Implementasi Decision Tree untuk Prediksi Kebutuhan Bahan Kain Pada Usaha Konveksi
Abstract
Convection businesses often inaccurately estimate fabric demand, leading to stock waste or material shortages that disrupt production. This study aimed to improve fabric demand prediction accuracy at Threetan Collection by applying the Decision Tree Regressor algorithm. The model was developed using historical production data consisting of five key variables: pants size, fabric type, fabric brand, pants model, and order quantity. The dataset was divided into 80% training and 20% testing. Two model versions were developed: one without parameter optimization and another with hyperparameter optimization using RandomizedSearchCV. The optimized model demonstrated better performance, achieving a mean absolute error of 0.7851 yards and explaining 98.62% of data variability. The results show that the proposed model enhances fabric stock management efficiency. The model has been implemented in a web-based application using Flask and MySQL to support a more effective production process.
Keywords: Decision Tree Regressor; Fabric demand prediction; Hyperparameter optimization; RandomizedSearchCV; Flask
Abstrak
Usaha konveksi sering mengalami kesalahan dalam estimasi kebutuhan bahan kain, yang menyebabkan pemborosan stok atau kekurangan bahan yang menghambat produksi. Penelitian ini bertujuan untuk meningkatkan akurasi prediksi kebutuhan kain pada usaha konveksi Threetan Collection dengan menerapkan algoritma Decision Tree Regressor. Model dikembangkan berdasarkan data historis produksi yang terdiri dari lima variabel utama: ukuran celana, jenis kain, merek kain, model celana, dan jumlah pesanan. Dataset dibagi menjadi 80% untuk pelatihan dan 20% untuk pengujian. Dua versi model dikembangkan, yaitu tanpa optimasi parameter dan dengan optimasi hyperparameter menggunakan RandomizedSearchCV. Model yang dioptimasi menunjukkan performa lebih baik, dengan kesalahan absolut rata-rata sebesar 0,7851 yard dan mampu menjelaskan 98,62% variabilitas data. Hasil penelitian menunjukkan bahwa model yang diusulkan dapat meningkatkan efisiensi manajemen stok bahan kain. Model ini telah diimplementasikan dalam aplikasi berbasis web menggunakan Flask dan MySQL untuk mendukung proses produksi secara lebih efektif.
Keywords
References
A. Pranata and M. Sihombing, “Analisis Peluang Usaha dalam Upaya Mempertahankan Keberlangsungan Usaha di Tengah Pandemi Covid-19,” J. Soc. Res., vol. 1, no. 7, pp. 773–784, 2022, doi: 10.55324/josr.v1i7.150.
R. Rohmanudin, “Analisis Kebutuhan Bahan Baku Konveksi Dalam Rangka Permintaan Dengan Menggunakan Metode Economic Order Quantity (Eoq) (Studi Kasus Di Ukm Suckseed Konveksi Tasikmalaya).,” J. Ind. Galuh, vol. 2, no. 2, pp. 80–87, 2020, doi: 10.25157/jig.v2i2.2970.
C. Atik, A. Kut, D. Birant, and S. Birol, “Prediction of Cloth Waste Using Machine Learning Methods in the Textile Industry,” in International Conference on Electrical and Electronics Engineering (ICEEE), 2022, pp. 165–169. doi: 10.1109/ICEEE55327.2022.9772517.
J. Prakash, V. Nashita, S. S. S, S. Shivathmika, K. Sivesh, and V. Ashwin, “Enhancing Clothing Size Prediction in E-Commerce: A Machine Learning Approach for Improved Customer Experience,” Int. Conf. Smart Syst. Electr. Electron. Commun. Comput. Eng., pp. 375–380, 2024, doi: 10.1109/icsseecc61126.2024.10649459.
A. Fahri and Y. Ramdhani, “Visualisasi Data dan Penerapan Machine Learning Menggunakan Decision Tree Untuk Keputusan Layanan Kesehatan COVID-19,” J. Tekno Kompak, vol. 17, no. 2, pp. 50–60, 2023, doi: 10.33365/jtk.v17i2.2438.
