Search

Data is increasingly recognized as a valuable asset for generating new insights and information. Given the importance of data, businesses must always look for ways to get more value from data generated from sales transactions. In data mining, association rule mining is a good standard technique and is widely used to find interesting relationships in databases. Association rule is closely related to market basket analysis to find items that often appear together in one transaction. This study proposes the frequent pattern growth (FP-Growth) algorithm in finding association rules on sales transaction data. Our methodology includes dataset preparation for modeling, evaluation of model performance, and subsequent integration into a web-based platform. We conducted a comparative analysis of the FP-Growth algorithm against the Apriori algorithm, finding that FP-Growth outperformed Apriori in efficiency. Using the same dataset and constraint level, both algorithms produce the same number of frequent itemsets. However, in terms of computation time, FP-Growth excels by taking 2.89 seconds while Apriori takes 5.29 seconds. We integrated trained FP-Growth algorithm into a web-based dashboard application using the streamlit framework. This system is anticipated to simplify the process for businesses to identify customer purchasing patterns and improve sales. [ABSTRACT FROM AUTHOR]

The retail industry is a vital sector of the world economy and is characterized by fierce competition, tight profit margins, and demanding consumers. Understanding customer buying behavior patterns is essential in devising the best retail strategy to enhance product sales. This research aims to comprehend customer shopping behaviors based on retail sales transactions and formulate the best strategies. By employing multi-level association rules, the dataset is arranged hierarchically into categories, sub-categories, and items. The sales transaction data used comprises 5830 transaction records over a month. The results of this study reveal 24 associations of categories, 49 associations of sub-categories, and 12 associations of product items. Moreover, the proposed marketing strategy offers recommendations including store layout improvement, planogram design, and bundled product offerings. This research addresses the gap in empirical evidence from a previous study and suggests further observation from diverse locations to authenticate the findings, which may yield various outcomes

Manufacturing companies rely on machines for operational activities to produce finished goods. Common factors constraining the demand and supply of spare parts are the high number of spare parts managed and irregular patterns of demand for spare parts. These varying quantities also require investment in spare parts inventory and longer response times than predicted. The research aims to apply the FP-Growth algorithm approach to find association rules and produce patterns of demand and supply of spare parts in lightweight brick manufacturing companies based on transaction data on demand and supply of spare parts from January – March 2023. The approach used is associated with the applied algorithm. In this research, the primary process of the FP-Growth algorithm is to create a combination of each item until no more combinations are formed using minimum support and minimum confidence parameters. Based on the results of making association rules using spare parts demand data from the machine maintenance department, it is stated that the regulations formed from processing the RapidMiner application with a confidence value of 100% recommend FD Regular Bolt spare parts, then the next rating with a confidence value of 94% is Steel Nuts, seven rules recommend Nuts. Steel. Therefore, it is recommended that FD Regular Bolts and Steel Nuts carry out safety stock to maintain stock availability and place them on shelves included in the fast-moving inventory category.

Sustainable agriculture is becoming increasingly important in the face of growing environmental challenges. One key aspect of sustainable agriculture is managing soil resources effectively. In this context, digital soil mapping (DSM) has emerged as a powerful tool to understand soil variability better and inform land management decisions. This paper proposes a comprehensive data warehouse for DSM that supports climate change analysis. Our architecture integrates frequent itemset mining (FMI) and association rules mining (ARM) to extract insights from large‐scale soil data. We review related studies in soil data warehousing and ARM, identify gaps, and propose a data warehouse architecture leveraging the galaxy multidimensional model for DSM based on the SCORPAN model, which incorporates all relevant soil forming factors. We employ and compare A‐priori, FP‐growth, and ECLAT algorithms to efficiently mine frequent itemsets and generate association rules. Our intensive experiments evaluation demonstrates that FP‐growth outperforms the other algorithms in accuracy, scalability, and speed and requires less memory. Additionally, we utilized correlation metrics for ARM, such as lift, cosine, kulc, and Imbalance ratio, to obtain the most significant and relevant association rules. These rules provide valuable insights into the complex relationships between soil properties and environmental factors, which can inform land management decisions and improve sustainable agriculture practices. This work contributes to the growing body of research on DSM and data‐driven approaches to sustainable agriculture. [ABSTRACT FROM AUTHOR]

