Search

Pharmacies are shops that sell and mix medicines based on doctors’ prescriptions and trade medical goods. Apart from being a business actor, the pharmacy also plays a role in providing health services that are easily accessible to the public. The problem that often occurs in pharmacies selling drugs is that they are less than optimal in service to consumers. The habit of consumers buying more than one type of drug makes pharmacy staff slow in providing the drug due to the inaccurate layout of the drug. The FP-Growth method in Data Mining is a method that can provide a solution in determining drug sales patterns at pharmacies. The FP-Growth method is a method used in determining the data set that occurs most frequently together (Frequent Itemset). The research objective was to determine drug sales patterns based on drug sales transaction data so that drug layouts could be determined. This research was conducted at the Pharmacy at the Pratama Sehati Husada Clinic in Medan with drug sales transaction data from November 2021 to December 2021. The results of applying the FP-Growth method with a value of ≥ 15% as a minimum support and a value of ≥ 15% as a minimum confidence, a pattern of drug sales in pairs. The application of Data Mining with the FP-Growth method has been implemented at the Pharmacy at the Pratama Sehati Husada Clinic with the desired goals with the final result in the form of a report on the results of determining drug sales patterns.

Beauty care and the need for cosmetics have become the lifestyle of modern women, especially in big cities. Public awareness to look beautiful makes modern women competing to take care of themselves to be more beautiful. The body care industry in Indonesia continues to grow. The growth has reached 6% and is predicted to continue to grow along with the high concern of Indonesian women in caring for their skin. To win the competition, companies need to know the market and consumer situation. One strategy that can be applied by the company is to use a promotional or advertising strategy. This research was conducted at the Ariana Audy beauty clinic in 2022 with the aim of identifying customer buying patterns which will then be used as reference material in the development of promotional menus for products and services offered by the beauty clinic. The approach used to design components on the promotional menu is Market Basket Analysis by applying the fp-growth algorithm using rapid miner software. Market basket analysis is focused on finding relationships between products based on customer purchases. The market basket analysis conducted resulted in 5 association rules that define consumer purchasing patterns for products and services provided by the Ariana Audy clinic. Through the 5 association rules formed, 3 promotional menus were produced, namely menu 1 consisting of baby skin crystal and oxy blue cream, menu 2 consisting of brightening cream products and sunscreen brightening, and menu 3 consisting of oxy jet peel and photodynamic therapy.

Predicting transportation mode choice is a classic challenge of travel behavior research. Over the years, different theoretical concepts and modeling approaches have been applied. This paper elaborates the application of class association rules (CARs) and examines their predictive performance using data extracted from the 2015 National Dutch Travel Survey. To solve the problem how to activate rules that have high confidence but low support, the information gain (IG) concept is introduced in the model building process. The modeling process in this study first involves extracting frequent items from the data using the FP-Growth algorithm and deriving CARs from these frequent items. Next, the IG statistic is used to construct a novel model (named CARIG), which consists of a set of decision rules that formally represent behavioral scripts, for predicting individuals’ transportation mode choice. The performance of CARIG is compared with the performance of conventional class-based association rules (CBA), decision trees (DT), a convolutional neural network (CNN) and a logistic regression (LR) model. In addition, a 10-fold cross validation test using a grid search parameter optimization method is conducted to validate the proposed approach. The results show that the proposed method is promising in predicting transportation mode choices observed in the national travel survey data.

Kemajuan terbaru dalam teknologi analitik data telah membuka banyak peluang bagi pelaku usaha ritel untuk meningkatkan efisiensi operasional. Kombinasi POS (Point Of Sale) dan data pelanggan dapat menjadi cara yang baik untuk membantu pelaku usaha memahami afinitas produk. Penelitian ini mengambil sebuah kasus pada Toko Mitra Swalayan Salatiga. Data diambil selama bulan Juni 2022, dengan menganalisis perilaku konsumen menggunakan metode Market Basket Analysis. Market Basket Analysis adalah metode yang digunakan untuk memahami pola pembelian pelanggan guna meningkatkan penjualan. Analisis ini melibatkan data riwayat dan perilaku pelanggan untuk mengungkap wawasan berharga seperti pengelompokan produk untuk mengoptimalkan penjualan. Berdasarkan hasil penelitian didapatkan 21 aturan asosiasi terbaik dengan cara mengklasifikasikan minimum nilai support sebesar 0,000471 dan minimum confidence sebesar 40%. Recent advancements in data analytics technology have opened up many opportunities for retailers to improve their operational efficiency. The combination of Point of Sale (POS) and customer data can be a great way to help retailers understand product affinity. This research was conducted at Mitra Swalayan Salatiga in June 2022, analyzing consumer behavior using the Market Basket Analysis method. Market Basket Analysis is a technique used to understand customer buying patterns to increase sales. This analysis leverages customer history and behavior data to uncover valuable insights such as product grouping to optimize sales for retailers. Based on the study's results, 21 of the best association rules were obtained by classifying the minimum support value of 0,000471 and a minimum confidence of 40%.

Along with the rapid development of the culinary industry, business competition is also getting tougher. Warung Oemah Tani serves a variety of menus and drinks, but to provide satisfying service to customers, business people must try to develop new products. Under these circumstances, the menu recommendations for Warung Oemah Tani need to be analyzed so that the recommendations made are right on target. This study aims to analyze the sales of Warung Oemah Tani using the FP Growth algorithm. This algorithm identifies the data set with the highest frequency of concurrent sales (frequent itemset). The results of the association rules show that the highest support value is 0.520 and the highest confidence value is 0.929, with a minimum support of 30% and a minimum confidence of 80%. Obtained 14 rule associations that meet the minimum support and minimum confidence.

Determination of sales patterns is very important in marketing. Sales pattern serves to conduct an effective analysis in improving marketing. Sales analysis aims to explore new knowledge that can help design effective strategies by utilizing sales transaction data. This study processes sales data for 12 transaction days containing 47 items using the Fp-Growth algorithm. The results of this study are items with a minimum value of support > 0.10 and confidence 0.60 and will be compared with testing data using RapidMiner to test whether the results are valid so that the test results can help in designing sales strategies., Penentuan pola penjualan sangat penting dalam pemasaran. Pola penjualan berfungsi untuk melakukan analisis yang efektif dalam meningkatkan pemasaran. Analisis penjualan bertujuan untuk menggali pengetahuan baru yang dapat membantu merancang strategi yang efektif dengan memanfaatkan data transaksi penjualan. Penelitian ini mengolah data penjualan selama 12 hari transaksi yang berisi 47 item dengan menggunakan algoritma Fp-Growth. Hasil dari penelitian ini adalah item dengan nilai minimal support > 0.10 dan confidence 0.60 dan akan dibandingkan dengan data pengujian menggunakan RapidMiner untuk menguji apakah hasil tersebut valid sehingga hasil pengujian tersebut dapat membantu dalam merancang strategi penjualan.

