Extracting Actionable Knowledge from Decision Trees

Most data mining algorithms and tools stop at discovered customer models, producing distribution information on customer profiles. Such techniques, when applied to industrial problems such as customer relationship management (CRM), are useful in pointing out customers who are likely attritors and customers who are loyal, but they require human experts to postprocess the mined information manually. Most of the postprocessing techniques have been limited to producing visualization results and interestingness ranking, but they do not directly suggest actions that would lead to an increase the objective function such as profit. Here, we present a novel algorithm that suggest actions to change customers from an undesired status (such as attritors) to a desired one (such as loyal) while maximizing objective function: the expected net profit. We develop these algorithms under resource constraints that are abound in reality. The contribution of the work is in taking the output from an existing mature technique (decision trees, for example), and producing novel, actionable knowledge through automatic postprocessing.

Objectives: Clustering algorithm is broadly used as spectral algorithm in social media, where a reference of contact is used and mined further for various combinations of suggested friends and lookups. This paper Identifies key lead generation techniques to be used in customer relationship management for sales marketing to decide data gathering. Also to define key merits and demerits of these techniques and to prepare a Matrix of comparison of these techniques to justify the data source and data set. M-Cluster algorithm is used for lead qualification i.e. training set preparation and data evaluation. Methods: Todefine a training set based on various attributes/fields in the data given for classification. This training set is used to run the data process and to produce expected result. This is assessed and accepted for definite data set processing or additional run for interim training data set preparation. Findings: This study is taken to customize clustering algorithm for data mining process in a customer relationship management field as the space of data is more and variant. Also proving the usability of customized clustering algorithm in data mining and the efficiency in processing mechanism compared to other methods used in current situation of data mining in customer relationship management is the part of this study. The customized algorithm developed as part of this study considers the two major areas of data mining using clusters. Applications: The results produced tremendous trends that the clustered algorithm suits to any data mining process when scaling and data classification are diversified and less in control.Keywords: Classification, Clustering Algorithm, Data Mining, K-Means, Lead Generation, M-Clustering Algorithm

The problem faced by the company is how to determine potential customers and apply CRM (Customer Relationship Management) in order to perform the right marketing strategy, so it can bring benefits to the company. This research aims to perform clustering and profiling customer by using the model of Recency Frequency and Monetary (RFM) to provide customer relationship management (CRM) recommendation to middle industrial company. The method used in this study consists of four steps: data mining from transaction history data of customer sales, data mining modeling using RFM with K-Means algorithm and customer classification with desicion tree (J48), determination of customer loyalty level and recommendation of customer relationship management (CRM) on the medium-sized industry. This research produces RFM data mining model for medium industrial companies. In addition, the results of the study provide recommendations of four customer segments and characteristics of each customer to perform customer relationship strategy.

Recent advances in computing, communications, digital storage technologies, and high-throughput data-acquisition technologies, make it possible to gather and store incredible volumes of data. It creates unprecedented opportunities for large-scale knowledge discovery from huge database. Data mining (DM) technology has emerged as a means of performing this discovery. There are countless researchers working on designing efficient data mining techniques, methods, and algorithms. Many data mining methods and algorithms have been developed and applied in a lot of application fields [1]. Unfortunately, most data mining researchers pay much attention to technique problems for developing data mining models and methods, while little to basic issues of data mining [2]. In this talk, some basic issues of data mining are addressed. What is data mining? What is the product of a data mining process? What are we doing in a data mining process? What is the rule we should obey in a data mining process? Through analyzing existing data mining methods, and domain-driven (or user-driven) data mining models [3-5], we find that we should take a data mining process as a process of knowledge transformation. Based on this understanding of data mining, a conceptual data mining model of domain-oriented data-driven data mining (3DM) is proposed [2]. The relationship between traditional domain-driven (or user-driven) data mining models and our proposed 3DM model is also analyzed. Some domain-oriented data-driven data mining algorithms for mining such knowledge as default rule [6], decision tree [7], and concept lattice [8] from database are proposed. The experiment results for these algorithms are also shown to illustrate the efficiency and performance of the knowledge acquired by our 3DM data mining algorithms.

