Analisis Faktor Keberhasilan Penjualan Kerajinan Tangan menggunakan Decision Tree dengan Optimasi Grid Search
DOI:
https://doi.org/10.30865/jurikom.v13i2.9534Keywords:
Decision Tree, Grid Search Cross-validation, E-commerce Sales Prediction, Handicraft MSMEs, Feature ImportanceAbstract
This study is motivated by the limited ability of handicraft Micro, Small, and Medium Enterprises (MSMEs) to analyze the key factors influencing sales success on e-commerce platforms, despite the availability of historical transaction data. Previous studies generally applied classification algorithms without systematic hyperparameter optimization, potentially leading to suboptimal models and overfitting issues. To address this gap, this research proposes the implementation of a Decision Tree algorithm optimized using Grid search Cross-validation. The dataset was obtained from the Brazilian e-commerce platform (Olist Dataset), specifically the ‘artes’ category as a proxy for handicraft products, with an 80:20 split for training and testing data. The optimization process explored 576 parameter combinations to determine the best configuration. The optimized model achieved an accuracy of 97.61% with a simplified tree structure (max_depth=None), enhancing interpretability. Feature importance analysis product_height_cm as the most dominant factor (64.23%), followed by product_height_cm, product_width_cm, Freight_value, product_weight_g, and price. These findings demonstrate that the combination of Decision Tree and Grid search effectively produces an accurate and interpretable predictive model, providing strategic decision-making support for handicraft MSMEs in digital marketplaces.
References
[1] N. L. W. S. Telagawathi, N. M. Suci, and K. K. Heryanda, “Strategi Transformasi Digital Umkm Kerajinan Tangan Pada Masa Pandemi Covid-19 Di Kabupaten Gianyar, Bali,” J. Ilmu Sos. dan Hum., vol. 11, no. 2, pp. 204–212, 2022, doi: 10.23887/jish.v11i2.39734.
[2] M. G. F. Christine, M. Dachyar, and R. Nurcahyo, “Product Segmentation of Wooden Handicraft Micro , Small and Medium Enterprises ( MSMEs ) in Indonesia,” IOP Conf. Ser. Mater. Sci. Eng., vol. 598, pp. 1–8, 2019, doi: 10.1088/1757-899X/598/1/012063.
[3] F. I. Sanjaya and A. D. Kalifa, “Precision Marketing Model using Decision Tree on SME e-commerce Case Study Orebae.com,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 5, pp. 1033–1039, 2023.
[4] R. S. T. Rahmayani and F. Budiman, “Analisa Optimasi Grid Search pada Algoritma Random Forest dan Decision Tree untuk Klasifikasi Stunting,” Build. Informatics, Technol. Sci., vol. 6, no. 3, pp. 1537–1546, 2024, doi: 10.47065/bits.v6i3.6128.
[5] A. Basir and F. A. Tyas, “Akuisisi Pengetahuan untuk Sistem Pakar Pencegahan Stunting (SIPENTING) Menggunakan Decision Tree dan Grid Search,” Sist. Sist. Inf., vol. 14, no. 3, pp. 1165–1175, 2025.
[6] D. I. Suranda and A. Nugroho, “KLASIFIKASI DATA PENJUALAN UNTUK MEMPREDIKSI TINGKAT PENJUALAN PRODUK MENGGUNAKAN METODE DECISION TREE,” J. TEKINKOM, vol. 7, no. 1, pp. 370–376, 2024, doi: 10.37600/tekinkom.v7i1.1269.
[7] S. O. Usnaat, Y. P. K. Kelen, and K. J. T. Seran, “IMPLEMENTASI METODE DECISION TREE DALAM MEMPREDIKSI PENJUALAN PRODUK TERLARIS (STUDI KASUS : KREATIF MART ATAMBUA),” Zo. J. Sist. Inf., vol. 7, no. 1, pp. 317–330, 2025.
[8] F. U. Aulya and Kusnawi, “Evaluating Classification Models for Predicting Product Success in Indonesian E-Commerce,” J. Tek. Inform., vol. 6, no. 4, pp. 2723–2739, 2025, doi: https://doi.org/10.52436/1.jutif.2025.6.4.5071.
[9] A. D. Prastika and Y. S. Nugroho, “Klasifikasi Efektivitas Iklan di E-Commerce dan Media Sosial terhadap Minat Beli Mahasiswa UMS dengan Decision Tree,” J. Pendidik. dan Teknol. Indones., vol. 5, no. 4, pp. 919–933, 2025, doi: https://doi.org/10.52436/1.jpti.727.