The automated fault detection and diagnostics (AFDD) of heating, ventilation, and air conditioning (HVAC) using data mining and machine learning models have recently received substantial attention from researchers and practitioners. Various models have been developed over the years for AFDD of complete HVAC or its sub-systems. However, HVAC complexities, which partly have roots in its close coupling nature and interrelated dependencies, mean that understanding the relationship between faults and the suitability of the techniques remains an unanswered question. The literature analysis and interactive visualization of the data collected from the past implementation of AFDD models can provide useful insight to further explore this question by applying artificial intelligence (AI). Association rule mining (ARM) is deployed by this paper, using the frequent pattern (FP) growth algorithm to generate frequent fault sets for most common HVAC faults from the body of AFDD models developed in the literature to represent the status quo. A new model is developed for common HVAC faults and the techniques most frequently used to detect and diagnose them. A recommender system is developed using the ARM model to extract knowledge from the body of knowledge of HVAC data-driven AFDD in the form of rule-sets that reflect the associations. Findings of this review paper can significantly help civil and building engineers, as well as facility managers, in better management of building HVAC systems.

In the era of covid-19, the response in controlling covid-19 requires an adequate supply of medicines in hospitals and pharmacies. The supply of these drugs is felt to be very important because seeing the impact of the covid-19 virus is very dangerous for human health. Therefore, the existence of the supply of medicines in pharmacies during this Covid era really needs to be considered. Every transaction of the sale of the drug in pharmacies is always recorded. This sales transaction data can be processed to find certain patterns in selling drugs in a certain period of having so many drug sales transaction activities. If the sales transaction data is analyzed, a pattern can be found out that is very helpful in estimating drug stocks from the drug sales data. To be able to estimate drugs, the right method is needed in order to get accurate results. One of them is the Fp-Growth method. With Fp-Growth, data is entered for calculations based on drug sales data so as to produce conclusions of minimum support and minimum confidence values. Based on this study, 35 data on drug sales transactions were taken. The test results of this study obtained calculation results from simultaneous drug sales data that are often purchased by consumers with the highest accuracy are 17.14% and 50%, namely Paracetamol and CTM.

One of the most challenging tasks in association rule mining is that when a new incremental database is added to an original database, some existing frequent itemsets may become infrequent itemsets and vice versa. As a result, some previous association rules may become invalid and some new association rules may emerge. We designed a new, more efficient approach for incremental association rule mining using a Fast Incremental Updating Frequent Pattern growth algorithm (FIUFP-Growth), a new Incremental Conditional Pattern tree (ICP-tree), and a compact sub-tree suitable for incremental mining of frequent itemsets. This algorithm retrieves previous frequent itemsets that have already been mined from the original database and their support counts then use them to efficiently mine frequent itemsets from the updated database and ICP-tree, reducing the number of rescans of the original database. Our algorithm reduced usages of resource and time for unnecessary sub-tree construction compared to individual FP- Growth, FUFP-tree maintenance, Pre-FUFP, and FCFPIM algorithms. From the results, at 3% minimum support threshold, the average execution time for pattern growth mining of our algorithm performs 46% faster than FP- Growth, FUFP-tree, Pre-FUFP, and FCFPIM. This approach to incremental association rule mining and our experimental findings may directly benefit designers and developers of computer business intelligence methods.

Current days an enormous amount of data is put away and recovered from the cloud because of its benefits like stowage size, assets pooling, and multi-occupancy. Because every administration is accessible through cyberspace, there is a lot of ambiguity about security and protection at various levels. This work proposed a privacy-preserving technique by applying Deoxyribonucleic Acid (DNA) coding-based novel Bit Incorporated Codon Positional Encoder (BICPE) algorithm for vertically divided cloud information. The transactional items are scrambled with a replacement of the DNA codon. Fictitious exchanges are appended unilaterally into the private database before encryption by the data owner to alleviate frequency analysis attacks of the items. The proposed BICPE algorithm encrypts the transactional data into A, C, G, T codons to upgrade the safety of the transactional items by replacement, operation, and intricacy. The concepts of binary coding and random values are utilized in DNA sequencing to encode the data. In this method, both the sender and the receiver will share a common DNA sequence for encryption and decryption process. The performance of the proposed technique is compared with the traditional Homomorphic Encryption (HE) in terms of support threshold values (Ts) for different items in a transaction. The exploratory outcomes demonstrate that the BICPE algorithm outperforms HE as far as ciphertext size, execution time, and privacy. Hence, the newly proposed technique is more efficient and offers better performance in terms of privacy.

The SPADE (spatio-temporal Spike PAttern Detection and Evaluation) method was developed to find reoccurring spatio-temporal patterns in neuronal spike activity (parallel spike trains). However, depending on the number of spike trains and the length of recording, this method can exhibit long runtimes. Based on a realistic benchmark data set, we identified that the combination of pattern mining (using the FP-Growth algorithm) and the result filtering account for 85–90% of the method's total runtime. Therefore, in this paper, we propose a customized FP-Growth implementation tailored to the requirements of SPADE, which significantly accelerates pattern mining and result filtering. Our version allows for parallel and distributed execution, and due to the improvements made, an execution on heterogeneous and low-power embedded devices is now also possible. The implementation has been evaluated using a traditional workstation based on an Intel Broadwell Xeon E5-1650 v4 as a baseline. Furthermore, the heterogeneous microserver platform RECS|Box has been used for evaluating the implementation on two HiSilicon Hi1616 (Kunpeng 916), an Intel Coffee Lake-ER Xeon E-2276ME, an Intel Broadwell Xeon D-D1577, and three NVIDIA Tegra devices (Jetson AGX Xavier, Jetson Xavier NX, and Jetson TX2). Depending on the platform, our implementation is between 27 and 200 times faster than the original implementation. At the same time, the energy consumption was reduced by up to two orders of magnitude.