In this modern era, there is so much competition in the business world, especially in the sales industry, that requires shop owners to find a strategy that can increase sales and marketing of the products they sell, one of which is by utilizing clothing sales transaction data using data mining. Data Mining is an iterative and interactive process to find new patterns or models that can be generalized for the future, useful and understandable in a very large database (massive database). In these conditions, good data processing techniques are needed, one of which is data mining techniques. One thing that can be used in this technique is to use the Association rule method using the FP-Growth algorithm, which is an algorithm that produces frequent itemsets which will later be used to determine recommendations for clothing products for the needs of the Siny.co Store. This research uses the RapidMiner Studio application to help process transaction data. This research method uses a minimum support of 20% and a minimum confidence of 80%, thereby creating 9 association rules, where these rules determine several products for recommendation at the Siny.Co Store, including Sashi, Canna, Alice, Tartan, Aruna, Cassandra, Nala, Lalita, and Acio. [ABSTRACT FROM AUTHOR]

By launching a war against Ukraine, Russia changed the entire world system and demonstrated the ineffectiveness of the global security system. Today it is necessary to look for effective solutions to support the adoption of security decisions and develop effective strategies for the formation of a new architecture of the international security system.

In order to make full use of the accumulated curriculum data of Folk costume and dig out useful information from it, so as to provide useful information for curriculum teaching, the article proposes three general functions based on the requirement analysis, and pre-processes the completed grade data of ethnic costume students in 4 academic years, analyzes these data by FP-growth algorithm to understand the situation of association rules between different courses, and through K-means++ algorithm The clustering analysis of students with different levels of achievement is carried out and the results are validated by examples. In the algorithm performance analysis, the performance of FP-growth algorithm is better, the average absolute error of FP-growth algorithm is always smaller than that of Apriori algorithm; When the support degree is 20%, the running time of FP-growth algorithm is 0.4s, which is 0.4s less than that of Apriori algorithm. when the number of calculation nodes is 5, the running time of FP-growth algorithm and the accuracy of the K-means++ algorithm were higher than that of the K-means algorithm. In the Iris dataset, the accuracy of the K-means++ algorithm was 91.05%, which was 8.94% higher than that of the K-means algorithm. When mining the course grade data, the confidence level of the obtained association rules was even higher, even up to 97.15%. The standardized test score for the second group of students was 0.960. The course evaluation method used in the article was more objective and the accuracy of the data analysis was higher, providing valuable reference information for teachers' teaching. [ABSTRACT FROM AUTHOR]

The limited ability to memorize, understand Arabic, and access sources are obstacles to understanding Islamic knowledge, especially understanding hadith. Searching for access to sources to obtain hadiths that are in accordance with the theme and the interrelationships between themes improves the quality of the preachers towards religious understanding. This study investigates how to automate the thematic tracking pattern of Prophet Muhammad's hadith using the FP-Growth (Frequent Pattern-Growth) and ECLAT algorithms. The research was conducted using qualitative and quantitative approaches. The next step involves creating a prototype using the dataset development framework. The result of this study is a prototype of hadith tracing using the FP-Growth algorithm with the prophet's hadith dataset based on the Bulughul Maram book. [ABSTRACT FROM AUTHOR]

The aim of this study is to identify crypto assets with similar characteristics and to explore the similar responses of these assets to market-priced events. This process is carried out in two stages. Cluster analysis and association analysis were applied in the research. First of all, cluster analysis was performed using the variables; the total number of active unique addresses, USD value of the current supply, fixed closing price of the asset, return on investment of the asset, total of the current supply, number of transactions, USD value of the sum of native units and 30 days volatility criteria. HK-Means algorithm and R Program were used for clustering. Then, the co-movement of crypto assets was analyzed using the FP-Growth algorithm and the WEKA program. 71 crypto assets with the highest market capitalization and meeting the research criteria were included in the research. The data used in the research covers the period of May 2021-May 2022. According to the main findings obtained from the research; within the framework of the criteria used in the research, 4 clusters were formed. Most important association rules found to be between; btc (bitcoin) & aave (nominex), eth (ethereum) & aave (nominex), dot (polkadot) & aave (nominex), neo & aave (nominex), uni (uniswap) & aave (nominex), btg (bitcoin gold) & etc (ethereum classic), xrp (riple) & algo (algorand) & doge (dogecoin), xrp (riple) & doge (dogecoin), cro (cronos) & xrp (riple) & algo ( algorand) & trx (tron) & doge (dogecoin). [ABSTRACT FROM AUTHOR]

In order to explore potential value of explosively growing data in thermal power unit, this paper proposes a big data mining method based on Hadoop-based Spark cluster-computing framework and algorithms. Firstly, positive and negative balance methods are used to accurately obtain actual net coal consumption, and maximum information coefficient method is used to select all parameters related to optimization objectives. Then, Spark-based Mini-Batch K-means algorithm and Elbow method are constructed to divide whole operating modes. After that, all data are discretized and mapped to corresponding intervals by using Spark-based Elbow method and Mini-Batch K-means algorithm. Finally, Spark-based parallel FP-growth algorithm is used to deeply mine the potential relationships and laws. To verify the proposed method, a 350-MW thermal power unit is taken as a study case. The important conclusions are as follows: (1) the proposed Spark-based Mini-Batch K-means algorithm reduces the calculation time by 57.11% compared with Mini-Batch K-means algorithm, and 85.61% calculation time compared with K-means algorithm. The proposed Spark-based FP-growth algorithm reduces computational time by 32.8% compared with FP-growth algorithm. (2) Strong association rules of whole operating modes are mined, and operating optimization guidance schemes for important parameters are obtained. Take operating mode 1 as an example: if the optimal result can be reasonably applied, it can save 2.942 g coal per kilowatt hour. (3) Besides, we have found out some other potential relationships among parameters, which have important reference value for on-site operators to analyze economy of the thermal power unit. [ABSTRACT FROM AUTHOR]

Data analysis and processing is very important to support business development. One example is The Javanese Café which requires analysis and processing to determine promotional menu package recommendations. To carry out data analysis and processing, of course you need technology to make these activities easier. The technology that can be used to overcome this problem is data mining. Data mining has an association rule method which functions to form association patterns. Researchers also use the FP-Growth algorithm to speed up the data processing process. The sales transaction data processing resulted in 14 association patterns with the highest confidence values and 9 menu items with the lowest support values. Then the results were analyzed again and produced 4 recommendations for promotional menu packages that could be used to support product marketing strategies.

The popular association rule algorithms are Apriori and fp-growth; both of these algorithms are very familiar among data mining researchers; however, there are some weaknesses found in the association rule algorithm, including long dataset scans in the process of finding the frequency of the item set, using large memory, and the resulting rules being sometimes less than optimal. In this study, the authors made a comparison of the fp-growth, Apriori, and TPQ-Apriori algorithms to analyze the rule results of the three algorithms. TPQ- Apriori is an algorithm developed from the Apriori algorithm. For experiments, the Apriori and fp-growth algorithms use RapidMiner and Weka tools, while the TPQ-apriori algorithm uses self-built application programs. The dataset used is the sales data for the Kopegtel NTB department store, which has been uploaded on the Kaggle site. As for the results of testing the base rules from the overall results of testing the rules with the good Kopegtel dataset for 100%, 50%, and 25% of the total volume of the dataset, a conclusion can be drawn that the larger the dataset to be processed, the results will be more optimal when using the fp-growth algorithm RapidMiner, but not optimal if the dataset to be processed is small. It is different from using the Apriori and Weka FP-growth algorithms, where the resulting rules are less than optimal if the dataset used is large and optimal if the dataset is small. Several rules do not appear in the fp-growth and Apriori Weka algorithms because the two algorithms do not have a tolerance value in Weka's tools for the support of the rules that will be displayed. Meanwhile, the TPQ- Apriori algorithm that has been developed is capable of producing optimal rules for both large datasets and small datasets.

The feed rate is an important evaluation index of combine harvester performance. The quick identification of the amount of feed rate that enters the combine during harvesting is of great significance for the efficiency and operational quality of the combine harvester. To address this issue, this study proposes a feed rate discrimination method based on association rule mining. A self-designed data acquisition system was designed, taking the wheat combine harvester as object, and collected seven speed signals and three torque signals when the feed rate was 6 kg/s~8 kg/s, 8 kg/s~10 kg/s, and 10 kg/s~11 kg/s, respectively. The collected time series data were discretized so as to facilitate the construction of transaction sets. Then, the association rules in the constructed transaction set were mined by FP-Growth, and the rules with weak or no correlation with the increase in feed rate were filtered using min-support, min-confidence, and min-lift of 1.3, 0.8, and 3, respectively, to obtain strong association rules. Then, the strong association rules were constructed as classifiers. The test results showed that the accuracy of the constructed classifier for the identification of 6 kg/s~8 kg/s, 8 kg/s~10 kg/s, and 10 kg/s~11 kg/s feed rates was 100 %, 96 %, and 98.7 %, respectively. Research results can provide a basis for the adjustment of the working state of the combine harvester.

