Article Per Year (5 Year)
p-Index From 2021 - 2026
1.168
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informatika dan Komputer Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) International Journal Of Computer, Network Security and Information System (IJCONSIST) Journal of Data Science Theory and Application Sains Data Jurnal Studi Matematika dan Teknologi
Maharani, Masti Fatchiyah
Universitas Pembangunan Nasional Veteran Jawa Timur
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Mathematics Physics Social Sciences

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Prediksi Risiko Depresi Pascapersalinan Menggunakan Algoritma K-Nearest Neighbor (KNN) Anugerah Putra, Bayu; Fadilah, Nur; Mukhtar, Harun; Fatchiyah Maharani, Masti; Addarisalam, Alif
JURNAL FASILKOM Vol. 15 No. 2 (2025): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v15i2.9562

Abstract

Abstrak Depresi pascapersalinan merupakan gangguan kesehatan mental serius yang sering terlewat pada tahap awal, sehingga dapat menurunkan kualitas hidup ibu dan memengaruhi tumbuh kembang anak. Deteksi dini menjadi kunci, namun pemeriksaan manual kerap memakan waktu dan dipengaruhi bias subjektif. Penelitian ini bertujuan mengembangkan model prediksi risiko depresi pascapersalinan berbasis machine learning dengan algoritma K-Nearest Neighbor (KNN) yang dikenal sederhana, transparan, dan efektif. Dataset berjumlah 1.503 sampel dengan sepuluh atribut psikologis sebagai prediktor serta satu label target risiko depresi. Tahapan preprocessing mencakup imputasi nilai hilang menggunakan rata-rata, pengkodean variabel kategorikal dengan label encoding, serta normalisasi fitur melalui StandardScaler. Data dibagi menjadi 65% untuk pelatihan dan 35% untuk pengujian. Eksperimen dilakukan untuk menentukan nilai K optimal, dan diperoleh K = 15. Hasil evaluasi menunjukkan akurasi sebesar 98,86%, menandakan kemampuan tinggi dalam membedakan individu berisiko dan tidak berisiko depresi pascapersalinan. Model ini berpotensi digunakan tenaga kesehatan untuk skrining awal secara cepat, objektif, dan terstandarisasi, sekaligus mengurangi stigma sosial karena penilaian berbasis data. Meski demikian, penerapan klinis tetap harus memperhatikan keamanan data, keterbukaan hasil, serta mitigasi bias algoritmik agar manfaatnya dapat dirasakan secara adil dan luas.
KLASIFIKASI DEPRESI PADA PELAJAR BERSDASARKAN GAYA HIDUP MENGGUNAKAN METODE TREE-BASED Haq, Dina Zatusiva; Bagus, Yerezqy; Maharani, Masti Fatchiyah; Dica Fitrani, Laqma; Pratama, Moch Deny
Journal of Data Science Theory and Application Vol. 5 No. 1 (2026): JASTA
Publisher : LP3M Universitas Putra Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32639/enqnkx98

Abstract

Depresi pada mahasiswa merupakan salah satu masalah kesehatan mental yang berdampak signifikan terhadap kualitas pendidikan dan produktivitas. Penelitian ini bertujuan untuk mengklasifikasikan depresi berdasarkan faktor gaya hidup menggunakan metode tree-based machine learning, yaitu Decision Tree, Random Forest, XGBoost, dan LightGBM. Data yang digunakan adalah Depression Student Dataset dengan 502 sampel yang mencakup atribut demografis, akademik, dan gaya hidup. Proses penelitian meliputi preprocessing data, pembagian data latih dan uji, pembangunan model, serta evaluasi menggunakan metrik akurasi, sensitivitas, dan spesifisitas. Hasil pengujian menunjukkan bahwa XGBoost memberikan performa terbaik dengan akurasi 94%, sensitivitas 100%, dan spesifisitas 87%, diikuti oleh LightGBM dengan akurasi 92%. Temuan ini menegaskan bahwa algoritma berbasis boosting lebih unggul dibandingkan metode pohon tunggal maupun bagging, sehingga dapat dimanfaatkan sebagai alat bantu deteksi dini depresi pada mahasiswa. Penelitian ini berkontribusi pada pengembangan model prediktif berbasis data yang mendukung pencapaian Sustainable Development Goals (SDG) terkait pendidikan berkualitas dan pekerjaan layak.
ANALISIS KUALITAS PERANGKAT LUNAK LEARNING MANAGEMENT SYSTEM BERBASIS WEB DALAM MENDUKUNG SDG’S 4 (QUALITY EDUCATION) MENGGUNAKAN ISO/IEC 25010 BAGUS, YEREZQY; Haq, Dina Zatusiva; Fitrani, Laqma Dica; Maharani, Masti Fatchiyah
Journal of Data Science Theory and Application Vol. 5 No. 1 (2026): JASTA
Publisher : LP3M Universitas Putra Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32639/z69ayx52