The extracting association rules of inter-user-product relations used by companies in decision-making processes have been popular for some time, especially for market basket analysis. In this study it is aimed to discover association rules from original online store transaction of a Turkish retail company, in order to help administrator and decision maker also Customer Relationship Management department to initiate campaigns. The main objective is to find out which product item sets are bought together. In order to better compare the results the data are analyzed with and without clustering according to range of ages and gender. Data mining Association analysis methods such as Apriori Algorithm, FP-Growth (Frequent Pattern) then applied which are used to extract association rules. Moreover some of the collaborative filtering metrics namely Jaccard, Pearson, and Cosine function are used to understand the association between products to obtain a recommendation system. The proposed recommendation methods successfully recommended the associated product for the obtained original dataset as high as %65 accuracy. Obtained association rules are shared with the marketing department to initiate and direct forthcoming marketing campaigns.

The use of gas in Indonesia is a more profitable alternative, one of which is the oil conversion program, LPG (liquefied petroleum gas). UD.Maju Bersama, which is a distribution agent for 3 Kg LPG gas for household needs, so far because of the many requests, of course LPG agents like this need to forecast the frequency of purchases to find out if the sales have been sold as optimally as possible and stocks can be provided well and supplies adequate for consumer demand. this problem can be solved by applying one of the Datamining techniques which is using the FP-Growth Algorithm method to find out the Frequency of Purchase of 3 Kg LPG Gas. Frequent Pattern Growth (FP-Growth) can be used to determine the set of data that most often appears (frequent itemset) in a data set. The results of data processing purchases at the Elpiji UD base. Forward Together the most sold or purchased values ​​at week 1 and 2 on each month with the highest value support 66.67% confidence 100.00%. the results can help base owners to make decisions on gas supply so that they can be used to increase the amount of supply from distributors to agents and increase profits with support and confidence.

Most retail companies have implemented computer-based information systems for recording sales transaction data. In the implementation of information systems, the data collected in the database is processed limited to making reports such as sales reports and inventory reports. Database generated from computer-based information systems can be further processed to obtain more valuable information. One strategy for using sales transaction data is to analyze consumer spending patterns. Consumer spending patterns can be in the form of associations of items that are often purchased simultaneously. The association between goods can be determined using the frequent itemset search technique. The Fp-growth algorithm is an algorithm that can be used to determine frequent itemsets in a data set. This article describes the results of implementing the FP-Growth algorithm in the consumer shopping pattern analysis application. The resulting shopping pattern is in the form of goods that are often purchased simultaneously by consumers. From the results of the application of the fp-growth algorithm, it was found that the minimum value of support had an effect, namely the smaller the input value of support, the more pairs of items were obtained. The application of the FP-Growth algorithm in determining frequent itemsets in association data mining can find customer spending habits in buying goods simultaneously.

Nowadays the competition between companies is increasing. Companies need to predict their customers to find out the level of customer loyalty. One way is to analyze customer data by doing Customer Churn Prediction. In this study the method used is the FP-Growth Algorithm. The FP-Growth algorithm is an algorithm that uses the association rules technique to determine the data that appears most frequently. The data used in this study are secondary data and have 7,403 data from customers. The data has 21 variables. By using a minimum support of 1.2% and confidence at 80%, the associative rules generated are 60. The variable of the type of internet the customer has is strong enough to predict churn. It can be seen that of the 60 associative rules, there are 36 associative rules that have this variable. Testing associative rules on test data yields an accuracy of 71%.

Bakery shop is a shop that sells variants menu like bread, cakes, and drinks. The main problem with this store's sales is still not knowing which product items are best sellers and the shop still markets a lot of non-selling menus, causing the shop to lose money. So it takes the right strategy to increase the sales of bakery shop menus by making a menu package recommendations from the menus most frequently purchased by customers. The k-means algorithm performs grouping on menus to get menu packages. Furthermore, the fp-growth algorithm looks for linkages between frequently purchased menus to get menu package recommendations. The results of the research that the dominant items often purchased in cluster0 packages are hotdogs, pancakes, milk, garlic breadsticks with a confidence value of 92%, cluster1 packages are garlic breadsticks, hotdogs, chicken sand, pancakes with a confidence value of 92% and the last cluster2 packages are garlic breadstick, pastry, milk with a confidence value of 79%.

U ovom radu opisan je proces analize potrošačke košare. Analiza potrošačke košare uobičajen je primjer pronalaska čestih podskupova velikog skupa elemenata. Pronalaženje čestih podskupova služi otkrivanju asocijativnih veza između elemenata sadržanih u velikoj relacijskoj ili transakcijskoj bazi podataka. U radu su opisani i programski ostvareni neki od najpoznatijih algoritama za pronalaženje čestih podskupova elemenata: A-Priori, FP-growth te ECLAT. Implementirani su algoritmi ispitani na velikom skupu transakcija te su prikazani rezultati izvođenja. Konačno je dana međusobna usporedba rezultata izvođenja programski ostvarenih algoritama i njihovih općih karakteristika. In this paper, process of market basket analysis is described. Market basket analysis is a common example of mining frequent itemsets in a large data set. Mining frequent itemsets is used for discovering association relationships among elements from transactional or relational data sets. In this paper, some of the most popular algorithms for finding frequent itemsets are described and implemented, such as A-Priori, FP-growth and ECLAT. The implemented algorithms are tested on a large set of transactions and the performance results are presented. Finally, a comparison of the performance results of the implemented algorithms and their general characteristics is given.

Perilaku konsumen dalam membeli suatu produk memang sangat beragam. Ada pembeli yang gemar membeli produk yang telah dipaket, tetapi ada juga pembeli yang membeli produk yang mendapat diskon, dan masih banyak lagi. Keragaman perilaku konsumen dalam memilih barang yang ingin dibeli tentunya menjadi permasalahan tersendiri bagi para penjual jika ingin meningkatkan penjualannya. Algoritma FP-Growth sendiri merupakan hasil perbaikan dari algoritma Apriori. FP-Growth membangkitkan struktur data tree atau yang lebih dikenal sebagai frequent pattern tree. FP tree memerlukan dua kali scanning database untuk menentukan frequent itemset sehingga membuatnya lebih efisien dibandingkan Apriori. Hasil dari association rules menggunakan FP-Growth dijadikan rekomendasi bagi para penjual / retailer dalam memberikan paket penjualan barang bagi konsumennya dan hasil dari penelitian ini adalah ditemukan dua pasangan item barang yakni kopi, gula dan teh, susu yang memiliki support sebesar 30% dan confidence sebesar 70%.