Under the background of large-scale PV (photovoltaic) integration, generating typical operation scenarios of power systems is of great significance for studying system planning operation and electricity markets. Since the uncertainty of PV output and system load is driven by weather factors to some extent, using PV output, system load, and weather data can allow constructing scenarios more accurately. In this study, we used a TimeGAN (time-series generative adversarial network) based on LSTM (long short-term memory) to generate PV output, system load, and weather data. After classifying the generated data using the k-means algorithm, we associated PV output scenarios and load scenarios using the FP-growth algorithm (an association rule mining algorithm), which effectively generated typical scenarios with weather correlations. In this case study, it can be seen that TimeGAN, unlike other GANs, could capture the temporal features of time-series data and performed better than the other examined GANs. The finally generated typical scenario sets also showed interpretable weather correlations. [ABSTRACT FROM AUTHOR]

For decades, changes in fish catch composition and the marine environment have been monitored worldwide and recorded in databases like FAO FishStatJ and the European Union Copernicus Marine Service. However, the complexity and high variability in the dataset makes it challenging to find meaningful information through conventional data analytical methods. Therefore, in this pilot data mining study, we employed association rule mining algorithms (Apriori, ECLAT, and FP-Growth) to find frequently occurring itemsets in the fish-catch composition and marine environment data of the west and east coasts of India during the past decade (2011-2020). Firstly, the inherent spatial and temporal variations in fish-catch composition and marine environment (sea surface temperature and chlorophyll) on the west and east coasts of India were statistically analyzed and described. Then, the data were preprocessed, selected, and transformed into categorical attributes. By applying the association rule mining algorithms written in the Python language in the Google Colab workspace, we obtained frequent itemsets of fish catch and marine environment with different levels of minimum support and confidence. The preliminary results showed linear and inverse associations between changes in the sea surface temperature, chlorophyll concentration, and major catch groups, such as anchovies, Indian oil sardine, Indian mackerel, hairtails, butterfish-pomfrets, Bombay duck, flatfish, tunas, giant tiger prawn, crabs, lobsters, and cephalopods. Among the tested data mining algorithms, FP-Growth was found to be more efficient and reliable in finding associations between the spatiotemporal dynamics of the marine environment and fish distribution and abundance. Therefore, it can be potentially used to support marine fisheries' resource assessment and management strategies after refinement. [ABSTRACT FROM AUTHOR]

The efficient discovery of frequent itemsets from a transaction database is the fundamental step for association rule mining in data analytics. Interesting associations among the items present in a transaction database contribute to knowledge enrichment. Thus, decision-making and pattern generation from the massive amounts of data become effortless. But one of the major problems associated with the algorithms of frequent itemset mining is excessive memory requirements, which cause them to be inappropriate for larger datasets with itemsets having high cardinality. A few novel data structures for mining frequent itemsets have been introduced in recent years. For example, N-List, NodeSet, DiffNodeSet, proximity list, etc. have been proposed that show a coherent mining approach for improving the execution time while still leaving the scope for further improvements in memory requirements. In this paper, we propose a novel algorithm using cellular learning automata (CLA) and multiple FP tree structures for frequent itemset mining that is efficient in both time and memory requirements. Extensive experimentation has been performed by comparing the performance of the proposed method with the leading algorithms and using publicly available real and synthetic datasets designed specifically for pattern mining algorithms. It can be concluded that the proposed method is memory-efficient and shows comparable execution time with varying dataset dimensions and dataset density, assuring its robustness. In addition to the proposal of the new methodology for frequent itemset mining, its potential domain-specific usage in species biodiversity data analysis has also been discussed. The fact that which groups of species are closely related can be derived from huge occurrence records of species datasets. This could help in understanding species co-occurrence in multiple sites, which in turn assists in solving ecology-related issues for afforesting and reforesting. It could be a step forward toward the advantageous use of computer science in the biodiversity domain. [ABSTRACT FROM AUTHOR]

Perkembangan teknologi memberikan dampak yang besar terhadap perkembangan dunia bisnis. Persaingan dalam dunia bisnis sangat ketat sehingga perlu melihat potensi transaksi penjualan produk dan memiliki strategi penjualan produk yang tepat. HNI Business Center 2 merupakan salah satu toko yang menjual produk herbal. Dengan banyaknya permintaan obat herbal pada saat covid-19 maka diperlukan stok obat guna meningkatkan penjualan produk. Maka diperkulan suatu anlisis untuk membantu pimpinan HNI Business Center 2 mengetahu produk yang harus ditingkatkan stoknya sesuai dengan data transaksi pelanggan. Maka dari permasalahan tersebut konsep yang bisa terapkan adalah data mining. Data yang di analisis nantinya menggunakan data mining adalah sejumlah 50 transaksi penjualan. Dengan menggunakan Minimum Support = 50% dan Maximum Support = 50%. Hasil penelitian ini dapat digunakan oleh HNI Businss Center 2 untuk mengambil keputusan menyetok kesediaan poroduk herbal.

