FP-Growth Implementation in Frequent Itemset Mining for Consumer Shopping Pattern Analysis Application

Tingkat persaingan dan kompleksitas permasalahan penjualan pada perusahaan retail, menuntut setiap perusahaan retail untuk mampu berkompetisi dengan perusahaan lain. Salah satu yang dapat dilakukan adalah melalui pengambilan keputusan terkait penjualan yang lebih tepat dan efektif. Besarnya data transaksinonal penjualan perusahaan retail dapat dilakukan ekstraksi informasi yang bermanfaat. Metode yang dapat digunakan untuk menggali informasi adalah melalui penerapan association rule mining. Association Rule Mining merupakan suatu metode data mining yang berfokus pada pola transaksi dengan cara mengekstraksi asosiasi atau hubungan suatu kejadian. Keranjang belanja yang terdapat pada perusahaan retail yang terkomputerisasi merupakan cara terbaik untuk memberikan dukungan rekomendasi keputusan secara ilmiah dengan cara menentukan hubungan antara barang yang dibeli secara bersamaan dalam setiap transaksi. Algoritma FP-growth digunakan untuk menentukan himpunan dataset yang paling sering muncul (frequent itemset) pada sekeompok data. Penelitian ini menghasilkan nilai minimum support 0,1% dan nilai minimum confidence 60% jumlah rule yang dihasilkan berjumlah 116457, nilai minimum confidence 70% jumlah rule yang dihasilkan berjumlah 84086, dan nilai minimum confidence 80% jumlah rule yang dihasilkan berjumlah 48623 dari data yang diolah sebanyak 22191. Hasil rule ini dapat digunakan untuk strategi pemasaran produk. Nilai minimum support 0,1% dimana semakin besar nilai minimum confidence maka menghasilkan rule yang semakin sedikit.

This study is motivated by the problem faced by Toko Polirindo, where sales transaction data are stored only as archives and have not been utilized for analytical purposes, resulting in unstable product availability, recurring stock shortages, and difficulties in predicting customer purchasing behavior; therefore, this research aims to identify patterns of item associations that frequently occur together by applying the Association Rule Mining method using the FP-Growth algorithm, which is recognized for its ability to extract frequent itemsets efficiently without the need to generate candidate combinations as in the Apriori algorithm. The dataset consists of sales transactions recorded from January to September 2025. It undergoes several stages, including preprocessing, binary transformation, and analysis using RapidMiner to generate frequent itemsets and association rules, evaluated using support, confidence, and lift metrics. The results reveal that item 3 consistently appears as the most dominant consequent across almost all generated rules, with confidence values ranging from 0.322 to 0.347, indicating that this item is most strongly associated with other items and frequently appears as a complementary product in customer transactions. These findings provide practical contributions by offering insights to optimize stock management, improve product placement, and develop promotional strategies based on actual purchasing patterns, while also demonstrating that the FP-Growth algorithm is an effective analytical tool to support data-driven decision-making aimed at enhancing operational efficiency and customer satisfaction in retail environments.

Background SIMRS is a communication information technology system that processes and integrates the entire flow of hospital service processes in forms of coordination network, reporting and administrative procedures to obtain precise and accurate information and is part of the Health Information System. The purpose of this study was to identify how to implement computer-based administrative information systems to improve service quality performance in hospitals. The method applied in this study was a literature study to examine journal articles regarding the Implementation of Computer-Based Administrative Information Systems to Improve Service Quality Performance in Hospitals, data collection used was secondary data. The results of 20 literature journal articles study showed that the implementation of SIMRS has not run efficiently or has problems. This is because the SIMRS implemented by the hospital was considered less attention by related parties and they have not properly prepared all related to SIMRS (i.e. many officers do not understand because there are no support, supervision and evaluation from the management and technology that has not been running maximally). Conclusion, based on the Literature Review on the Implementation of Computer-Based Administrative Information Systems to Improve Service Quality Performance in Hospitals were found there were obstacles in implementing computer-based information systems, including lack of personnel, less skilled, less disciplined and less responsible personnel, facilities and infrastructure constraints (less stable Wi-Fi network and crashed system) and obstacles from the management (no training and proper SOP). To deal with these problems, IT knowledge training to the employees, improving the system and applying proper SOP should be applied so that information systems can be implemented and used in order to help simplify the work and improve service quality in hospitals in the future.