El objetivo de este trabajo de investigación es descubrir reglas de asociación relevantes entre las categorías de productos en una base de datos de una entidad retail de electrodomésticos, a través del uso del algoritmo de inducción FP-Growth de la minería de datos. Cada regla de asociación determina un comportamiento de compra de los clientes, y permite conocer cuál es la probabilidad de que un determinado cliente compre un producto categorizado como Y dado que anteriormente compró un producto categorizado como X. El trabajo se aplicó en tres de las tiendas más representativas de la región norte del país de la entidad retail: Trujillo, Chiclayo y Piura. Se construyó un modelo en el software de minería de datos RapidMiner Studio conectado a una base de datos en Microsoft SQL Server que contiene la información histórica de diez años de la entidad retail. El modelo fue ejecutado una vez para cada tienda. Como resultado se encontraron reglas de asociación relevantes en Chiclayo y Piura que relacionan computadoras de escritorio e impresoras, reproductores y televisores. Los resultados también demostraron patrones de comportamiento distintos de clientes en cada tienda.

The design of steel logistics parks acts as fundamental infrastructure supporting the operations of storage, allocation, and distribution of steel products in the steel logistics industry, which actually lags behind the development of other logistics industries, such as e-commerce logistics, due to its large lot bulk storage, low turnover rate, and costly transportation and operations. This research proposes a data-driven approach for a specific steel logistics park, aiming to improve its operational efficiency in terms of product layout and allocation in multiple yards. The entry and delivery order data are analyzed comprehensively so as to determine the products with high operational frequency and the corresponding relevancy among them. Experimental results show that, among the 69 steel specifications, 14 high-frequency products are identified, and the correlation among the 14 identified high-frequency products possesses evident distribution characteristics concerning their brands and specifications. The identified frequency and correlation among various products can not only facilitate the product layout and allocation in steel logistics parks, but also advance the vehicle scheduling efficiency for product pick-up and delivery. Moreover, the research methodology and framework can provide managerial insights for other industries with mass data processing requirements.

International audience; Nowadays, the high interest of Android applications makes them the target of a huge number of malware. To detect this severe increase of Android malware and help end-users make a better evaluation of apps at install time, several approaches have been proposed such as statistic and dynamic approaches. However, these approaches cannot detect with high accuracy unfamiliar malware types. That inspired us to find a new approach for recognizing a malware basing on the anomalous set of permission it requests. To actualize that idea, we used the theory of frequent patterns, a data mining technique, for mining the frequent combination of requested permissions. We also compare the performance of the proposed system to other malware detection applications. Experimental results show that the proposed system yielded high accuracy with approximately 97 percent of normal applications and 86 percent of abnormal applications.

The organizations extremely are competitive surroundings, in which the administration of the relations with the clients acquires a signicant, especially in the related thing to the loyalty, the increase of the sales and the increase of the yield. Consequently, the organizations are called to administer the relations with their clients from the strategic point of view, but also from the tactical and operative point of view. By such reason, the technology is one of those components that such management supports and that its effective implementation potentialises. The present article sets out the results of a degree project, that approached problematic concerning the management of relations with the clients in a restaurant of fast meals of Tuluá, based on the methodology the SCRUM and techniques of mining of data, the result was a computer science system for the support to the decision making in the context of the intelligence of businesses. The integration of the algorithms of near neighbors (KNN) and FP-GROWTH stands out, with the purpose of emitting recommendations in relation to the preferences of the consumers with base in the composition of products more consumed by them. In addition, once integrated the algorithms they tried on in four different scenes, which allowed to conclude that such integration does not have associate a high computer cost. Actualmente las organizaciones se encuentran un entorno sumamente competitivo, en el que la administración de las relaciones con los clientes cobra un valor significativo, especialmente en lo relacionado a la fidelización, el aumento de las ventas y el incremento de la rentabilidad. En consecuencia, las organizaciones están llamadas a administrar las relaciones con sus clientes desde el punto de vista estratégico, pero también desde el punto de vista táctico y operativo. Por tal motivo, la tecnología es uno de esos componentes que apoya tal gestión y que potencializa su efectiva 28implementación. El presente artículo expone los resultados de un proyecto de grado , que abordó la problemática concerniente a la gestión de relaciones con los clientes en un restaurante de comidas rápidas de Tuluá, basado en la metodología SCRUM y técnicas de minería de datos, el resultado fue un sistema informático para el apoyo a la toma de decisiones en el contexto de la inteligencia de negocios. Se destaca la integración de los algoritmos de vecinos cercanos (KNN) y FP-GROWTH, con el fin de emitir recomendaciones en relación con las preferencias de los consumidores con base en la composición de los productos más consumidos por ellos. Además, una vez integrados los algoritmos se probaron en cuatro escenarios diferentes, lo que permitió concluir que tal integración no tiene asociado un costo computacional elevado. As organizações são encontradas resumo-atualmente um ambiente superiormente competitivo, onde a administração das relações com os clientes percebe um valor significativo, especialmente que está relatório délisation, o aumento das vendas e o crescimento da rentabilidade. Por conseguinte, as organizações são chamadas de administrar as relações com os seus clientes do ponto de vista estratégico, mas também o ponto de vista tático e operacional. Por tal motivo, a tecnologia é um destes componentes que apoia tal gestão e que potencialize a sua aposta em obra efetiva. O presente artigo expõe os resultados de um projeto de grau [1], que abordou a problemática relativa à gestão de relações com os clientes num restaurante de restaurações rápidas de Tuluá, baseado a metodologia SCRUM e técnicas de indústria mineira de dados, o resultado foi um sistema informático para o apoio à tomada de decisão no contexto da inteligência de negócios. Sublinha-se a integração dos algoritmos de vizinhos próximos (KNN) e de FP-GROWTH, a em de emitir recomendações em relação às preferências dos consumidores com base na composição dos produtos mais consumidos por eles. Além disso, uma vez integrados os algoritmos foram provados em quatro cenas diferentes, que permitiu concluir que tal integração não associou um custo computacional que importa.

