anak panti asuhan dan pengasuh tentang teknologi informasi serta etika komunikasi online. Kegiatan ini diharapkan dapat memberikan manfaat jangka panjang dalam meningkatkan keterampilan digital anak-anak asuh, sehingga mereka lebih siap menghadapi tantangan di dunia yang semakin digital. Kata Kunci: Panti Asuhan, PPM, Teknologi Informasi
Analisis Prediktif Dan Preprocessing Untuk Kualitas Buah Apel Pendekatan Machine Learning Purnomo, Indu Indah; Syafarina, Gita Ayu
Technologia : Jurnal Ilmiah Vol 15, No 4 (2024): Technologia (Oktober)
Publisher : Universitas Islam Kalimantan Muhammad Arsyad Al Banjari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v15i4.15945

Abstract

Peningkatan prediksi kualitas buah apel melalui pendekatan machine learning dan analisis prediktif. Dengan menggunakan dataset yang mencakup berbagai variabel-variabel tersebut mencakup ukuran, berat, kemanisan, garing, juicy, kematangan, keasaman, dan kualitas sebagai variabel target. Penelitian ini berupaya memanfaatkan teknologi machine learning sebagai solusinya. Melalui pengumpulan data yang komprehensif mengenai berbagai karakteristik fisik dan kimia buah apel, serta penerapan berbagai algoritma klasifikasi seperti K-Nearest Neighbors, Random Forest, dan Extra Gradient Boosting, penelitian ini berhasil membangun model prediksi yang efektif. Setelah mengumpulkan dan memproses data yang relevan, berbagai algoritma klasifikasi, termasuk K-Nearest Neighbors, Random Forest, Decision Tree, Extra Trees Classifier, dan Extra Gradient Boosting, telah diterapkan untuk membangun model. Hasil evaluasi menunjukkan bahwa algoritma K-Nearest Neighbors memberikan akurasi tertinggi dalam memprediksi kualitas apel, yaitu 91,375%. Hal ini mengindikasikan bahwa model mampu mengidentifikasi pola yang kuat antara karakteristik fisik dan kimia buah apel dengan kualitasnya. Algoritma ensemble seperti Extra Gradient Boosting dan Extra Trees Classifier juga menunjukkan kinerja yang sangat baik. Nilai AUC yang tinggi menandakan kemampuan model dalam membedakan kelas dengan akurat. Dengan demikian, penelitian ini menjadi landasan untuk pengembangan lebih lanjut dalam memanfaatkan potensi machine learning dalam meningkatkan produktivitas dan kualitas hasil pertanian.
Prediksi Klik Iklan Online Menggunakan Regresi Logistik: Studi Empiris Tentang Pendekatan Berbasis Data Syafarina, Gita Ayu; Zaenuddin, Zaenuddin
Technologia : Jurnal Ilmiah Vol 16, No 2 (2025): Technologia (April)
Publisher : Universitas Islam Kalimantan Muhammad Arsyad Al Banjari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31602/tji.v16i2.15943

Abstract

Penelitian ini bertujuan untuk mengembangkan model yang mampu memprediksi apakah pengguna akan mengklik iklan online atau tidak. Model prediksi ini diharapkan dapat membantu para pengiklan untuk mengalokasikan anggaran secara lebih efektif. Dalam penelitian ini, algoritma Random Forest digunakan untuk membangun model prediksi. Data yang digunakan meliputi informasi demografi pengguna, perilaku penjelajahan, serta karakteristik iklan. Hasil pengujian menunjukkan bahwa model Random Forest mampu mencapai akurasi sebesar 53% dalam memprediksi klik iklan. Meskipun hasil ini cukup baik, masih terdapat ruang untuk peningkatan. Beberapa kendala yang dihadapi dalam penelitian ini antara lain adalah kompleksitas data, ketidakseimbangan kelas, serta perubahan perilaku pengguna yang dinamis. Untuk penelitian selanjutnya, disarankan untuk mengeksplorasi algoritma lain, melakukan feature engineering yang lebih mendalam, serta mempertimbangkan konteks sosial dan budaya pengguna
Implementasi Framework Streamlit Sebagai Prediksi Harga Jual Rumah Dengan Linear Regresi Syafarina, Gita Ayu; Zaenuddin, Zaenuddin
METIK JURNAL (AKREDITASI SINTA 3) Vol. 7 No. 2 (2023): METIK Jurnal
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/metik.v7i2.608

Abstract

This research aims to develop an Artificial Intelligence (AI)-based application using the Streamlit framework to predict house sale prices in Banjarmasin City using Linear Regression methodology. The increase in demand and supply of properties in Banjarmasin City poses a complex challenge in determining house sale prices. The Linear Regression method was chosen as the primary analytical tool to identify factors influencing house sale prices. This application utilizes historical data of house sale prices and variables such as land area, building area, number of rooms, proximity to public facilities, and geographical location as inputs for the Linear Regression model. Furthermore, the Streamlit framework is employed to create an interactive and user-friendly interface for end-users. The outcome of this research is an AI application that assists potential buyers or sellers in Banjarmasin City in determining competitive prices. By inputting information about the property being evaluated, users can obtain a more accurate estimated sale price based on factors identified by the Linear Regression model. In testing the application, actual house sale price data from Banjarmasin City was used to assess the model's accuracy. The testing results indicate that the application is capable of providing reasonably accurate price estimates, achieving an accuracy level of 67.8%. Thus, this AI application holds the potential to be a valuable tool in the property industry in Banjarmasin City, aiding stakeholders in more informed and data-driven decision-making regarding house sale prices. Additionally, this application could serve as a foundation for further developments in AI research and property price analysis.
Training on the Utilization of Mail Merge for Efficient Creation of RT Cover Letters in the Pasar Lama Urban Village Environment Maulani, Jauhari; Ridho, Ihda Innar; Mahalisa, Galih; Amin, Muhammad; Firdaus, Muhammad Iqbal; Syafarina, Gita Ayu; Hijriana, Nadiya
Jurnal Pengabdian Masyarakat Vol. 5 No. 2 (2024): Jurnal Pengabdian Masyarakat
Publisher : Institut Teknologi dan Bisnis Asia Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jpm.v5i2.1237

Abstract

Purpose: This research paper aims to explore the use of mail merge to improve administrative correspondence for the Heads of RT (Neighborhood Associations) and their staff in the Pasar Lama sub-district of Banjarmasin. It identifies challenges with current handwritten methods, such as inefficiency and disorganization, highlighting the importance of this study for enhancing community administrative services.Method: The study employs a qualitative approach through training sessions developed by the PKM team from Uniska. Data collection includes pre- and post-training assessments and participant feedback, focusing on the impact of mail merge on the efficiency and accuracy of letter creation.Practical Applications: The findings suggest that implementing mail merge can significantly reduce the time spent on correspondence, ensure consistent formatting, and improve record-keeping. These enhancements can serve as a model for other regions looking to modernize administrative processes and increase efficiency.Conclusion: In conclusion, this research demonstrates the benefits of mail merge for administrative correspondence, leading to greater efficiency and organization. The results underscore the necessity of modernizing communication methods to address current challenges in local governance.
Co-Authors Fikri, Ihsanul Mahalisa, Galih Maulani, Jauhari Muhammad Amin Muhammad Iqbal Firdaus, Muhammad Iqbal Nadiya Hijriana, Nadiya Purnomo, Indu Indah Ridho, Ihda Innar Rusdina, Rusdina SIRAJUDDIN, HAJI Wathani, Muhammad Rais Zaenuddin Zaenuddin, Zaenuddin