CD Skripsi

Prediksi Stok Gudang Dengan Machine Learning Menggunakan Metode Support Vector Regression Pada Pt Jamika Raya Pom

---

The effective management of warehouse inventory is essential to prevent potential losses for the company. Stock management faces challenges such as demand uncertainty, long procurement times, stock depletion, and delivery delays, requiring anticipation in purchasing to avoid stockouts and minimize overstock or understock situations. This research aims to predict warehouse inventory at PT Jamika Raya POM in the upcoming months. To handle manual warehouse inventory supervision and management, the Support Vector Regression (SVR) method is chosen. The research was conducted on 24 electrical warehouse items out of a total 3.171 warehouse inventory data points. Cross-validation and parameter tuning techniques are performed to create an optimal model. The accuracy of the model is evaluated using RMSE (Root Mean Squared Error) with an average of 22.68%. The best model is capable of predicting four-hole electrical outlets with an RMSE of 0,78%.

Keyword : Cross-Validation, Electrical, RMSE (Root Mean Squared Error), Warehouse Inventory, SVR (Support Vector Regression), Parameter Tuning

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

1903113643

Penerbit

Pekanbaru : Universitas Riau FMIPA Sistem Informasi., 2024

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

1903113643

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

SISTEM INFORMASI

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Mutia

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar