<![CDATA[Produksi ikan lele merupakan salah satu kegiatan budidaya yang memiliki nilai ekonomi dan memerlukan perencanaan hasil panen yang tepat. Pengelolaan data produksi yang masih dilakukan secara manual dapat menyulitkan proses memperkirakan hasil produksi secara akurat. Penelitian ini bertujuan membangun model prediksi hasil produksi ikan lele menggunakan algoritma Artificial Neural Network (ANN). Penelitian menggunakan pendekatan kuantitatif dengan metode Machine Learning. Dataset yang digunakan berjumlah 10.000 data, terdiri atas 8.000 data training dan 2.000 data testing. Variabel input yang digunakan meliputi jumlah bibit, berat awal, total pakan, suhu air, pH air, dan survival rate, sedangkan hasil produksi ikan lele digunakan sebagai variabel output. Tahapan penelitian meliputi pengumpulan data, data preparation, normalisasi, pembagian dataset, pemodelan ANN, dan evaluasi. Pemodelan dilakukan menggunakan perangkat lunak RapidMiner dengan arsitektur Multi-Layer Perceptron dan metode backpropagation. Hasil pengujian menghasilkan nilai Root Mean Squared Error (RMSE) sebesar 235,001. Hasil penelitian menunjukkan bahwa ANN mampu mempelajari hubungan antara variabel input dan hasil produksi ikan lele sehingga dapat digunakan sebagai pendekatan untuk membantu proses estimasi dan perencanaan produksi berbasis data. Catfish production is an important aquaculture activity with economic value and requires accurate production planning. Manual production data management can make it difficult to estimate production outcomes accurately. This study aims to develop a catfish production prediction model using an Artificial Neural Network (ANN) algorithm. This study employed a quantitative approach using Machine Learning. The dataset consisted of 10,000 records, including 8,000 training data and 2,000 testing data. The input variables included the number of seeds, initial weight, total feed, water temperature, water pH, and survival rate, while catfish production was used as the output variable. The research stages consisted of data collection, data preparation, normalization, dataset division, ANN modeling, and evaluation. The modeling process was performed using RapidMiner with a Multi-Layer Perceptron architecture and the backpropagation method. The evaluation resulted in a Root Mean Squared Error (RMSE) value of 235.001. The results indicate that ANN can learn the relationship between the input variables and catfish production and can therefore be used as an approach to support data-based production estimation and planning.]]>
