Claim Missing Document
Check
Articles

Prediksi Pola Penjualan Barang pada UMKM XYZ dengan Metode Algoritma Apriori Harma Oktafia Lingga Wijaya; Andri Anto Tri. S; A Armanto; Wisdalia Maya Sari
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 3 No. 4 (2022): Juni 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v3i4.4200

Abstract

Through the development of information technology today, the need for clear and accurate information is needed in everyday life, so that information will become an important thing in society. Sometimes high information needs are not accompanied by the presentation of adequate information, often information through the mining process is expected to provide information that was previously hidden in the data warehouse so that it becomes important and valuable information [1]. Utilization of existing data in the information system to support decision-making activities, it is not enough to just rely on operational data, a data analysis is needed to explore the potential of existing information. Decision makers try to take advantage of existing data warehouses to explore useful information to help make decisions, this encourages the emergence of new branches of science to overcome the problem of extracting important or interesting information or patterns from large amounts of data, which is called data mining. 2]. MSME XYZ is one of the leading MSMEs in Lubuklinggau City where this MSME sells various kinds of durian products such as tempoyak, lempok durian, peeled durian, durian pancakes, durian ice cream, durian coffee, durian seed chips etc. Every day MSME XYZ carries out activities such as sales transactions, providing product stock and so on, from the existing sales data so far XYZ has not been able to provide information about the pattern of customer spending habits so that transaction data cannot help leaders in making decisions from data collected. there is. Association analysis or association rule mining is a data mining technique to find the rules of a combination of items. One of the stages of association analysis that has attracted the attention of many researchers to produce efficient algorithms is high frequency pattern analysis (frequent pattern mining). The output of data mining can be used to improve decision making in the future.
INTEGRASI APRIORI & FP-GROWTH PADA BUSINESS INTELLIGENCE SYSTEM UNTUK OPTIMALISASI STRATEGI PENJUALAN Mita Lestari; Harma Oktafia Lingga Wijaya
Jurnal Media Infotama Vol 22 No 1 (2026): April 2026
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v22i1.10910

Abstract

Grocery stores as small-scale retail businesses generate large volumes of sales transaction data that have not been optimally utilized to support business decision-making. These transaction data contain valuable information in the form of customer purchasing patterns that can be analyzed using association rule mining techniques. This study aims to integrate the Apriori and FP-Growth methods into a Business Intelligence System to optimize sales strategies in a grocery store.Sales transaction data were processed using the WEKA application by applying two association rule mining methods, namely Apriori and FP-Growth. The Apriori method was implemented with a minimum confidence value of 90%, while the FP-Growth method used a minimum confidence value of 55%. The results show that the Apriori method produces association rules with a higher level of confidence, particularly for combinations of staple products such as rice, cooking oil, sugar, and instant noodles. Meanwhile, the FP-Growth method generates a wider variety of association rules with lower confidence values but offers superior computational efficiency in terms of processing time.A comparative analysis indicates that the Apriori method is more effective in producing highly reliable association rules for specific strategic recommendations, whereas the FP-Growth method is more suitable for exploring overall purchasing patterns with lower computational complexity. The integration of both methods into a Business Intelligence System provides strategic recommendations related to inventory management, product placement, and promotion planning based on customer purchasing behavior. Therefore, the proposed integration of Apriori and FP-Growth is expected to enhance sales strategy effectiveness and improve the competitiveness of grocery stores.
ANALISIS POLA PEMILIHAN JALUR PENDAKIAN PENGUNJUNG DALAM MENDUKUNG BUSINESS INTELLIGENCE PARIWISATA Mawar Pitri; Harma Oktafia Lingga Wijaya
Jurnal Media Infotama Vol 22 No 1 (2026): April 2026
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v22i1.10953