The solution space of a frequent itemset generally presents exponential explosive growth because of the high-dimensional attributes of big data. However, the premise of the big data association rule analysis is to mine the frequent itemset in high-dimensional transaction sets. Traditional and classical algorithms such as the Apriori and FP-Growth algorithms, as well as their derivative algorithms, are unacceptable in practical big data analysis in an explosive solution space because of their huge consumption of storage space and running time. A multi-objective optimization algorithm was proposed to mine the frequent itemset of high-dimensional data. First, all frequent 2-itemsets were generated by scanning transaction sets based on which new items were added in as the objects of population evolution. Algorithms aim to search for the maximal frequent itemset to gather more non-void subsets because non-void subsets of frequent itemsets are all properties of frequent itemsets. During the operation of algorithms, lethal gene fragments in individuals were recorded and eliminated so that individuals may resurge. Finally, the set of the Pareto optimal solution of the frequent itemset was gained. All non-void subsets of these solutions were frequent itemsets, and all supersets are non-frequent itemsets. Finally, the practicability and validity of the proposed algorithm in big data were proven by experiments.

The Car Spare Part Shop is one of the Car Spare Parts Shops in Tangerang Regency. Based on interviews conducted with shop owners at the Car Spare Parts Store, it was stated that there was a decrease in sales income every month, so there was limited capital in purchasing car spare parts products which resulted in difficulties in choosing which car spare parts products to order. The purpose of this study is to create a system to process and utilize sales transaction data using the FP-Growth algorithm as well as up selling and cross selling methods which will later be used to sell car spare parts that are purchased simultaneously in a sales package determination system. The sales transaction data used is 6,674 transaction data for 1 year of operation of the Car Spare Part Shop (July 2021 - June 2022) with 30,956 records in Microsoft Excel format. The prototype system uses the Python framework flask and mysql database. Validation test results ensure that the software that has been made is in accordance with the expected functional requirements specifications. The results of the system quality test with ISO 9126 can be concluded in the criteria of Very Good with a value of 98.59%. With the results of the Functionality aspect of 99.25%, the results of the Reliability aspect of 98.13%, the results of the Usability aspect of 98.33% and the results of the Efficiency aspect of 98.66%. The results of system security testing with Acunetix and LOIC software have been carried out and the system is still stable and the system is declared safe when used.

Pharmacy sales transaction data contain valuable information on customer purchasing patterns; however, in practice, such data are often used merely as operational records, making relationships between purchased drugs difficult to identify. This study analyzes drug purchasing patterns using the Apriori and FP-Growth algorithms based on sales transaction data from Apotek Gadi Lamba Condet for the period January to June 2025. The transaction data were processed through data cleaning, drug name standardization, and transformation into transaction format, resulting in 7,038 transactions with 1,495 drug items. Association rule mining was performed using a minimum support of 0.01 and a minimum confidence of 0.17. The results show that the Apriori and FP-Growth algorithms generate ten identical association rules with the same support, confidence, and lift values, and all rules have lift values greater than one. Paracetamol 500 MG emerges as the most frequently involved drug in the association rules. These findings demonstrate that, for medium-scale pharmacy transaction datasets, Apriori and FP-Growth have equivalent capability in identifying drug purchasing patterns, with the primary difference lying in computational efficiency rather than the quality of the generated patterns.