Abstract

Sustainable Development Goals (SDGs) Goal 4 emphasizes the importance of inclusive and equitable quality education. The utilization of information technology, particularly web-based Learning Management Systems (LMS), plays a significant role in supporting sustainable and accessible education. This study aims to analyze the software quality of a web-based LMS in supporting SDGs 4 (Quality Education) using the ISO/IEC 25010 standard. A quantitative research method with a survey approach was employed. Data were collected through questionnaires distributed to 40 LMS users consisting of students and lecturers. The software quality aspects analyzed include functional suitability, usability, reliability, and maintainability. The results indicate that the LMS demonstrates good overall software quality, with functional suitability and usability achieving very good ratings. However, reliability and maintainability aspects still require improvement to ensure long-term system sustainability. This study is expected to serve as a reference for the development and evaluation of sustainable educational software systems.
PERBANDINGAN LSTM DAN PROPHET DALAM PREDIKSI TREN BAJU LEBARAN 2026 BERBASIS GOOGLE TRENDS Maharani, Masti Fatchiyah; Laqma Dica Fitrani; Yerezqy Bagus; Dina Zatusiva Haq
Journal of Data Science Theory and Application Vol. 5 No. 1 (2026): JASTA
Publisher : LP3M Universitas Putra Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32639/tgeq5784

Abstract

Tren busana Lebaran di Indonesia menunjukkan pola musiman yang kuat dan berulang setiap tahun, sehingga prediksi yang akurat menjadi penting bagi perencanaan produksi dan strategi bisnis industri fesyen. Penelitian ini bertujuan membandingkan kinerja metode Prophet dan Long Short-Term Memory (LSTM) dalam memprediksi tren busana Lebaran tahun 2026 menggunakan data Google Trends periode 2018–2025. Model dilatih menggunakan data hingga Desember 2024 dan dievaluasi pada periode pengujian tahun 2025 menggunakan metrik Mean Absolute Error (MAE) dan Root Mean Squared Error (RMSE). Hasil menunjukkan bahwa LSTM memiliki akurasi numerik yang lebih baik, sedangkan Prophet lebih konsisten dalam menangkap pola musiman tahunan. Temuan ini menunjukkan bahwa pemilihan metode prediksi perlu disesuaikan dengan tujuan analisis. Penelitian ini berkontribusi dalam mendukung pengambilan keputusan berbasis data pada industri fesyen serta selaras dengan Sustainable Development Goals (SDGs) 8 terkait pertumbuhan ekonomi yang inklusif dan berkelanjutan.
Stock Price Prediction Using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) Methods Riza Akhsani Setyo Prayoga; Fery Almas Ariansyah; Muhammad Falikhuddin Daffa; Laqma Dica Fitrani; Masti Fatchiyah Maharani; Angga Lisdiyanto; Steven Angkawidjaja
IJCONSIST JOURNALS Vol 7 No 1 (2025): September
Publisher : International Journal of Computer, Network Security and Information System