In this research we extract knowledge from human resources data, accumulated in IT companies for the right selection of teams to work on software projects. We are looking for interesting and unknown dependencies and connections in the data, based on which managers can form more cohesive and professionally working project teams. The proposed approach to improve the selection of teams working on IT projects is based on association rule mining and can be used by IT managers to select the members of the teams. The approbation of the proposed approach is made using the software product RapidMiner. Keywords –IT project, Project team, Association Rule Mining, Apriori, FP-Growth.

Journal of Applied Informatics and Technology, 1, 2, 103-111

Bilişim teknolojilerinin hızlı gelişimine bağlı olarak her sektör ve sistemde hızla artan veri yığınları, veri madenciliği alanındaki çalışmalara çeşitlilik ve önem kazandırmaktadır. Veri madenciliği çalışmaları, perakendecilik sektöründe müşterilerin ihtiyaçlarının tespiti ve onlara uygun çözümler bulma, sunulan hizmetlerin geliştirilmesi bunlara dayalı olarak yapılacak yatırımların ve stratejilerin tespitinde, günümüzde karar verme sürecinde yer alanlara oldukça yardımcı olmaktadır. Bu çalışmada Veri Madenciliği teknikleri ile perakende sektöründe hizmet veren bir firmaya ait 10000 satırlık verileri üzerinde, uygulama bölümünde WEKA programı aracılığıyla, FP-Growth algoritması kullanılarak veri madenciliği birliktelik analizi yapılmıştır. Yapılan bu çalışma sonucunda birlikte satılma eğilimi gösteren ürünler hakkında bilgiler verilmiştir. Üç bölümden oluşan tez, Veri Madenciliği hakkında genel bilgiler, analizde kullanılan “Birliktelik Analizi” hakkında detaylı teorik bilgiler ve son olarak da uygulama bölümlerini içermektedir., Rapidly growing data stacks in every sector and systems give importance and diversity to studies on data mining depending on rapid development of information technologies. Data mining studies are quite helpful for decision makers take part in retail industry in determining of customer needs and finding proper solutions for them and developing services offered and building strategies and investment policies according to them. In this study, data mining association analysis were conducted using FR-Growth algorithm through WEKA software on 10,000 rows of data which belong to business firm serve in retail industry. In consequence of this study, information was given about products that tend to be sold together. The thesis which consist of three chapters contains general information about data mining, elaborative theoretical information about “Association Analysis” used in analysis and sections of applications conducted in this research.

Artikel ini merupakan versi postprint, artikel ini sudah dipublikasi pada prosiding SNASTIKOM 2015 yang dilaksanakan pada tanggal 1-2 September 2015 di Hotel Grand Kanaya dengan penyelenggara STTH Medan

Identifying related offences in a criminal investigation is an important goal for crime analysts. This can deliver evidence that can assist in apprehension of suspects and better attribution of past crimes. The use of pattern based approaches has the potential to assist crime experts in discovering new patterns of criminal activity. Hence, research in this area continues. This paper revisits frequent pattern growth models for crime pattern mining. Frequent pattern (FP) based approaches, such as the FP-Growth model, have been identified to be more effective than techniques proposed in the past, such as Apriori. Therefore, this research proposes a descriptive statistical approach, based on a quartile (floor-ceil) function, for the minimum support threshold (MST) choice selection, which is a major decision step in the pruning phase of the Traditional FP-Growth (TFPG) model. Our revised frequent pattern growth (RFPG) model further proposes a Pattern-pattern (Pp) paradigm to identify tuples of subtle crime pattern(s) sequences or recurring trends in criminal activity. We present empirical results in order to guide intended audience about future decisions or research regarding this model. Results indicate that RFPG is more promising than TFPG and will always ensure the utilisation of a reasonable percentage of the crime dataset, in order to produce more reliable and sufficiently informative patterns or trends.

Asocijativna pravila pogodna su za pronalaženje relacijskih odnosa između više varijabli u velikim skupovima podataka. Odnosi između varijabli, takozvana asocijativna pravila, izvode se u obliku implikacija AKO-ONDA. Najčešće korišteni algoritmi generiranja asocijativnih pravila su Apriori, FP-Growth, Tertius, Eclat i OPUS. U okviru ovog rada opisani su principi rada algoritama Apriori i FP-Growth te je opisan postupak implementacija algoritma Apriori unutar sustava za upravljanje podatcima imena Splunk. U konačnici vlastita implementacija algoritma Apriori uspoređena je na više skupova podataka sa postojećom implementacijom istog algoritma u aplikaciji imena Weka. The association rules are suitable for finding relationships between multiple variables in large sets of data. Relationships between variables, so-called association rules, are derived in the form of IF-THEN implications. The most commonly used algorithms for generating association rules are Apriori, FP- Growth, Tertius, Eclat and OPUS. This thesis describes the principles of Apriori and FP-Growth algorithms and also describes the procedure of Apriori algorithm implementation within Splunk data management system. Results of Splunk implementation of the Apriori algorithm are compared to multiple data sets with the existing implementation of the same algorithm in the Weka application.

One of the most popular methods of knowledge discovery in databases is the extraction of association rules. There are many different algorithms for association rule learning , which differ in space and time complexity. To perform a comparative analysis, we have implemented Apriori, Eclat and FP-growth algorithms and compared their time and memory consumption using synthetic and real databases. The analysis has shown that the FP-growth algorithm is the most efficient in the majority of cases. Zanimanje za metode odkrivanja znanja v podatkovnih bazah nenehno raste. Sodobne podatkovne baze so zelo velike, dosegajo terabajte in težijo k nadaljnemu povečanju, kar zahteva učinkovite, razširljive algoritme, ki lahko rešujejo težavo obdelave podatkov v razumnem roku. Ena od najbolj učinkovitih in priljubljenih metod za odkrivanje znanja je učenje asociacijskih pravil za ugotovitev različnih vrst pravilnosti v podatkih.