Abstract- Utilization data mining in banking marketing strategy is very effective. Prospective customer seg-mentation is one of the processes carried out in the banking marketing strategy. To support the results of the success rate of telemarketing personnel to market the product in its role of banking services that the process requires a prospective customer data, then data mining support is very important in the classification of the prospective customers of the bank so that it can predict the degree of success in product marketing such services. Based on mapping studies of support data mining on prospective customers to come is no classification algorithms are often used for the classification of a borrower among others Neural Network, Naive Bayes, Dececion Tree, K-NN and Logistic Regreesion, of this algorithm can result from the evaluation process by using Cross Validation, confusion matrix, ROC Curve and T-Test to determine the classification of data mining algo-rithms are the most accurate in predicting success in product mar-keting telemarketing services from the bank to do trials in the Neural Network algorithm was more accurate with an accuracy of 89.71% the AUC value of 0872, this may be a comparison of data mining classi-fication Seeing AUC values of the five methods, then five groups of classification algorithms including both because of its AUC value between 0.80-1.00. Keywords : Comparison of data mining, decision tree, naive Bayes, neural network, k-nn, logistic regression

Preparing a data set for analysis is generally the most time consuming task in a data mining project, requiring many complex SQL queries, joining tables and aggregating columns. Existing SQL aggregations have limitations to prepare data sets because they return one column per aggregated group. In general, a significant manual effort is required to build data sets, where a horizontal layout is required. We propose simple, yet powerful, methods to generate SQL code to return aggregated columns in a horizontal tabular layout, returning a set of numbers instead of one number per row. This new class of functions is called horizontal aggregations. Horizontal aggregations build data sets with a horizontal denormalized layout (e.g. point-dimension, observation-variable, instance-feature), which is the standard layout required by most data mining algorithms. We propose three fundamental methods to evaluate horizontal aggregations: CASE: Exploiting the programming CASE construct; SPJ: Based on standard relational algebra operators (SPJ queries); PIVOT: Using the PIVOT operator, which is offered by some DBMSs. Experiments with large tables compare the proposed query evaluation methods. Our CASE method has similar speed to the PIVOT operator and it is much faster than the SPJ method. In general, the CASE and PIVOT methods exhibit linear scalability, where as the SPJ method does not. In a relational database, especially with normalized tables, a significant effort is required to prepare a summary data set that can be used as input for a data mining or statistical algorithm. Most algorithms require as input a data set with a horizontal layout, with several Records and one variable or dimension per column. That is the case with models like clustering, classification, regression and PCA; consult. Each research discipline uses different terminology to describe the data set. In data mining the common terms are point-dimension. Statistics literature generally uses observation-variable. Machine learning research uses instance-feature. This article introduces a new class of aggregate functions that can be used to build data sets in a horizontal layout (denormalized with aggregations), automating SQL query writing and extending SQL capabilities. We show evaluating horizontal aggregations is a challenging and interesting problem and we introduced alternative methods and optimizations for their efficient evaluation. II. MOTIVATION As mentioned above, building a suitable data set for data mining purposes is a time- consuming task. This task generally requires writing long SQL statements or customizing SQL Code if it is automatically generated by some tool. There are two main ingredients in such SQL code: joins and aggregations; we focus on the second one. The most widely- known aggregation is the sum of a column over groups of rows. Some other aggregations return the average, maximum, minimum or row count over groups of rows. There exist many aggregations functions and operators in SQL. Unfortunately, all these aggregations have limitations to build data sets for data mining purposes. The main reason is that, in general, data sets that are stored in a relational database (or a data warehouse) come

Stepping into the 21st century, Information Technology has reached a new era, and its market competition has become hotter than ever due to the request for higher standards. To all corporations, their means of survival is profits. The source for profits are customers; may it be business clients or individual consumers. Domestic insurance industry’s tactic on customer relationship has developed into using IT as a tool for Customer Relationship Management. 21st century is (e世代), naturally, the information technology is advancing into a powerful tool, but the merging of the (CRM) and (IT) has to first unify the company’s business strategies for it to be successful. New Information Technologies such as the Web、Internet、EC、Data Warehouse、Data Mining and IA has matured. They rely on strong interaction with the consumers to gain an edgy on the competition with other forms of communication. The goal of the company is to use the advantages that the IT provides so that it will stand out from the crowds. The aim of this research is to understanding the present commercial environment, for the enterprise to monitor the customer's demands regarding to the service, and the personnel's ability to provide the customers with necessary informations. it also attempts to create a modle to evaluate the quality of the system. It lets the company to understand why CRM went wronk, and how satisfied the customers are regarding to the system. The research concludes: -The system quality can affect the service personnels on the system useage and the system degree of satisfaction. -The information quality can affect the service personnels on the system useage and system degree of satisfaction -The service personnel's personal background factor?can also affect the service personnels on the system use and the system degree of satisfaction. -The degree of system useage can affect the service personnels on the degree of system satisfaction these findings may be used to supply other life insurance companies in the renewal, the development or reference to introduction of information system, they may also develop more appropriate insurance company information system with the information cooperation design

