Pengembangan Lifespan-Aware Association Rule Mining dengan Validasi Lintas Algoritma Apriori dan FP-Growth untuk Sistem Rekomendasi Menu Kantin

Navsih, Muhammad Ghinan (2026) Pengembangan Lifespan-Aware Association Rule Mining dengan Validasi Lintas Algoritma Apriori dan FP-Growth untuk Sistem Rekomendasi Menu Kantin. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) Cover Thesis Fix (1)_removed.pdf Download (884kB)
	Text (Bab 1) 22083010057.-bab1.pdf Download (117kB)
	Text (Bab 2) 22083010057.-bab2.pdf Restricted to Repository staff only until 22 January 2029. Download (501kB)
	Text (Bab 3) 22083010057.-bab3.pdf Restricted to Repository staff only until 22 January 2029. Download (2MB)
	Text (Bab 4) 22083010057.-bab4.pdf Restricted to Repository staff only until 22 January 2029. Download (251kB)
	Text (Bab 5) 22083010057.-bab5.pdf Download (117kB)
	Text (Daftar Pustaka) 22083010057.-daftarpustaka.pdf Download (118kB)
	Text (Lampiran) Just Lampiran (1).pdf Restricted to Repository staff only Download (777kB)

Abstract

In managing small-scale canteens such as boarding school canteens, cashiers generally do not have a systematic reference for recommending additional menu items to customers, so the potential for increased sales is often not optimally utilized. This problem becomes even more complex given the dynamic nature of the menu offered, where a number of items can be introduced or discontinued at any given time. To address this challenge, this study developed a Lifespan-Aware Association Rule Mining-based menu recommendation system using a hybrid approach between the Apriori and FP-Growth algorithms. The data used came from a real point-of-sale (POS) application connected to Firebase Firestore, covering more than 14736 historical transactions. The methodological process consists of five main stages: data preprocessing, association rule extraction from two algorithms, selection of relevant metrics, rule ensembling, and metric adjustment based on the active lifespan period of the product. The experimental results show that Apriori and FP-Growth produce a consistent rule set, supporting cross-algorithm validation, while the lifespan-aware approach improves recommendation relevance by reducing bias caused by differences in product active periods. The final system is capable of providing real-time menu suggestions to cashiers based on customer order lists, supporting smarter decision-making and potentially increasing canteen revenue.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Muhaimin, Amri	NIDN0023079502	amri.muhaimin.stat@upnjatim.ac.id
Thesis advisor	Wara, Shindi Shella May	NUPTK1850774675230252	shindi.shella.fasilkom@upnjatim.ac.id
Thesis advisor	Idhom, Mohammad	NIP198303102021211006	idhom@upnjatim.ac.id
Thesis advisor	Adziima, Andri Fauzan	NIP199505122024061001	andri.fauzan.fasilkom@upnjatim.ac.id