Abstract

This study aims to analyze visitor behavior patterns in selecting hiking trails at Mount as a basis for decision-making driven by Business Intelligence (BI). The primary issue addressed is the congestion of hikers on specific trails, which risks ecological degradation and diminishes the quality of the tourism experience. This research employs two main methods: Market Basket Analysis (Association Rules) to map hikers' equipment needs based on their chosen trails, and Spatial Zoning Analysis to manage visitor density distribution in real-time.The results indicate a strong association between the "Kawah Hidup" trail selection and the demand for masks, as well as night hiking trails with the rental of flashlights and heavy jackets. Based on these patterns, a service segmentation strategy was developed through four primary packages: "The Adventurer" (Jungle Trail), "The Express Sightseer" (Asphalt Trail), "Summit Explorer" (Gajah Peak & Dead Crater), and "Kawah Hidup Exclusive". Business Intelligence is implemented through digital information boards for zoning management and loyalty programs for local hikers to maintain the sustainability of jungle trails. The conclusion of this research confirms that optimizing logistics stock and digitalizing trail information enhances operational efficiency and supports the ecological sustainability of the Mount forest area.
PREDIKSI HARGA SAHAM BANK MANDIRI BERDASARKAN DATA BMRI HISTORICAL STOCK PRICE Khairul Imam Mahmud; Rudi Kurniawan; Harma Oktafia Lingga Wijaya
Jurnal Media Infotama Vol 22 No 1 (2026): April 2026
Publisher : UNIVED Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37676/jmi.v22i1.10983

Abstract

Stock price movements exhibit dynamic and highly fluctuating characteristics, making accurate prediction challenging when using conventional approaches. Therefore, this study aims to develop and evaluate a stock price prediction model for PT Bank Mandiri (Persero) Tbk using a deep learning approach based on Long Short-Term Memory (LSTM). The LSTM model is applied for time series forecasting by utilizing historical stock price data, with a primary focus on the closing price as the target variable. The historical stock price data of Bank Mandiri undergo preprocessing stages, including data cleaning and normalization using the Min–Max Scaling method, to align data scales and improve training stability and convergence. The proposed LSTM architecture consists of two LSTM layers with dropout mechanisms for regularization, followed by fully connected layers to generate stock price predictions. The model is trained using the Adam optimizer with Mean Squared Error (MSE) as the loss function. Model performance is evaluated using the Mean Absolute Percentage Error (MAPE) metric on the testing dataset. The experimental results show that the LSTM model achieves a MAPE value of 2.7572%, indicating a very high prediction accuracy. Furthermore, the future forecasting results suggest a relatively stable stock price movement with a gradual upward trend in the short term. Based on the findings, it can be concluded that the Long Short-Term Memory (LSTM) method is effective for predicting Bank Mandiri’s stock prices and has strong potential as a data-driven decision support tool for investment analysis, although it should be complemented with fundamental analysis and external market factors
KLASIFIKASI SUARA BURUNG LOKAL INDONESIA MENGGUNAKAN PEMBELAJARAN MESIN Prety Sugiharta Suwita; Tri Hasanah Bimastari Aviani; Harma Oktafia Lingga Wijaya
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.2998

Abstract

Identifikasi spesies burung lewat sinyal bioakustik sangat penting untuk pemantauan biodiversitas, tetapi sering terkendala oleh subjektivitas pengamatan manual dan kesamaan pola kicauan antarspesies. Penelitian ini bertujuan untuk mengembangkan model klasifikasi otomatis dengan memanfaatkan algoritma Support Vector Machine (SVM). Metode diterapkan melalui tahap pra-pemrosesan sinyal berupa normalisasi amplitudo dan penghapusan hening, serta augmentasi data yang intensif. Ekstraksi fitur Mel-Frequency Cepstral Coefficients (MFCC) digunakan untuk menggambarkan karakteristik spektral suara dalam bentuk data numerik. Evaluasi terakhir pada data uji menunjukkan akurasi keseluruhan mencapai 80,95%, dengan presisi sempurna 100% tercatat pada kelas Nuri Tanau. Kekuatan implementasi didukung oleh pengujian inferensi tunggal yang menghasilkan identifikasi akurat dengan tingkat kepercayaan (confidence score) 87,98%. Penemuan ini menegaskan bahwa walaupun ada tantangan pada spesies yang berkerabat dekat, sistem dapat mengklasifikasikan sinyal bioakustik secara efisien sebagai suatu solusi teknologi untuk konservasi.
KLASIFIKASI KEPUASAN PENGGUNA APLIKASI PUSAKA MENGGUNAKAN ALGORITMA DECISION TREE DAN RANDOM FOREST Riska Almira; Davit Irawan; Harma Oktafia Lingga Wijaya
JUSIM (Jurnal Sistem Informasi Musirawas) Vol. 11 No. 1 (2026): JUSIM : Jurnal Sistem Informasi Musi Rawas Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jusim.v11i1.2588