Association rule mining is one of the most important fields of data mining and knowledge discovery. In this paper, we propose an efficient multiple support frequent pattern growth algorithm which we called “MSFP-growth” that enhancing the FPgrowth algorithm by making infrequent child node pruning step with multiple minimum support using maximum constrains. The algorithm is implemented, and it is compared with other common algorithms: Apriori-multiple minimum supports using maximum constraints and FP-growth. The experimental results show that the rule mining from the proposed algorithm are interesting and our algorithm achieved better performance than other algorithms without scarifying the accuracy., {"references":["S. Brin, R. Motwani, J. Ullman, and S. Tsur, \"Dynamic itemset counting\nand implication rules for market basket data,\" in SIGMOD-97, 1997, pp.\n255-264.","C. Aggarwal, and P. Yu \"Online generation of association rule,\" in\nICDE-98, (1998), pp. 402-411.","R. Uday Kiran, P. Krishna Reddy , \"An efficient approach to mine rare\nassociation rules using maximum items support constraints data Security\nand security data, \" Springer, vol. 6121, pp. 84-95,2010.","L. Troiano, G. Scibelli and C. Birtolo, \"A fast algorithm for Mining rare\nitemsets,\" in Conf. 2009 the Ninth IEEE International Conference on\nIntelligent Systems Design and Applications, pp. 1149-1155.","K. S. C. Sadhasivam, T. Angamuthu, \"Mining rare Itemset with\nAutomated Support Thresholds,\" Computer Science J., vol. 7, pp. 394-\n399, 2011.","R. Agrawal, T. Imielinksi and A. Swami, \"Mining association rules\nbetween sets of items in large database,\" in 1993The ACM SIGMOD\nConf., pp. 207–216.","R. Agrawal and R. Srikant, \"Fast algorithms for mining association\nrules,\" in 1994VLDB Conf., Santiago, Chile, Expanded version\navailable as IBM Research Report RJ9839.","Y. Lee, T. Hong and W. Lin, \"Mining association rules with multiple\nminimum supports using maximum constraints,\" Elsevier Inc., 2005.","B. Liu, W. Hsu and Y. Ma, \"Mining association rules with multiple\nminimum supports,\" in 1999The International Conf. on Knowledge\nDiscovery and Data Mining, pp. 337–341.\n[10] J. Han, J. Pei and Y. Yin, \"Mining frequent patterns without candidate\ngeneration,\" in 2000International Conf. on Management of data, vol. 29,\npp. 1-12.\n[11] Z. Sun, \"Analysis and implementation of the algorithm of fp-growth,\"\nGuangxi Institute of Technology J., vol. 16, no. 3, pp. 64-67, 2004.\n[12] R. U. Kiran, P. K. Reddy, \"An improved multiple minimum support\nbased approach to mine rare association rules,\" in 2009 IEEE Int. Conf.\nCommunications Computational Intelligence and Data Mining, pp. 340-\n347.\n[13] R. U. Kiran, P. K. Reddy , \"An Improved Frequent Pattern growth\nApproach To Discover Rare Association rules,\" in 2009 International\nConf. on Knowledge Discovery and Information Retrieval, pp. 43-52.\n[14] S. Tsang, Y. S. Koh and G. Dobbie, \"Finding Interesting Rare\nAssociation Rules Using Rare Pattern Tree,\" The University of\nAuckland, Springer-Verlag Berlin Heidelberg,2013.\n[15] J. Pei, J. Han, B. Mortazavi-Asl, J. Wang, H. Pinto, Q. Chen, M. Hsu, ,\n\"Mining sequential patterns by pattern-growth: the prefixspan\napproach,\" IEEE Trans. Knowledge and Data Engineering 16, 1424–\n1440, 2004.\n[16] R. Srikant, Q. Vu, and R. Agrawal, \"Mining association rules with item\nconstraints,\" KDD-97, pp. 67-73, 1997.\n[17] Y. Hu, F. Wu, Y. Liao, \"Sequential pattern mining with multiple minimum\nsupports: a tree based approach\", in 2010, The 2nd International\nConf. on Software Engineering and Data Mining, Chengdu, China.\n[18] J. Pie, J. Han, and L. Lakshmanan., \"Mining frequent itemsets with\nconvertible constraints\", in 2001 IEEE ICDE Conf., p.433– 442.\n[19] M. S. Saravanan, R.J. Rama, \"Performance study of Association Rule\nMining Algorithms for Dyeing Processing System Innovative Systems\nDesign and Engineering\", Vol 2, No 5, 2011.\n[20] http://www.cs.waikato.ac.nz/ml/weka , Last acess : 6 march 2015 \n[21] M. Walaa, H. Ahmed and K. Hoda, \"Combined Algorithm for Data\nMining using Association rules,\" Ain Shams of Electrical Engineering\nJ., Vol. 1.No. 1 ISSN: 1687-8582, 2008.\n[22] P. Jyothi, V. D. Mytri, \"A Fast association rule algorithm based on\nbitmap computing with multiple minimum supports using max\nconstraints,\" International of Comp. Sci & Electronics J.,Volume1,Issue\n2, IJCSEE,2013.\n[23] F.A. Hoque , N. Easmin and K. Rashed, \" Frequent pattern mining for\nmultiple minimum supports with support tuning and tree maintenance on\nincremental database,\" Research of Information Technology J., 3(2): 79-\n90 ,2012."]}

Pagrindinis šio magistro baigiamojo darbo tikslas buvo apžvelgti kai kurių algoritmų ir jų kombinacijų pritaikymą daugiamačiams sekų šablonams analizuoti ir įgyvendinti algoritmą, gebantį tai atlikti. Buvo aprašyta FP-Tree medžio struktūra, kuri yra skirta kompaktiškai saugoti kritiniams (pvz., dažnai pasikartojantiems) duomenims, pateiktas FP-Growth algoritmas, galintis analizuoti tokią duomenų struktūrą ir rezultate pateikiantis visų dažnų elementų šablonų aibę. Pristatyta modifikuotų FP-Growth ir PrefixSpan algoritmų kombinacija – MD-PS-FPG algoritmas, pateikti kai kurių atliktų testavimų rezultatai, tolimesnių darbų pagrindiniai tikslai ir pan. The main goal of this master final work was to present some of the algorithms and their combinations for the multidimensional sequence pattern mining and implement an algorithm, that is capable of doing that. FP-Tree, that is used to store critical (for example, often repeated) data, was described. FP-Growth algorithm, that can analyze FP-Tree structure and give frequent pattern set as a result, was presented. MD-PS-FPG algorithm – a combination of modified FP-Growth and PrefixSpan algorithms – was introduced. The results of some tests, further work objectives and other things were also presented.