[10] D. Anggreani, Hamdani, Nurmisda, and Lukman, “Grid Search Hyperparameter Analysis in Optimizing The Decision Tree Method for Diabetes Prediction,” Indones. J. Data Sci., vol. 5, no. 3, pp. 190–197, 2024, doi: https://doi.org/10.56705/ijodas.v5i3.190 Research.
[11] T. Suprapti, B. Nurhakim, B. W. A. Hermina, and V. A. Syahputra, “A Decision Tree Model with Grid Search Optimization for Scholarship Recipient Classification,” J. Tek. Inform., vol. 6, no. 5, pp. 3800–3813, 2025, doi: https://doi.org/10.52436/1.jutif.2025.6.5.5235.
[12] A. Arista, “Comparison Decision Tree and Logistic Regression Machine Learning Classification Algorithms to determine Covid-19,” Sink. J. dan Penelit. Tek. Inform., vol. 6, no. 1, pp. 56–62, 2022, doi: https://doi.org/10.33395/sinkron.v7i1.11243.
[13] M. J. Vikri, I. W. Prastya, Dwi, U. P. Sanjaya, and M. A. Barata, “RICE QUALITY IDENTIFICATION FOR INDONESIAN FOOD STANDARDS BASED ON ELECTRONIC NOSE,” J. INOVTEK POLBENG - SERI Inform., vol. 10, no. 1, pp. 49–60, 2025, doi: https://doi.org/10.35314/0y0xct32.
[14] M. J. Vikri and R. Rohmah, “Penerapan Fungsi Exponential Pada Pembobotan Fungsi Jarak Euclidean Algoritma K-Nearest Neighbor,” Gener. J., vol. 6, no. 2, pp. 98–105, 2022, doi: https://doi.org/10.29407/gj.v6i2.18070.
[15] W. A. Medyanti, M. Faisal, and H. Nurhayati, “Optimasi Metode Single Exponential Smoothing Dengan Grid Search Pada Prediksi Nilai Ekspor Migas,” SINTECH J., vol. 7, no. 1, pp. 59–69, 2024, doi: https://doi.org/10.31598.
[16] Y. Aprillia, Z. Alawi, I. T. A. Aristia, and S. A. Ida, “Implementasi Algoritma Naive Bayes Dengan Feature Selection Backward Elimination Dalam Pengklasifikasian Status Penderita Stunting Pada Balita,” J. Multidiscip. Appl. Quantum Inf. Sci., vol. 4, no. 02, pp. 1–6, 2024.
[17] A. H. Anshor and A. T. Zy, “Implementasi Metode Decision Tree pada Sistem Prediksi Status Kualitas Produk Minuman A,” J. Ilm. Inform. Glob., vol. 15, no. 1, pp. 17–22, 2024.
[18] S. Ramadhan, Z. Alamin, M. Jannah, M. Akbar, and R. Fikriyansah, “Data-driven MSME Success Prediction Using Decision Tree-Based Machine Learning Techniques,” Journix J. Informatics Comput., vol. 1, no. 1, pp. 1–9, 2025, doi: 10.63866/journix.v1i1.3.
[19] W. Nugraha and A. Sasongko, “Hyperparameter Tuning pada Algoritma Klasifikasi dengan Grid Search,” Sist. Sist. Inf., vol. 11, no. 2, pp. 391–401, 2022.
[20] T. Sugihartono, Marini, K. Irfan, and H. A. Pradana, “Optimalisasi Kinerja Extreme Gradient Boosting melalui Grid Search untuk Prediksi Risiko Penyakit Jantung,” J. Pendidik. dan Teknol. Indones., vol. 5, no. 10, pp. 3074–3084, 2025, doi: https://doi.org/10.52436/1.jpti.1346.
[21] M. Arifin and S. Adiyono, “Hyperparameter Tuning in Machine Learning to Predicting Student Academic Achievement,” Int. J. Artif. Intelegence Res., vol. 8, no. 1.1, pp. 1–8, 2024, [Online]. Available: http://ijair.id
[22] Mukhlisin and H. W. Nugroho, “Customer Loyalty Classification Using KNN and Decision Tree for Sales Strategy Development,” Sink. J. dan Penelit. Tek. Inform., vol. 9, no. 3, pp. 1159–1166, 2025, doi: https://doi.org/10.33395/sinkron.v9i3.15110 e-ISSN.
[23] H. S. Putra, H. Okyprana, and R. K. Sormin, “IMPLEMENTASI ALGORITMA DECISION TREE DALAM MENENTUKAN LOKASI PENJUALAN DAGANGAN PADA DINAS PASAR SERBELAWAN SIMALUNGUN,” SmartEDU J., vol. 1, no. 2, pp. 61–69, 2022.