The retail industry continues to grow and develop in Indonesia. The retail sector as a provider of goods used in everyday life has long started digital transformation in its business. Digital technology helps the retail industry collect valuable customer data. Business analytic is the use of data, information technology and statistical analysis, which is used to obtain information about a business and make decisions based on facts. Business analytic turns data into steps or actions in the context of making business decisions. Consumer needs and purchasing behavior can be predicted with big data-based technology. Association Rule is a technique in data mining to find the relationship between items in an item set combination. One of the utilizations of the association rule method is market basket analysis. Algorithms that can be used to analyze consumer purchasing patterns include the Apriori algorithm, Frequent Pattern Growth (FP-Growth) which represents a database structure in a horizontal format, and the Equivalence Class Transformation (ECLAT) algorithm which represents a vertical data format. In addition, this research will first analyze the complexity of the algorithm based on the time complexity in running the algorithm. This analysis uses these three algorithms, which are applied to Supermarket "X" transaction data in 2021, namely 136,202 transactions. The measure of goodness that is used to find out the best algorithm uses support and confidence values. The results show that the ECLAT algorithm is the most superior algorithm compared to the others based on the execution time required by the algorithm. The support value used in forming associations in the ECLAT algorithm is 1%, resulting in 19 rules. From the results of these rules, the highest support value was generated by the purchase of Indomie goreng special and Indomie ayam bawang, where as many as 1,362 shopping transactions bought these two items together or 2.71% of the total transactions.

Copyright of Techno.com is the property of Universitas Dian Nuswantoro, Fakultas Ilmu Komputer and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Schools and universities shuttered as a result of the worldwide COVID-19 pandemic lockdown, and student screen time skyrocketed. Since the programs are delivered online, a spike in social media use during lockdown resulted in many pupils becoming victims of cyberbullying, which includes criticizing one another, posting sexual comments on images of young ladies, and using fake accounts to bully others. Machine Learning (ML) and Natural Language Processing (NLP) techniques are being used in a growing body of work on automated cyberbullying detection. Different machine learning methods, however, are unable to converge to the requisite accuracy. Thus, numerous classifier systems known as "ensemble learning" are proposed in order to improve predictive performance by aggregating the predictions from various models. In our proposed system, we use a novel method of detecting online harassment (cyberbullying) on the Instagram dataset. The attributes of abusive words are initially analyzed from feature selection and pre-trained word embedding language models like Bidirectional Encoder Representations from Transformers (BERT) and Embeddings from Language Models (ELMO). A knowledge-based frequent pattern method is used to find the intention of the harasser and is created by the Knowledge-BERT (K-BERT). The unsupervised approaches such as Latent Semantic Analysis (LSA), Frequent pattern growth (FP-Growth), and a clustering technique K-Means. The results from the detection models are ensembled using Extreme Gradient Boosting (XGBoost) for classifying the categories of online harassment. The performance of the ensemble model is then cross-validated using machine learning metrics and compared with various existing techniques. An ensemble model performs better with a higher F1 score of 92.04% with less error rate in the classification of harassment categories. [ABSTRACT FROM AUTHOR]

The safety and stability of power networks have become increasingly important in the field of industrial control. Traditional information analysis for power networks overly relies on expert knowledge, and existing analysis models suffer from problems such as high algorithm complexity and rule redundancy. To address these issues, this paper proposes an advanced alarm information correlation analysis method that takes into account the characteristics of power networks. The method first eliminates noisy parts in the original alarm logs through a pre-processing module, then generates alarm transaction sets using a proposed method based on dynamic sliding time window, and subsequently applies the FP-Growth algorithm to mine alarm association rules for power networks. Finally, a time-based alarm rule filtering algorithm is proposed to eliminate invalid rules. Experiments conducted on alarm data collected from a situation awareness platform deployed in a power grid company show that this method reduces the redundancy of alarm rules by an average of about 30% compared to other similar association analysis method, and can effectively extract key alarm rules in power networks to guide fault warning. [ABSTRACT FROM AUTHOR]