Due to copyright restrictions, the access to the full text of this article is only available via subscription. Günümüzde bilişim dünyası faydalı bilgiye ulaşma yolunda “büyük veri” problemleri (verinin kütlesi, hızı, çeşitliliği, tutarsızlığı) ile baş etmeye çalışmaktadır. Bu makalede, büyük veri akışları üzerinde İlişkisel Kural Madenciliği’nin (İKM) daha önce literatürde yapılmamış bir şekilde “çevrimiçi” olarak gerçeklenme detayları ile başarım bulguları paylaşılacaktır. Akış madenciliği için Apriori ile FP-Growth algoritmaları Esper isimli olay akış motoruna eklenmiştir. Elde edilen sistem üzerinde bu iki algoritma kayan penceler ve LastFM sosyal müzik sitesi verileri kullanılarak karşılaştırılmıştır. Başarımı yüksek olan FPGrowth seçilerek gerçek-zamanlı ve kural-tabanlı bir tavsiye motoru oluşturulması sağlanmıştır. En önemli bulgularımız çevrimiçi kural çıkarımı sayesinde: (1) çevrimdışı kural çıkarımından çok daha fazla kuralın (2) çok daha hızlı ve etkin olarak ve (3) çok daha önceden hesaplanabileceği gösterilmiştir. Ayrıca müzik zevklerine uygun “George Harrison⇒The Beatles” gibi pekçok ilginç ve gerçekçi kural bulunmuştur. Sonuçlarımızın ileride diğer büyük veri analitik sistemlerinin tasarım ve gerçeklemesine ışık tutacağını ummaktayız. TÜBİTAK ; European Commission

Frequent itemset mining finds frequently occurring itemsets in transactional data. This is applied to diverse problems such as decision support, selective marketing, financial forecast and medical diagnosis. The cloud, computation as an utility service, allows us to crunch large mining problems. There are a number of algorithms for doing frequent itemset mining, but none are out-of-the-box suited for the cloud, requiring large data structures to be synchronized across the network. One of the best algorithms for doing frequent itemset mining is the known FP-growth (Frequent Patterns growth). We develop a cloud-enabled algorithmic variant for frequent itemset mining that scales with very little communication and computational overhead and even, with only one worker node, is faster than FP-growth. We develop the concept of a postfix path and show how this allows us to lower the communicational cost and leads to adjustable work sizes. This concept provides a very exible algorithmic solution that can be applied to a wide variety of different problem sizes and setups.

Due to copyright restrictions, the access to the full text of this article is only available via subscription. Due to prevalent use of sensors and network monitoring tools, big volumes of data or “big data” today traverse the enterprise data processing pipelines in a streaming fashion. While some companies prefer to deploy their data processing infrastructures and services as private clouds, others completely outsource these services to public clouds. In either case, attempting to store the data first for subsequent analysis creates additional resource costs and unwanted delays in obtaining actionable information. As a result, enterprises increasingly employ data or event stream processing systems and further want to extend them with complex online analytic and mining capabilities. In this paper, we present implementation details for doing both correlation analysis and association rule mining (ARM) over streams. Specifically, we implement Pearson-Product Moment Correlation for analytics and Apriori & FPGrowth algorithms for stream mining inside a popular event stream processing engine called Esper. As a unique contribution, we conduct experiments and present performance results of these new tools with different tumbling and sliding time-windows over two different stream types: one for moving bus trajectories and another for web logs from a music site. We find that while tumbling windows may be more preferable for performance in certain applications, sliding windows can provide additional benefits with rule mining. We hope that our findings can shed light on the design of other cloud analytics systems. Avea Labs ; TÜBİTAK ; European Commission ; IBM Shared University Research Program

This article proposes an innovative utility sentient approach for the mining of interesting association patterns from transaction databases. First, frequent patterns are discovered from the transaction database using the FP-Growth algorithm. From the frequent patterns mined, this approach extracts novel interesting association patterns with emphasis on significance, utility, and the subjective interests of the users. The experimental results portray the efficiency of this approach in mining utility-oriented and interesting association rules. A comparative analysis is also presented to illustrate our approach's effectiveness.

Conselho Nacional de Desenvolvimento Científico e Tecnológico O processo tradicional de descoberta de conhecimento em bases de dados (KDD Knowledge Discovery in Databases) não contempla etapas de processamento multidimensional e multinível (i.e., processamento OLAP - OnLine Analytical Processing) para minerar cubos de dados. Por conseqüência, a maioria das abordagens de OLAM (OLAP Mining) propõe adaptações no algoritmo minerador. Dado que esta abordagem provê uma solução fortemente acoplada ao algoritmo minerador, ela impede que as adaptações para mineração multidimensional e multinível sejam utilizadas com outros algoritmos. Além disto, grande parte das propostas de OLAM para regras de associação não considera o uso de um servidor OLAP e não tira proveito de todo o potencial multidimensional e multinível presentes nos cubos OLAP. Por estes motivos, algum retrabalho (e.g., re-implementação de operações OLAP) é realizado e padrões possivelmente fortes decorrentes de generalizações não são identificados. Diante desse cenário, este trabalho propõe a arquitetura DOLAM (Decoupled OLAM) para mineração desacoplada de regras de associação multidimensional, multinível e de outliers em cubos OLAP. A arquitetura DOLAM deve ser inserida no processo de KDD (Knowledge Discovery in Databases) como uma etapa de processamento que fica entre as etapas de Pré-Processamento e Transformação de Dados. A arquitetura DOLAM define e implementa três componentes: 1) Detector de Outliers, 2) Explorador de Subcubos e 3) Expansor de Ancestrais. A partir de uma consulta do usuário, estes componentes são capazes de, respectivamente: 1) identificar ruídos significativos nas células do resultado; 2) explorar, recursivamente, todas as células do resultado, de forma a contemplar todas as possibilidades de combinações multidimensional e multinível e 3) recuperar todos os antecessores (generalizações) das células do resultado. O componente central da arquitetura é o Expansor de Ancestrais - o único de uso obrigatório. Ressalta-se que, a partir desses componentes, o processamento OLAM fica desacoplado do algoritmo minerador e permite realizar descobertas mais abrangentes, as quais, por conseqüência, podem retornar padrões potencialmente mais fortes. Como prova de conceito, foi realizado um estudo de caso com dados reais de uma empresa de micro-crédito. O estudo de caso foi implementado em Java, fez uso do servidor OLAP Mondrian e utilizou as implementações dos algoritmos para mineração de regras de associação APriori e FP-Growth do pacote de software Weka