This study focuses on predicting which firms will increase capital by issuing new stocks in the near future. Many stakeholders, including banks, credit rating agencies and investors, performs a variety of analyses for firms' growth, profitability, stability, activity, productivity, etc., and regularly report the firms' financial analysis indices. In the paper, we develop predictive models for rights issues using these financial analysis indices and data mining techniques. This study approaches to building the predictive models from the perspective of two different analyses. The first is the analysis period. We divide the analysis period into before and after the IMF financial crisis, and examine whether there is the difference between the two periods. The second is the prediction time. In order to predict when firms increase capital by issuing new stocks, the prediction time is categorized as one year, two years and three years later. Therefore Total six prediction models are developed and analyzed. In this paper, we employ the decision tree technique to build the prediction models for rights issues. The decision tree is the most widely used prediction method which builds decision trees to label or categorize cases into a set of known classes. In contrast to neural networks, logistic regression and SVM, decision tree techniques are well suited for high-dimensional applications and have strong explanation capabilities. There are well-known decision tree induction algorithms such as CHAID, CART, QUEST, C5.0, etc. Among them, we use C5.0 algorithm which is the most recently developed algorithm and yields performance better than other algorithms. We obtained data for the rights issue and financial analysis from TS2000 of Korea Listed Companies Association. A record of financial analysis data is consisted of 89 variables which include 9 growth indices, 30 profitability indices, 23 stability indices, 6 activity indices and 8 productivity indices. For the model building and test, we used 10,925 financial analysis data of total 658 listed firms. PASW Modeler 13 was used to build C5.0 decision trees for the six prediction models. Total 84 variables among financial analysis data are selected as the input variables of each model, and the rights issue status (issued or not issued) is defined as the output variable. To develop prediction models using C5.0 node (Node Options: Output type = Rule set, Use boosting = false, Cross-validate = false, Mode = Simple, Favor = Generality), we used 60% of data for model building and 40% of data for model test. The results of experimental analysis show that the prediction accuracies of data after the IMF financial crisis (59.04% to 60.43%) are about 10 percent higher than ones before IMF financial crisis (68.78% to 71.41%). These results indicate that since the IMF financial crisis, the reliability of financial analysis indices has increased and the firm intention of rights issue has been more obvious. The experiment results also show that the stability-related indices have a major impact on conducting rights issue in the case of short-term prediction. On the other hand, the long-term prediction of conducting rights issue is affected by financial analysis indices on profitability, stability, activity and productivity. All the prediction models include the industry code as one of significant variables. This means that companies in different types of industries show their different types of patterns for rights issue. We conclude that it is desirable for stakeholders to take into account stability-related indices and more various financial analysis indices for short-term prediction and long-term prediction, respectively. The current study has several limitations. First, we need to compare the differences in accuracy by using different data mining techniques such as neural networks, logistic regression and SVM. Second, we are required to develop and to evaluate new prediction models including variables which research in the theory of capital structure has mentioned about the relevance to rights issue.

Many organisations across a variety of industries are engaging in the process of data mining as part of an overall strategy for business intelligence, customer relationship management (CRM), including churn prevention. This paper provides an overview of the data mining process and illustrates a case study in which data mining is utilised as a churn prevention tool for a major Midwest USA newspaper. For this case study, a decision tree, a common modelling technique, was the analytical tool of choice. Lessons learned throughout the data mining process are provided to offer insight and to promote the sharing of information. Strategies for getting started in the data mining process are presented to encourage organisations to embrace a data-driven strategy for business intelligence, CRM and churn prevention.

In this paper, we expand the process of classification to an ensemble of fuzzy decision tree. For indoor space recognition, many research use Boosted Tree, consists of Adaboost and decision tree. The Boosted Tree extracts an optimal decision tree in stages. On each stage, Boosted Tree extracts the good decision tree by minimizing the weighted error of classification. This decision tree performs a hard decision. In most case, hard decision offer some error when they classify nearby a dividing point. Therefore, We suggest an ensemble of fuzzy decision tree, which offer some flexibility to the Boosted Tree algorithm as well as a high performance. In experimental results, we evaluate that the accuracy of suggested methods improved about 13% than the traditional one.