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33005/ijconsist.v7i1.158

Abstract

This research aims to improve the accuracy of stock price prediction through the application of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) methods, focusing on stocks from the Composite Stock Price Index (CSPI) referred to as the IDX Composite. The research process includes comprehensive steps, including data collection and preprocessing, dataset creation with emphasis on stock closing prices, and division of the dataset into training and test data. The LSTM and GRU models were designed with a recurrent layer and a Dense layer and then trained for 100 epochs with a batch size of 32. Model evaluation was performed by comparing key metrics such as Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Mean Absolute Error (MAE) on the test set. The EPOCH-RMSE graph provides an overview of the changes in the RMSE value during training. The best result of the LSTM model was achieved at the 96th epoch with RMSE 40.36, MSE 1385.97, and MAE 30.09, while GRU achieved peak performance at the 92nd epoch with RMSE 37.33, MSE 908.29, and MAE 25.42. In conclusion, GRU can be considered as a more effective option in predicting JCI stock prices based on performance evaluation using various metrics such as RMSE, MSE, and MAE.
A Comparative Study of Holt-Winters Exponential Smoothing Models for Forecasting Palm Oil Production at PT XYZ Difta Alzena Sakhi; Karina Auralia; Muhammad Nasrudin; Masti Fatchiyah Maharani
Sains Data Jurnal Studi Matematika dan Teknologi Vol 4, No 2: July-December 2026
Publisher : Institut Nurul Islam Mojokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52620/sainsdata.v4i2.420

Abstract

Monthly palm oil production fluctuates due to seasonal patterns and long-term trends, making accurate forecasting essential for operational planning in plantation companies. This study aims to compare seven Holt–Winters Exponential Smoothing models with different trend and seasonal component configurations to forecast the monthly palm oil production of PT XYZ using a univariate approach. The analysis is based on 135 observations covering the period from January 2015 to March 2026. The performance of each model configuration was evaluated using the last 12 months as the test set and assessed based on the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results indicate that the Holt–Winters model with a multiplicative trend and additive seasonality consistently achieved the best forecasting performance, with a MAPE of 5.71%, an MAE of 284.89 tons, and an RMSE of 331.83 tons, substantially outperforming the other six model configurations. The selected model was subsequently used to generate production forecasts for the next 12 months, providing a basis for managerial decision-making in harvest planning, mill capacity management, workforce allocation, and sales strategy.
Digital Business Model Development through the Implementation of a Smart Tuition Payment System Laqma Fitrani; Angga Lisdiyanto; Masti Fatchiyah Maharani; Yerezqy Bagus; Dina Zatusiva Haq
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3282

Abstract

  The tuition payment system is an essential component of school financial administration that supports educational operations. However, many schools still rely on manual or semi-digital payment processes, which often result in delayed transaction recording, data entry errors, and limited transparency in financial reporting. This study aims to develop a web-based online tuition payment application to improve the efficiency, accuracy, and transparency of school financial management. The research employed a qualitative descriptive approach with data collected through observation, interviews, and literature review. System development was conducted using the Agile method, allowing the application to be refined iteratively according to user needs. The system was implemented using PHP and MySQL and includes features such as student data management, tuition billing generation, payment recording, digital receipt generation, and real-time financial reporting. The results indicate that the developed system enhances administrative efficiency, reduces recording errors, and improves the timeliness and transparency of financial reports. Furthermore, the implementation of this system supports the achievement of Sustainable Development Goal (SDG) 4: Quality Education by strengthening governance and sustainability in educational services.
Co-Authors Addarisalam, Alif Angga Lisdiyanto Bagus, Yerezqy Bayu Anugerah Putra Dica Fitrani, Laqma Difta Alzena Sakhi Fery Almas Ariansyah Fitrani, Laqma Dica Haq, Dina Zatusiva Harun Mukhtar Karina Auralia Laqma Dica Fitrani Laqma Dica Fitrani Laqma Fitrani Muhammad Falikhuddin Daffa Muhammad Nasrudin NUR FADILAH Pratama, Moch Deny Riza Akhsani Setyo Prayoga Steven Angkawidjaja Yerezqy Bagus