P. Adeodato, G. C. Vasconcelos, A. L. Arnaud, Rodrigo C. L. V. Cunha, Domingos S. M. P. Monteiro, R. Neto
This article presents an efficient solution for the PAKDD-2007 Competition cross-selling problem. The solution is based on a thorough approach which involves the creation of new input variables, efficient data preparation and transformation, adequate data sampling strategy and a combination of two of the most robust modeling techniques. Due to the complexity imposed by the very small amount of examples in the target class, the approach for model robustness was to produce the median score of the 11 models developed with an adapted version of the 11-fold cross-validation process and the use of a combination of two robust techniques via stacking, the MLP neural network and the n-tuple classifier. Despite the problem complexity, the performance on the prediction data set (unlabeled samples), measured through KS2 and ROC curves was shown to be very effective and finished as the first runner-up solution of the competition.
{"title":"The Power of Sampling and Stacking for the PAKDD-2007 Cross-Selling Problem","authors":"P. Adeodato, G. C. Vasconcelos, A. L. Arnaud, Rodrigo C. L. V. Cunha, Domingos S. M. P. Monteiro, R. Neto","doi":"10.4018/jdwm.2008040104","DOIUrl":"https://doi.org/10.4018/jdwm.2008040104","url":null,"abstract":"This article presents an efficient solution for the PAKDD-2007 Competition cross-selling problem. The solution is based on a thorough approach which involves the creation of new input variables, efficient data preparation and transformation, adequate data sampling strategy and a combination of two of the most robust modeling techniques. Due to the complexity imposed by the very small amount of examples in the target class, the approach for model robustness was to produce the median score of the 11 models developed with an adapted version of the 11-fold cross-validation process and the use of a combination of two robust techniques via stacking, the MLP neural network and the n-tuple classifier. Despite the problem complexity, the performance on the prediction data set (unlabeled samples), measured through KS2 and ROC curves was shown to be very effective and finished as the first runner-up solution of the competition.","PeriodicalId":399104,"journal":{"name":"Strategic Advancements in Utilizing Data Mining and Warehousing Technologies","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123170394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.4018/978-1-60566-717-1.CH021
Dehong Qiu, Ye Wang, Qifeng Zhang
The rapid growth in information science and technology has lead to generation of huge amount of valuable data in many areas. In finance for example, over the past five years, many banks have experienced exceptional growth in service and have built up bank’s Group Data Warehouse. In order to realize faster, more effective decisions and provide more excellent customer services, new technologies to handle or extract fully the latent knowledge within the data are urgently required. The finance company that donated the data for 2007 PAKDD competition would like to build a cross-selling model to predict the potential take-ups of cross-selling home loans to its credit card customers (Qiu, Wang & Bi, 2008). abstract
随着信息科学技术的飞速发展，在许多领域产生了大量有价值的数据。以金融为例，在过去五年中，许多银行在服务方面取得了非凡的增长，并建立了银行的集团数据仓库。为了实现更快、更有效的决策，提供更优质的客户服务，迫切需要处理或充分提取数据中潜在知识的新技术。为2007年PAKDD竞赛提供数据的金融公司希望建立一个交叉销售模型，以预测向其信用卡客户交叉销售住房贷款的潜在占有率(Qiu, Wang & Bi, 2008)。摘要
{"title":"Selecting Salient Features and Samples Simultaneously to Enhance Cross-Selling Model Performance","authors":"Dehong Qiu, Ye Wang, Qifeng Zhang","doi":"10.4018/978-1-60566-717-1.CH021","DOIUrl":"https://doi.org/10.4018/978-1-60566-717-1.CH021","url":null,"abstract":"The rapid growth in information science and technology has lead to generation of huge amount of valuable data in many areas. In finance for example, over the past five years, many banks have experienced exceptional growth in service and have built up bank’s Group Data Warehouse. In order to realize faster, more effective decisions and provide more excellent customer services, new technologies to handle or extract fully the latent knowledge within the data are urgently required. The finance company that donated the data for 2007 PAKDD competition would like to build a cross-selling model to predict the potential take-ups of cross-selling home loans to its credit card customers (Qiu, Wang & Bi, 2008). abstract","PeriodicalId":399104,"journal":{"name":"Strategic Advancements in Utilizing Data Mining and Warehousing Technologies","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129487998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.4018/978-1-60566-098-1.ch019
Gerasimos Marketos, Y. Theodoridis, I. Kalogeras
Earthquake data composes an ever increasing collection of earth science information for post-processing analysis. Earth scientists, local or national administration officers and so forth, are working with these data collections for scientific or planning purposes. In this article, we discuss the architecture of a so-called seismic data management and mining system (SDMMS) for quick and easy data collection, processing, and visualization. The SDMMS architecture includes, among others, a seismological database for efficient and effective querying and a seismological data warehouse for OLAP analysis and data mining. We provide template schemes for these two components as well as examples of their functionality towards the support of decision making. We also provide a comparative survey of existing operational or prototype SDMMS.
