MARIATI DURUBANUA, NPM 2209100075 (2026) PENERAPAN ALGORITMA DECISIONTREE UNTUK PREDIKSI VOLUME PRODUKSI TEMPE ASLI HB BERDASARKAN DATA PENJUALAN DAN BAHAN BAKU. Skripsi thesis, Universitas Labuhanbatu.
![[img]](http://repository.ulb.ac.id/style/images/fileicons/text.png) |
Text
COVER.pdf Download (754kB) |
|
Text
BAB I.pdf Download (68kB) |
|
Text
BAB II.pdf Download (307kB) |
|
Text
BAB III.pdf Restricted to Registered users only Download (601kB) |
|
Text
BAB IV.pdf Restricted to Registered users only Download (652kB) |
|
Text
BAB V.pdf Download (11kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (147kB) |
|
Text
LAMPIRAN.pdf Download (269kB) |
Abstract
Penentuan jumlah produksi yang tepat merupakan faktor penting dalam memenuhi permintaan pasar dan menjaga efisiensi produksi. Industri Tempe Asli HB masih melakukan penentuan jumlah produksi berdasarkan perkiraan, sehingga diperlukan metode prediksi berbasis data. Penelitian ini bertujuan untuk menerapkan algoritma Decision Tree Regression dalam memprediksi volume produksi tempe berdasarkan data penjualan dan bahan baku serta mengevaluasi tingkat akurasi model yang dihasilkan. Penelitian ini menggunakan 80 data historis produksi yang terdiri atas variabel Penjualan, Kedelai, Ragi, dan Produksi. Data dibagi menjadi 64 data latih dan 16 data uji menggunakan metode split validation dengan perbandingan 80:20. Proses pemodelan dilakukan menggunakan perangkat lunak RapidMiner Studio dengan algoritma Decision Tree Regression. Evaluasi model dilakukan menggunakan Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), dan koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa variabel Penjualan menjadi atribut yang paling dominan dalam pembentukan model prediksi. Model menghasilkan nilai MAE sebesar 144,196, MSE sebesar 40.576,722, RMSE sebesar 201,437, dan R² sebesar 0,670. Nilai tersebut menunjukkan bahwa model memiliki kemampuan yang cukup baik dalam memprediksi volume produksi tempe berdasarkan data historis yang tersedia. Kata Kunci: Decision Tree Regression, Prediksi, Produksi Tempe, Rapidminer, Machine Learning =========================================================================== Determining the appropriate production volume is a key factor in meeting market demand and maintaining production efficiency. The HB Authentic Tempe Industry still determines production volumes based on estimates, making a data-driven forecasting method necessary. This study aims to apply the Decision Tree Regression algorithm to predict tempe production volumes based on sales and raw material data, and to evaluate the accuracy of the resulting model. This study used 80 historical production data points consisting of the variables Sales, Soybeans, Yeast, and Production. The data were divided into 64 training data points and 16 test data points using the split validation method with an 80:20 ratio. The modeling process was performed using RapidMiner Studio software with the Decision Tree Regression algorithm. Model evaluation was performed using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²). The results of the study indicate that the Sales variable is the most dominant attribute in the development of the predictive model. The model produced an MAE of 144.196, an MSE of 40,576.722, an RMSE of 201.437, and an R² of 0.670. These values indicate that the model has a fairly good ability to predict tempeh production volume based on the available historical data. Keywords: Decision Tree RapidMiner, Machine learning
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | Decision Tree Regression, Prediksi, Produksi Tempe, Rapidminer, Machine Learning=============Decision Tree RapidMiner, Machine learning |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases |
| Divisions: | Fakultas Sains Dan Teknologi > Sistem Informasi |
| Depositing User: | Unnamed user with email repository@ulb.ac.id |
| Date Deposited: | 30 Jul 2026 08:30 |
| Last Modified: | 30 Jul 2026 08:30 |
| URI: | http://repository.ulb.ac.id/id/eprint/2615 |
Actions (login required)
 |
View Item |
