PERAMALAN PENJUALAN BERAS MENGGUNAKAN ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM SEBAGAI DASAR PENGAMBILAN KEPUTUSAN PERSEDIAAN

Dinda Almira, . (2025) PERAMALAN PENJUALAN BERAS MENGGUNAKAN ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM SEBAGAI DASAR PENGAMBILAN KEPUTUSAN PERSEDIAAN. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf

Download (198kB)
[img] Text
AWAL.pdf

Download (860kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only

Download (233kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only

Download (780kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only

Download (888kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only

Download (3MB)
[img] Text
BAB 5.pdf

Download (149kB)
[img] Text
DAFTAR PUSTAKA.pdf

Download (263kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only

Download (103kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only

Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only

Download (25MB)
[img] Text
ARTIKEL.pdf
Restricted to Repository staff only

Download (1MB)

Abstract

The retail sector serves as a critical pillar of Indonesia’s economy; however, inventory management remains a persistent challenge for many retail enterprises, including Toko XYZ. Toko XYZ is a cooperative engaged in both retail and wholesale, focusing on the sale of essential goods, with rice being the highest revenue-generating commodity. Despite this, the company frequently experiences stockouts, which introduce censorship bias in rice sales data due to unrecorded demand during stockout periods. This distortion results in inaccurate and intuition-driven replenishment decisions. In addressing this issue, this research employs the Adaptive Neuro-Fuzzy Inference System (ANFIS), a hybrid machine learning model that integrates artificial neural networks and fuzzy logic, and is capable of managing non-linear patterns and small-sized datasets. The model is utilized to forecast rice demand over a one-year horizon, determine optimal safety stock and reorder point levels, and simulate lost sales using a counterfactual scenario framework. The forecasting results demonstrate that the ANFIS model yields consistently high predictive accuracy across all product types, exceeding 80%, with peak performance reaching 96.93%. The derived safety stock and reorder point thresholds vary by product, reflecting unique demand behaviors characteristics. Simulation outcomes reveal that unmitigated stockouts could lead to potential losses of 668 BALL, equivalent to approximately Rp119,334,000. These findings underscore the efficacy of ANFIS as a data-driven decision-support tool for inventory optimization, enabling more proactive and precise stock planning in retail operations.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110312008] [Pembimbing: Donny Montreano] [Penguji 1: Yulizar Widiatama] [Penguji 2: Santika Sari]
Uncontrolled Keywords: ANFIS, Forecasting, Inventory
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management
Q Science > QA Mathematics
T Technology > T Technology (General)
Divisions: Fakultas Teknik > Program Studi Teknik Industri (S1)
Depositing User: DINDA ALMIRA
Date Deposited: 01 Aug 2025 07:54
Last Modified: 01 Aug 2025 07:54
URI: http://repository.upnvj.ac.id/id/eprint/38855

Actions (login required)

View Item View Item