This paper proposes a machine learning model based on the co-existence of static features for Android malware detection. The proposed model assumes that Android malware requests an abnormal set of co-existed permissions and APIs in comparing to those requested by benign applications. To prove this assumption, the paper created a new dataset of co-existed permissions and API calls at different levels of combinations, which are the second level, the third level, the fourth level and the fifth level. The extracted datasets of co-existed features at different levels were applied on permissions only, APIs only, permissions and APIs, and APIs and APIs frequencies. To extract the most relevant co-existed features, the frequent pattern growth (FP-growth) algorithm, which is an association rule mining technique, was used. The new datasets were extracted using Android APK samples from the Drebin, Malgenome and MalDroid2020 datasets. To evaluate the proposed model, several conventional machine learning algorithms were used. The results show that the model can successfully classify Android malware with a high accuracy using machine learning algorithms and the co-existence of features. Moreover, the results show that the achieved classification accuracy depends on the classifier and the type of co-existed features. The maximum accuracy, which is 98%, was achieved using the Random Forest algorithm and the co-existence of permissions features at the second combination level. Furthermore, the results show that the proposed approach outperforms the state-of-the-art model. Using Malgenome dataset, the proposed approach achieved an accuracy of about 98%, while the state-of-the-art achieved an accuracy of about 87%. In addition, the experiments show that using the Drebin dataset, the proposed approach achieved an accuracy of about 95%, while the state-of-the-art achieved an accuracy of about 93%.

The Apriori algorithm is one of the most widely developed and used association rule algorithms because it can produce optimal rules. The association rule a priori algorithm has three main problems: the old dataset scan process, less than optimal rules formed, and the use of large memory. Therefore, this study aims to improve the performance of the a priori algorithm in the itemset frequency search process with optimal rules, small memory usage, and fast dataset scans. The method used in this study is TID-List Vertical and data partitioning. This study result indicates that the TPQ-Apriori method improves the performance of the dataset scan process up to two times faster in scanning datasets compared to the study's results using the traditional a priori method. The performance of the dataset scan process from the results of this study is also superior in processing speed by up to 7% on scanning datasets compared to the ETDPC-Apriori method on testing three data sets (mushroom, chess, and c20d10k). [ABSTRACT FROM AUTHOR]

The Medan Marelan Health Center is one of the health centers in the city of Medan. The supply of medicines is considered necessary so that these medicines can still be available at any time with various types and functions. In order not to experience difficulties in distributing medicines and anticipating the supply of medicines in the Puskesmas, research was carried out using the Data Mining method. In this study, a test will be carried out on the Association Rule which is used as a solution to problems with the pattern of the drug procurement system, and will display information about the value of support and confidence from each Data Mining process. Tests in this study using Weka Software to determine the procurement of drugs that are often needed. Information obtained from the stages of the FP-Growth Algorithm is to produce patterns in the procurement of medicines, and an itemset combination pattern has been formed using the FP-Growth Algorithm method so that the results of this study can be used in drug supply effectively and efficiently.

This study aimed to find associated patterns by association rule mining and propose a prediction model using ensemble learning methods of high levels of trauma items affecting depression and suicide among primary school students in Thai rural extended opportunity schools. Our proposed methods were different from others that have analysed the relationship of high life trauma leading to depression and suicide by using statistical analysis. We found strongly associated patterns and effects among primary students’ trauma, depression, and suicide. The trauma of psychological abuse and neglect may result in suicide, whereas psychological abuse, neglect, and the experience of self-harm are also likely to result in the increased severity of traumatic events in life. The trauma of physical and sexual abuse, neglect, helplessness, feeling worthless, being weak, and self-harm were associated with depression. Our research discovered new knowledge that the risk of suicide arises from two extreme types of trauma: when children’s safety is frequently threatened and the family communicates frequently using rude or abusive words; these traumas may not merely correlate with depression but may ultimately result in suicide. Moreover, this study discovered 7 highly important trauma items and 4 suicide items for predicting depression and suicide using the Random Forest technique. We found that the Random Forest technique performed well in predicting depression and suicide. The predicted depression results show that the overall accuracy was 85.84%, precision was 89.33%, and recall was 75.28%. The predicted suicide results show that the overall accuracy was 91.28%, precision was 89.05%, and recall was 84.72%. From these results, we identified high life trauma affecting depression and suicide, which are very beneficial to practitioners to use in preliminary screening. In addition, those involved need to be aware and attentive in counselling these people with these symptoms in time. Doi: 10.28991/ESJ-2022-06-04-02 Full Text: PDF