Indonesia is an equatorial country that has abundant natural wealth from the seabed to the top of the mountains, the beauty of the country of Indonesia also lies in the mountains that it has in various provinces, for example in the province of West Nusa Tenggara known for its beautiful mountain, namely Rinjani. The increase in outdoor activities has attracted many people to open outdoor shops in the West Nusa Tenggara region. Sales transaction data in outdoor stores can be processed into information that can be profitable for the store itself. Using a market basket analysis method to see the association (rules) between a number of sales attributes. The purpose of this study is to determine the pattern of relationships in the transactions that occur. The data used is the transaction data of outdoor goods. The analysis used is the Association Rules with the Apriori algorithm and the frequent pattern growth (FP-growth) algorithm. The results of this study are formed 10 rules in the Apriori algorithm and 4 rules in the FP-Growth algorithm. The relationship pattern or association rule that is formed is in the item "if a consumer buys a portable stove, it is possible that portable gas will also be purchased" at the strength level of the rules with a minimum support of 0.296 and confidence 0.774 at Apriori and 0.296 and 0.750 at FP-Growth.

The transaction database contains a very large and irregular dataset that requires another mechanism to read it, even though there is a lot of new knowledge that can be revealed, including associations or relationships between goods or products that are often purchased by customers. The new finding of the relationship between these variables is usually called association rule mining. The algorithm that is developing and often used is frequent pattern-growth (FP-Growth). The problem of very many transaction databases also occurred in Mr. A. So, in this research, we will look for customer patterns using the FP-Growth algorithm. The algorithm aims to find the maximum frequent itemset. The frequent itemset will be generated into associative rules so that it becomes valuable new knowledge. This knowledge can be used as a reference and consideration in making decisions. The FP-Growth algorithm will be implemented using the rapidminer tools on the transaction data of Mr.A's goods sales. The pattern of rules that will be searched for is based on data on sales of goods transactions. The results of the study obtained six association rules with five conclusions being the gift category. So that the suggestion for decision making is to lay out items close to and around the gift category in order to improve marketing and service strategies in order to attract the attention and interest of pointers in making purchases of goods.

A cosmetic cheerful shop located in the Marelan area of Medan city is a shop that sells women's cosmetic equipment. The owner of a cheerful cosmetics shop is very disciplined in recording sales and purchases of goods. Every transaction is always recorded and stored in the Microsoft Excel application. Meanwhile, the Ceria Cosmetics store has been running since 2015 and has recorded lots of transactions, both sales and purchases. From 2015 until now the data has been increasing, and so far this data has only been a record and stored in a folder on the store's computer. From the piles of transaction data at the cheerful cosmetics store, the authors took the idea of research to utilize this pile of data. One of the applications of information technology that can be used to utilize the pile of data is the data mining technique. By using data mining, a pile of data from a cheerful cosmetic store can be used to find association patterns. And the application of data mining with association rules can use the FP-Growth algorithm. The FP-Growth algorithm can be used as an alternative to determine the most frequently occurring data set (frequent itemset) in a data set. Later, the combination patterns obtained in this study can be used to arrange the layout of goods (cosmetics) at the Ceria Cosmetics store in Medan Marelan.

Sales data stored in enterprise databases are usually stored as archives or documentation. In the case of retail companies, data mining science can be used to extract new information from sales database, ie consumer purchase pattern analysis. The algorithm that can be used to analyze consumer purchase pattern is FEM algorithm using combination of Frequent Pattern Growth (FP-Growth) and Eclat algorithm. The construction of FP-Tree tree structure is done by using FP-Growth algorithm, while the process of extraction of items purchased (frequent itemset) is done by using Eclat algorithm. The application designed can be used to analyze consumer purchase pattern by generating associative rules using FEM algorithm through the Analysis form and printing the consumer purchase pattern through the purchase pattern report.