Journal of Information Science and Technology, 1, 1, 15-22

Actualmente, a prescrição electrónica na prática clínica é muitas vezes utilizada em acções de apoio à tomada de decisão e à monitorização dos serviços prestados por organismos ligados à saúde pública. O sucessivo armazenamento de dados relativos à prescrição de medicamentos fez com que, já hoje, se possa aplicar algumas técnicas de mineração de dados com sucesso na procura de padrões de prescrição de medicamentos que possam ser interessantes para a optimização dos serviços dos organismos em causa. As regras de associação, usualmente utilizadas em processos de análise sobre dados referentes a transacções, podem ser aplicadas nesta área com alguma pertinência e utilidade. Na realidade, a ideia de descobrir padrões de prescrição de medicamentos é, só por si, muito atractiva pelo leque de novas opções de gestão e de rentabilização de serviços que abre. Neste trabalho apresentamos os resultados de um estudo realizado sobre a prescrição de medicamentos na região norte de Portugal, cujo objectivo principal foi o de descobrir padrões de prescrições entre os medicamentos prescritos, os médicos prescritores e os laboratórios prescritos., Today, electronic prescription in clinical scenarios is frequently used to support decision-making tasks and services monitoring in public health institutions. The huge amount of data that has been stored during last years about medication prescriptions makes now possible to apply data mining techniques with a significant success to discover patterns that could be useful to optimize medical services and resources related to medication prescription. Association rules, which are frequently used in the analysis of commercial transactions data, could be applied usefully on the medical prescriptions area. In fact, the idea of discovering medication prescriptions patterns it is quite attractive due to the wide range of new applications that can be opened to service management and optimisation. In this work, we present a study about medication prescriptions in the north region of Portugal, in order to discover some relevant patterns among medication, doctors and laboratories., (undefined)

La detección de alteraciones de la salud de los animales mediante pruebas de laboratorio es un proceso complejo que implica relacionar diversas variables y factores clínicos de los individuos; por ello, en esta investigación se evaluaron técnicas de inteligencia computacional que contribuyeron a la identificación de patrones de comportamiento de las alteraciones detectadas en las pruebas de hemograma aplicadas en bovinos. Aunque diversos algoritmos de inteligencia computacional son utilizados en la solución de problemas médicos, no se encontró registro de investigaciones en procesos médicos veterinarios. Una vez hecha una minuciosa caracterización de las variables y la evaluación de las técnicas de inteligencia computacional, se determinó que el algoritmo que mejor se ajusta al propósito de análisis de datos planteado es FP-Growth.

Journal of information systems in Business JISB, 6, 3, 56

With the development of technology, there is an increase in size and complexity of data. The increase bring about new needs in the process of data processing. Data mining, aimed to satisfy these needs, is the process of acquiring useful information from large data warehouses. In data mining, the purpose is usually to find the frequent items which is called frequent itemset mining (FIM). Different algorithms are developed and studied for this purpose. Because of the limited physical capacity, serial algorithms aren’t sufficient when solving large data problems. So, paralel computing becomes important. With parallel algorithms, it is aimed to save on time and sources (like storage and memory). FP-Growth is a data mining algorithm that is developed to find frequent itemsets. FP-Growth is known with performing only two scans while reading database and using frequent pattern tree to find frequent items. Because of this data structure, it becomes more efficient than other frequent itemset mining algorithms. In the study, there are three different parallel approaches implemented in MPI, a library that is used to write parallel programs. The first basis thing for the approaches is whether there is a database on all of the nodes or not. The second thing is how task parallelism is done. For task, there are static and dynamical approaches. These are tested and analysed in two different clusters. According to the results, two of them are better than the other one which is sent database (tree) to the other processors. For both of them, the running time of the parallel algorithms is decreased by one forth by using two nodes. In addition to that, dynamical task parallelism is better than the static one in better algorithms., Teknolojinin gelişmesiyle verilerin miktarında ve çeşitliliğinde bir artış gözlemlenmiştir. Bu artış, veri işleme yöntemlerinde yeni ihtiyaçları gündeme getirmiştir. Veri madenciliği bu ihtiyaçlara cevap verebilmek amacıyla geliştirilen büyük veri ambarlarından yararlı bilgi elde etme sürecidir. Veri madenciliği kapsamında, çoklukla gereksinim duyulan ve araştırılan konulardan biri sık öge küme madenciliğidir. Sık öge küme madenciliği için farklı algoritmalar üretilmekte ve incelenmektedir. Ancak, fiziksel kapasitelerin sınırlı olmasından dolayı seri algoritmalar artan veri miktarını karşılamaya yetmemektedir. Bu durum paralel hesaplamayı gündeme getirir. Paralel algoritmalarla, zamandan ve kaynaktan (depolama, hafıza gibi) tasarruf edebilmek amaçlanır. FP-Growth, sık öge kümelerini bulmak için geliştirilen bir veri madenciliği algoritmasıdır. Literatürde FP-Growth, işlenecek veritabanını sadece iki kez tarama ve sık ögeleri bulurken kullandığı sık örüntü ağacı özelliği ile bilinir. Kullandığı bu ağaç yapısı ile daha verimli bir algoritma sunar. Bu çalışma içerisinde FP-Growth algoritmasına, paralel programlar yazmak için geliştirilen bir kütüphane olan MPI ile kodlanan üç farklı paralel yaklaşım önerilmektedir. Bu yaklaşımlarda temel alınan şey, paralel uygulama sırasında düğümlerin tümünde veritabanının mevcut olup olmadığıdır. Ek olarak, paralellik için görev dağılımı esas alındığından görev dağılımının statik ya da dinamik olması da diğer bir parametredir. Bu yaklaşımların iki farklı öbek bilgisayar üzerinde performans analizi gerçekleştirilmiştir. Çıkan sonuçlara göre, veritabanının mevcut olduğu iki yaklaşımın ağaç gönderimi esasına dayanan diğer yaklaşıma göre daha iyi sonuç verdiği gözlemlenmektedir. Her ikisi için de, paralel algoritma iki işlemciyle çalıştığı durumda bile çalışma zamanını dörtte bir oranında azaltmaktadır. Buna ek olarak, daha iyi sonuç veren iki algoritma içerisinde görev dağılımının dinamik olarak gerçekleştiği durum statik görev dağılımlı yaklaşımdan daha iyi sonuç vermektedir.

Frontiers in neuroinformatics 15, 723406 (2021). doi:10.3389/fninf.2021.723406, Published by Frontiers Research Foundation, Lausanne