Z. Li, “Comparison of Decision Tree Regression with Linear Regression Based on Prediction of Apple Stock Price,” Adv. Econ. Manag. Polit. Sci., vol. 45, pp. 62–69, 2023, doi: 10.54254/2754-1169/45/20230259.
D. E. Waluyo, C. Paramita, H. W. Kinasih, D. Pergiwati, and F. A. Rafrastara, “Aplikasi Prediksi IHSG Berbasis Web Dengan Integrasi Multi-Algoritma,” J. Inform. J. Pengemb. IT, vol. 9, no. 2, pp. 121–129, 2024, doi: 10.30591/jpit.v9i2.6193.
M. Sivananda and D. G. K. Kumar, “Classification and Regression Based on Decision Tree Algorithm for Machine Learning,” Indian Sci. J. Res. Eng. Manag., vol. 08, no. 02, pp. 1–7, 2024, doi: 10.55041/ijsrem28533.
H. Zermane, H. MADJOUR, A. Ziar, and H. Zermane, “Forecasting material quantity using machine learning and times series techniques,” J. Electr. Eng., vol. 75, no. 3, pp. 237–248, 2024, doi: 10.2478/jee-2024-0029.
I. Azure, “Predictive modeling for industrial productivity: Evaluating linear regression and decision tree regressor approaches,” J. appliedmath, vol. 2, no. 4, pp. 1435–1446, 2024, doi: 10.59400/jam.v2i4.1435.
A. Thabibi and R. Supriyanto, “Perbandingan Model Multiple Linear Regression Dan Decision Tree Regression (Studi Kasus: Prediksi Harga Saham Telkom, Indosat, Dan Xl),” J. Ilm. Teknol. dan Rekayasa, vol. 28, no. 1, pp. 78–92, 2023, doi: 10.35760/tr.2023.v28i1.6081.
Dwita Elisa Sinaga, Agus Perdana Windarto, and Rizki Alfadillah Nasution, “Analisis Data Mining Algoritma Decision Tree Pada Prediksi Persediaan Obat (Studi Kasus : Apotek Franch Farma),” KLIK Kaji. Ilm. Inform. dan Komput., vol. 2, no. 4, pp. 123–131, 2022, doi: 10.30865/klik.v2i4.328.
H. Asyraf and M. E. Prasetya, “Implementasi Metode CRISP DM dan Algoritma Decision Tree Untuk Strategi Produksi Kerajinan Tangan pada UMKM A,” J. Media Inform. Budidarma, vol. 8, no. 1, pp. 94–105, 2024, doi: 10.30865/mib.v8i1.7050.
N. Alamsyah, B. Budiman, T. P. Yoga, and R. Y. R. Alamsyah, “Xgboost hyperparameter optimization using randomizedsearchcv for accurate forest fire drought condition prediction,” Pilar Nusa Mandiri J. Comput. Inf. Syst., vol. 20, pp. 103–110, 2024, doi: 10.33480/pilar.v20i2.5569.
I. Indriyanti, N. Ichsan, H. Fatah, T. Wahyuni, and E. Ermawati, “Implementasi Orange Data Mining Untuk Prediksi Harga Bitcoin,” J. Responsif Ris. Sains dan Inform., vol. 4, no. 2, pp. 118–125, 2022, doi: 10.51977/jti.v4i2.762.
N. Almajid, Y. R. Ginting, and A. I. Ramadhan, “Penerapan Decision Tree Regression dalam Memprediksi Harga Rumah di Provinsi Jawa Barat,” J. Ris. Inform. dan Teknol. Inf., vol. 1, no. 3, pp. 111–115, 2024, doi: 10.58776/jriti.v1i3.64.
N. E. Vijayan, “Building Scalable MLOps: Optimizing Machine Learning Deployment and Operations,” Indian Sci. J. Res. Eng. Manag., vol. 08, no. 10, pp. 1–9, 2024, doi: 10.55041/ijsrem37784.
How To Cite This :
Refbacks
- There are currently no refbacks.