The size of the agricultural sector in Indonesia provides opportunities for small businesses managed by local residents to provide various needs to support agricultural activities. The rise of agricultural shops has made business competition in the agricultural sector quite competitive. Therefore, a marketing strategy is needed that can increase the sales of various marketed agricultural products. The method applied in this research is Association Rule Mining using the FP-Growth algorithm. This method is applied to obtain association rules that are used as a reference in making recommendations for agricultural product packages at agricultural shops to increase sales. The system workflow starts from preprocessing data to form an itemset which is then processed using the FP-Growth algorithm. The next step is to determine the minimum value of support and minimum confidence as a limit in calculating the FP-Growth algorithm. The system will eliminate a number of itemsets that do not meet the specified threshold to produce frequent itemsets which are then mined into rules as a reference to form the most recommended package of agricultural products. From the research conducted it can be seen that there are 3 itemets that almost always appear and the most recommended agricultural product package is Prowl 250 ml (Herbicide) which is associated with Antracol 70wp 1 kg (fungicide) with a support value of 6.38% and a confidence value of 85, 71% and the lift ratio is 8.95.

In the era of digitalization, data utilization has emerged as a key to increasing company competitiveness in the current era of digital transformation, especially in the culinary industry. Recommendation systems are one way of analyzing data. Kedai Kopi Raja Palembang has so far only used transaction data as documentation without further analysis, making it difficult to determine sales products and customer purchasing patterns. This study aims to develop a menu package recommendation system using the Fp-Growth algorithm to analyze transaction data and provide more relevant recommendations. The development method used is the prototype method, with the provisions of the Knowledge Discovery in Database (KDD) stages which include data selection, preprocessing, transformation, application of the Fp-Growth algorithm, and evaluation using the Lift Ratio. The system was developed using Python and allows users to flexibly determine the minimum support and confidence values. The results of the study from the data used in the Raja Coffee Shop transaction history show that the system successfully identified 24 association rules from a minimum support of 1% and a Confidence of 70%. Then, an evaluation was carried out using the Lift Ratio which has a strong relationship between items and the 5 highest rules were taken from the Lift Ratio results for the recommendation menu. The implementation of the Fp-Growth algorithm in a transaction data-based recommendation system can enable business owners to make decisions by utilizing transaction data, to increase the efficiency of menu preparation, and become a model for other culinary businesses in optimizing marketing strategies.

Internet of Things (IoT) technology is developing rapidly and is widely applied to assist all human needs. Radio Frequency Identification (RFID) is a very popular IoT device. One application is to limit employee access in the office. In this study, RFID devices are used to limit room access rights, after the building user performs an RFID scan, the data will be stored in the database. The stored data is then used to find patterns of employee activity using the FP-Growth algorithm. The FP-Growth algorithm runs by tracing the tree from bottom to top and getting frequent itemsets obtained from the FP Tree based on the stored data. This study indicates that the time required for the RFID device to scan to determine whether the user has access or not is 2000ms. The hardware communication time with the information system using the API is 262ms then proceeding from the software to the database is 239ms. In the implementation of the FP-Growth algorithm, the time required for the FP-Growth algorithm to process 100 activity data divided into 10 days is 324 ms. From the 100 activity data, it can be concluded that if the employee enters the server room, server room, guest room, and guest room, the probability of the employee entering the multimedia room is 1 (100%). Furthermore, if the employee enters the multimedia room, multimedia room, server room, employee room, and the guest room then the probability of the employee entering the data room is 0.1 (10%).

Indonesian slang are commonly used in social media. Due to their unstructured syntax, it is difficult to extract their features based on Indonesian grammar for text mining. To do so, we propose Set of Frequent Word Item sets (SFWI) as text representation which is considered match for Indonesian slang. Besides, SFWI is able to keep the meaning of Indonesian slang with regard to the order of appearance sentence. We use FP-Growth algorithm with adding separation sentence function into the algorithm to extract the feature of SFWI. The experiments is done with text data from social media such as Facebook, Twitter, and personal website. The result of experiments shows that Indonesian slang were more correctly interpreted based on SFWI.

In recent years, the data mining technology has been developed rapidly. New efficient algorithms are emerging. Association data mining plays an important role in data mining, and the frequent item sets are the highest and the most costly. This paper is based on the association rules data mining technology. The advantages and disadvantages of Apriori algorithm and FP-growth algorithm are deeply analyzed in the association rules, and a new algorithm is proposed, finally, the performance of the algorithm is compared with the experimental results. It provides a reference for the extension and improvement of the algorithm of association rule mining.