Abstract

Tingkat kepuasan pengguna adalah salah satu dari faktor yang mempengaruhi keberhasilan suatu aplikasi. Kepuasan pengguna dapat dianalisis menggunakan pendekatan machine learning yang mampu mengungkap pola sentimen dari ulasan pengguna. Aplikasi PUSAKA adalah salah satu aplikasi layanan publik yang memberikan akses ke berbagai dokumen penting secara digital. Namun, aplikasi ini menghadapi beberapa keluhan pengguna, seperti masalah force close, kesulitan login, dan update yang bermasalah, yang memengaruhi tingkat kepuasan pengguna. Penelitian ini bertujuan untuk menganalisis tingkat kepuasan pengguna aplikasi PUSAKA berdasarkan ulasan di App Store dengan menggunakan algoritma Decision Tree dan Random Forest. Data penelitian ini terdiri dari 294 ulasan pengguna yang dikumpulkan melalui web scraping, dengan 185 ulasan positif dan 109 ulasan negatif. Data yang diperoleh melalui scraping dianalisis menggunakan model machine learning dengan tahapan preprocessing, pembagian data menggunakan skema 80:20, dan ekstraksi fitur menggunakan TF-IDF. Pengujian algoritma menunjukkan bahwa Random Forest memiliki performa yang lebih baik dengan akurasi 95%, precision 97%, dan recall 94%, dibandingkan Decision Treeyang memiliki akurasi 86%, precision 94%, dan recall 83%. Analisis visualisasi menunjukkan bahwa ulasan negatif sering kali berisi kata-kata seperti absen, tolong, update, dan login, yang dapat dijadikan fokus perbaikan aplikasi. Hasil penelitian ini memberikan rekomendasi kepada pengembang aplikasi PUSAKA untuk meningkatkan pengalaman pengguna melalui penanganan masalah utama yang ditemukan dalam ulasan negatif, serta memastikan stabilitas dan keandalan aplikasi untuk meningkatkan kepuasan pengguna. Kata kunci: Decision Tree, Random Forest, Machine Learning, Aplikasi PUSAKA, Ulasan Pengguna
PENERAPAN METODE TREND PARABOLIC PROJECTION UNTUK PREDIKSI JUMLAH PENGUNJUNG BANK BNI WILAYAH KOTA LUBUKLINGGAU Cici Melika; Harma Oktafia Lingga Wijaya; Bunga Intan
Didaktik : Jurnal Ilmiah PGSD STKIP Subang Vol. 12 No. 3 (2026): Volume 12 No. 3, September 2026 Produce
Publisher : STKIP Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36989/didaktik.v12i3.19198

Abstract

This study aims to analyze and predict the number of visitors at Bank BNI using the Trend Parabolic Projection method. The data used in this research consist of historical visitor data which were analyzed to identify visitor growth trends over time. The research process included data collection, data processing, parabolic regression parameter calculation, data visualization, and forecasting for the next 12 months. The results show that the Trend Parabolic Projection method is capable of representing the data trend effectively, with model parameters becoming more stable as additional data are incorporated. Based on the forecasting results, the number of Bank BNI visitors in 2026 is predicted to gradually increase from approximately 655 visitors at the beginning of the year to around 693 visitors at the end of the year. These findings indicate that the proposed method can provide valuable insights into future visitor trends and can be used as a reference for operational planning and service quality improvement at Bank BNI.
Penerapan Algoritma Random Forest Dalam Klasifikasi Penjurusan Di SMA Negeri Tugumulyo Haiza Marlina; E Elmayati; Antoni Zulius; Harma Oktafia Lingga Wijaya
Brahmana : Jurnal Penerapan Kecerdasan Buatan Vol 4, No 2 (2023): Edisi Juni
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/brahmana.v4i2.188

Abstract

The problem in this study is the difficulty in determining the majors at Tugumulyo State High School, for that a classification model is needed that can determine the right majors in student majors at Tugumulyo State High School. This research uses data collection methods, by observing and recording directly at the research site (observation), asking questions directly to the source (interview), and documentation by reading literature guidelines. The results showed that the majors classification model using the Random Forest algorithm. It can be concluded that the model built using the R programming language gets an accuracy value of 0.9314 and is included in the good classification category.
CROSSELLING CERDAS MELALUI MARKET BASKET ANALYSIS DENGAN ASOCIATION RULE MINING Rani Saputri; M Nur Alamsyah; Harma Oktafia Lingga Wijaya
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 5 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/7h6e4y35

