A PERANCANGAN MODEL PREDIKSI PERMINTAAN PRODUK PADA TOKO HAVE TAPE MENGGUNAKAN METODE REGRESI LINEAR
Abstract
ABSTRAKToko Have Tape mengalami kendala dalam memprediksi permintaan produk untuk perencanaan stok karena prosesnya masih manual dan mengandalkan intuisi. Hal ini berpotensi menyebabkan kesalahan prediksi dan manajemen stok yang tidak optimal. Penelitian ini bertujuan membangun sistem berbasis website yang mengintegrasikan model Machine Learning dengan metode Regresi Linear Berganda untuk mengotomatisasi prediksi permintaan produk, sehingga meningkatkan akurasi dan efisiensi waktu. Sistem dikembangkan menggunakan metode Waterfall. Model regresi dibangun dengan Scikit-Learn (Python) menggunakan variabel margin keuntungan dan permintaan bulan sebelumnya. Sistem diimplementasikan sebagai website dinamis dengan framework Flask untuk kemudahan akses. Hasil evaluasi model pada data produk "Lakban Coklat 100 Yard" menunjukkan nilai R² sebesar 0,382, MAPE 11,55%, dan RMSE 50,29. Pengujian fungsional (Black Box) dan struktural (White Box) membuktikan sistem berjalan sesuai spesifikasi. Simpulan penelitian adalah sistem yang dibangun berhasil mengurangi ketergantungan pada prediksi manual dan mempercepat proses peramalan di Toko Have Tape. Saran untuk pengembangan selanjutnya adalah mengeksplorasi algoritma lain dan menggunakan dataset yang lebih besar.
Kata Kunci: Prediksi Permintaan, Machine Learning, Regresi Linear Berganda, Website, Manajemen Stok.
ABSTRACTThe Have Tape store faces challenges in predicting product demand for stock planning because the process is still manual and relies on intuition. This can potentially lead to prediction errors and suboptimal stock management. This research aims to build a website-based system that integrates a Machine Learning model with the Multiple Linear Regression method to automate product demand prediction, thereby improving accuracy and time efficiency. The system was developed using the Waterfall method. The regression model was built with Scikit-Learn (Python) using profit margin and previous month's demand as variables. The system was implemented as a dynamic website with the Flask framework for easy access. Model evaluation results on the "100 Yard Brown Duct Tape" product data showed an R² value of 0.382, a MAPE of 11.55%, and an RMSE of 50.29. Functional (Black Box) and structural (White Box) testing demonstrated that the system performed according to specifications. The research concluded that the system successfully reduced reliance on manual predictions and accelerated the forecasting process at the Have Tape store. Suggestions for further development include exploring other algorithms and using a larger dataset.
Keywords: Demand Prediction, Machine Learning, Multiple Linear Regression, Website, Stock Management.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Reza Fadillah, Sartika Lina Mulani Sitio

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Prosiding Seminar Informatika dan Sistem Informasi have CC-BY-NC-SA or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities, Prosiding Seminar Informatika dan Sistem Informasi recognize that free access is better than priced access, libre access is better than free access, and libre under CC-BY-NC-SA or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
Prosiding Seminar Informatika dan Sistem Informasi is licensed under a Creative Commons Attribution 4.0 International License
YOU ARE FREE TO:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms