Peramalan penjualan berbasis machine learning di han cover dashboard dengan algoritma LSTM (long short-term memory)

Soegondo, Muhammad Ilya Asha (2022) Peramalan penjualan berbasis machine learning di han cover dashboard dengan algoritma LSTM (long short-term memory). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05311840000010-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Han Cover Dashboard adalah produsen aksesoris interior mobil berbasis di Indonesia yang berfokus pada cover dashboard sejak 2016. Karena penjualan melalui e-commerce meningkat pesat, proyeksi penjualan yang konsisten dapat memungkinkan perusahaan untuk secara efisien mempersiapkan situasi yang tidak terduga seperti lonjakan permintaan atau gangguan mendadak pada rantai pasokan. Oleh karena itu diusulkan penerapan peramalan penjualan berdasarkan data penjualan Han Cover Dashboard. Metode peramalan yang akan dipergunakan adalah metode Machine Learning yaitu Long Short-Term Memory (LSTM). Long Short-Term Memory (LSTM) adalah sebuah arsitektur artificial Recurrent Neural Network (RNN). Perhitungan tingkat kesalahan yang digunakan pada studi ini adalah Root Mean Square Error (RMSE) dan Mean Absolute Percent Error (MAPE). Hasil penelitian ini menunjukkan bahwa LSTM dapat diterapkan untuk peramalan penjualan pada Han Cover Dashboard dan dari hasil peramalan penjualan pada Han Cover Dashboard didapatkan model terbaik dengan rata-rata error hasil ramalan memiliki RMSE senilai 146,651 dan MAPE senilai 8,849%.
====================================================================================================================================
Han Cover Dashboard is an Indonesia-based car interior accessories manufacturer that has focused on cover dashboards since 2016. As sales through e-commerce are increasing rapidly, consistent sales projections can enable the company to efficiently prepare for unexpected situations such as spikes in demand or sudden disruptions to sales. supply chain. Therefore, it is proposed to apply sales forecasting based on sales data from Han Cover Dashboard. The forecasting method that will be used is the Machine Learning method, namely Long Short-Term Memory (LSTM). Long Short-Term Memory (LSTM) is an artificial Recurrent Neural Network (RNN). The calculation of the error rate used in this study is the Root Mean Square Error (RMSE) and Mean Absolute Percent Error (MAPE). The results of this study indicate that LSTM can be applied to sales forecasting at Han Cover Dashboard and from the results of sales forecasting at Han Cover Dashboard, the best model best model is obtained with an average forecast error has an RMSE of 146.651 and a MAPE of 8.849%.

Item Type:	Thesis (Other)
Additional Information:	RSIf 006.31 Soe p-1 2022
Uncontrolled Keywords:	Peramalan, Peramalan Penjualan, Machine Learning, RNN, LSTM., Forecast, Sales Forecast, Machine Learning, RNN, LSTM.
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis
Depositing User:	Mr. Marsudiyana -
Date Deposited:	22 Apr 2026 05:53
Last Modified:	22 Apr 2026 05:53
URI:	http://repository.its.ac.id/id/eprint/132860

Actions (login required)

View Item