Abstract

Dalam era persaingan bisnis yang semakin ketat, analisis data transaksi penjualan menjadi penting untuk memahami pola pembelian konsumen dan mendukung penyusunan strategi pemasaran yang lebih efektif. Penelitian ini bertujuan mengidentifikasi hubungan antarproduk menggunakan pendekatan Market Basket Analysis melalui teknik Association Rule Mining. Dataset yang digunakan adalah Groceries dataset yang terdiri dari 9.835 transaksi dengan 40 atribut produk. Proses analisis dilakukan menggunakan aplikasi WEKA dengan menerapkan algoritma Apriori dan FP-Growth untuk menghasilkan aturan asosiasi berdasarkan nilai support dan confidence. Hasil penelitian menunjukkan bahwa kedua algoritma mampu mengidentifikasi pola pembelian pelanggan secara efektif. Produk kentang menjadi produk yang paling sering muncul dan memiliki hubungan kuat dengan beberapa produk lain, seperti ikan, sereal, mie, ayam, dan beras. Temuan ini menunjukkan bahwa Market Basket Analysis dapat mendukung strategi cross-selling dan pengambilan keputusan pemasaran berbasis data. Kata Kunci: Market Basket Analysis,Association Rule Mining,FP-Growth,Cross-Selling.
Klasifikasi Kemampuan Ekonomi Calon Siswa Baru dengan Metode K-Nearest Neighbor pada SMA Negeri 1 Musi Rawas Romi Aprillia Soleha; Harma Oktafia Lingga Wijaya; Nelly Khairani Daulay
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 8, No 1 (2023): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v8i1.542

Abstract

The need for an analysis of the classification at SMA Negeri 1 Musi Rawas was the reason for conducting research on the clasification of the economic abilities of new student, determining classification in large numbers was impossible to do manually because it required quite a long time. For that we need a method that can solve classification problems automatically with a computer. in classifying an application in the form of orange is used and in analyzing using the K-Nearest Neighbor method because it has the working principle of fiding the shortest distance between the data to be evaluated with the nearest K in the training data. This study aims to apply the orange application using the K-Nearest Neighbor method and find out what the level of accuracy is with the K-Nearest Neighbor method. From this study the training data is 150 and testing 1 with a K value of 50 gets an accuracy value of 92%.
Co-Authors A.A. Ketut Agung Cahyawan W Adi Saputra Aditya Nugroho Aktavera, Beni Ali Amran Andri Anto Tri Susilo, Andri Anto Anita Sari Antoni Zulius Aprisusanti, Rani Purnama Armanto Armanto Armanto Armanto Armanto armanto armanto Armanto, A Armanto, Armanto Audya, Rosa Ayu Fitria, Sekar Basmansyah, Attaya Rifki Beni Aktavera Beni Mandala Putra Biankha Ariesty Bunga Intan Bunga Intan Chandra Yuliansyah Cici Melika Cindi Wulandari Daulay, Nelly Khairaini Daulay, Nelly Khairani Davit Irawan Davit Irawan Devi Purwanti, Devi Dwi Budi Santoso E Elmayati E Elmayati Elmayati Elmayati, Elmayati Fachry Abda El Rahman Fauzan, Muazim Rahman Fienda Altamevia Haiza Marlina Handayani , Diah Fitria Hartansyah, Dendi Hidayat, Asep Toyib Intan, Bunga Jeki Saputra joni karman Karman, Joni Khairul Imam Mahmud Khoirina Khoirina M Nur Alamsyah Mawar Pitri Mediriansyah Mediriansyah Mita Lestari Mohamad, Fatma Susilawati nansyah, Satria Nelly Khairani Daulay Nopalia Nopalia Nur Alamsyah, Muhammad Nurdiansyah, Deni Prety Sugiharta Suwita Rani Purnama Aprisusanti Rani Saputri Regina Regina Riska Almira Romi Aprillia Soleha Rudi Kurniawan Rudi Kurniawan Rusdiyanto Rusdiyanto Rusdiyanto Rusdiyanto, Rusdiyanto Samsuryadi Samsuryadi Sari, Wisdalia Maya Satrianansyah, Satrianansyah Selviyani sobri, ahmad Soleha, Romi Aprillia Sujayanti, Elies Fifit Susanto Susanto Susanto Susanto Susanto Syamsul Arifin, M. Agus Taufik Rahman Tri Hasanah Bimastari Aviani Wisdalia Maya Sari Wisdalia Maya Sari Wulandari, Cindi Yunita Yunita Yunita Yunita Zulhipni Reno Saputra Elsi