Most data mining algorithms and tools when applied to industrial problems such as Customer Relationship Management, insurance and banking they stop search at producing actual applicable knowledge. Unlike these models, actionable knowledge discovery techniques are useful in pointing out customers who are likely attritors and loyal. However, actionable knowledge discovery techniques require human experts to postprocess the discovered knowledge manually. Postprocessing is one of the actionable knowledge discovery techniques which are effective in decision making and overcomes considerable inefficiency which leads to human errors that are inherent in the traditional data mining systems. Hence, decision trees are postprocessed which suggest cost effective actions in order to maximize the profit based objective function. In the proposed approach, an effective actionable knowledge discovery based classification algorithm namely Actionable Multiple Decision Trees (AMDT) is developed to improve the robustness and classification accuracy and tests are conducted on UCI German benchmark data.KeywordsData miningactionable knowledge discoveryPostprocessingDecision tree

This dissertation contributes with novel predictive modelling approaches to data-driven computational psychiatry and offers alternative analyses frameworks to the standard statistical analyses in psychiatric research. In particular, this document advances research in medical data mining, especially psychiatry, via two phases. In the first phase, this document promotes research by proposing synergistic machine learning and statistical approaches for detecting patterns and developing predictive models in clinical psychiatry data to classify diseases, predict treatment outcomes or improve treatment selections. In particular, these data-driven approaches are built upon several machine learning techniques whose predictive models have been pre-processed, trained, optimised, post-processed and tested in novel computationally intensive frameworks. In the second phase, this document advances research in medical data mining by proposing several novel extensions in the area of data classification by offering a novel decision tree algorithm, which we call PIDT, based on parameterised impurities and statistical pruning approaches toward building more accurate decision trees classifiers and developing new ensemblebased classification methods. In particular, the experimental results show that by building predictive models with the novel PIDT algorithm, these models primarily led to better performance regarding accuracy and tree size than those built with traditional decision trees. The contributions of the proposed dissertation can be summarised as follow. Firstly, several statistical and machine learning algorithms, plus techniques to improve these algorithms, are explored. Secondly, prediction modelling and pattern detection approaches for the first-episode psychosis associated with cannabis use are developed. Thirdly, a new computationally intensive machine learning framework for understanding the link between cannabis use and first-episode psychosis was introduced. Then, complementary and equally sophisticated prediction models for the first-episode psychosis associated with cannabis use were developed using artificial neural networks and deep learning within the proposed novel computationally intensive framework. Lastly, an efficient novel decision tree algorithm (PIDT) based on novel parameterised impurities and statistical pruning approaches is proposed and tested with several medical datasets. These contributions can be used to guide future theory, experiment, and treatment development in medical data mining, especially psychiatry.

A scalable decision tree system and its application in pattern recognition and intrusion detection

The identification of useful patterns from a medical dataset benefits early diagnosis. Classification techniques in data mining are famous for medical data prediction. Decision Tree (J48) and Navie Bayes are the most popular and frequently used algorithms in the field of prediction analysis. The efficiency of such prediction algorithms can be improved with better pre-processing approaches. This paper aims at finding optimum features using permutation combination of input data attributes for improving the classifier accuracy. The Pima Indian Diabetes Dataset from UCI repository is used for experimentation. The performance of J48 and Navie Bayes has been tested for different combination of features. Keywords: Diabetes; J48; Navie Bayes; Permutation

Data Mining is getting increasingly important for discovering association patterns for health service innovation and Customer Relationship Management (CRM) etc. Yet, there are deficits of existing data mining techniques. Since most of them perform a plain mining based on predefined schemata through the data warehouse as a whole, a re-scan must be done whenever new attributes are added. Secondly, an association rule may be true on a certain granularity but fail on a smaller one and vise verse. Last but not least, they are usually designed to find either frequent or infrequent rules.After a survey of a category of significant health services, we propose a data mining algorithm alone with a forest data structure to solve aforementioned weaknesses at the same time. At first, we construct a forest structure of concept taxonomies that can be used for representing the knowledge space. On top of it, the data mining is developed as a compound process to find the large-itemsets, to generate, to update and to output association rules that can represent services portfolio. After a set of benchmarks derived to measure the performance of data mining algorithms, we present the performance with respect to efficiency, scalability, information loss, etc. The results show that the proposed approach is better than existing methods with regard to the level of efficiency and effectiveness.