{"title":"Seismological Data Warehousing and Mining","authors":"Gerasimos Marketos, Y. Theodoridis, I. Kalogeras","doi":"10.4018/978-1-60566-098-1.ch019","DOIUrl":"https://doi.org/10.4018/978-1-60566-098-1.ch019","url":null,"abstract":"Earthquake data composes an ever increasing collection of earth science information for post-processing analysis. Earth scientists, local or national administration officers and so forth, are working with these data collections for scientific or planning purposes. In this article, we discuss the architecture of a so-called seismic data management and mining system (SDMMS) for quick and easy data collection, processing, and visualization. The SDMMS architecture includes, among others, a seismological database for efficient and effective querying and a seismological data warehouse for OLAP analysis and data mining. We provide template schemes for these two components as well as examples of their functionality towards the support of decision making. We also provide a comparative survey of existing operational or prototype SDMMS.","PeriodicalId":399104,"journal":{"name":"Strategic Advancements in Utilizing Data Mining and Warehousing Technologies","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123414004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.4018/978-1-60566-717-1.CH017
Hualin Wang, Xiaogang Su
The 11th Pacific-Asia Knowledge Discovery and Data Mining Conference (PAKDD 2007) hosted a data mining competition, co-organized by the Singapore Institute of Statistics. The data set is from a consumer finance company with the aim of finding solutions for a cross-selling business problem. The company currently has two databases, one for credit card holders and the other for home loan (mortgage) customers and they would like to make use of this opportunity to cross-sell home loans to its credit card holders. Thus, it is of their keen interest to have an effective scoring model for predicting potential cross-sell take-ups. The training dataset contains information on 40,700 customers with 40 input variables, most of which are related to the point of application for the company’s credit card, plus a binary target variable indicating the home loan take-up status. This is a sample of customers who opened a new credit card with the company within a specific 2-year period and did not have an existing home loan with the company. The binary target variable has a value of 1 if the customer then opened a home loan with the company within 12 months after opening the credit abstract
{"title":"Bagging Probit Models for Unbalanced Classification","authors":"Hualin Wang, Xiaogang Su","doi":"10.4018/978-1-60566-717-1.CH017","DOIUrl":"https://doi.org/10.4018/978-1-60566-717-1.CH017","url":null,"abstract":"The 11th Pacific-Asia Knowledge Discovery and Data Mining Conference (PAKDD 2007) hosted a data mining competition, co-organized by the Singapore Institute of Statistics. The data set is from a consumer finance company with the aim of finding solutions for a cross-selling business problem. The company currently has two databases, one for credit card holders and the other for home loan (mortgage) customers and they would like to make use of this opportunity to cross-sell home loans to its credit card holders. Thus, it is of their keen interest to have an effective scoring model for predicting potential cross-sell take-ups. The training dataset contains information on 40,700 customers with 40 input variables, most of which are related to the point of application for the company’s credit card, plus a binary target variable indicating the home loan take-up status. This is a sample of customers who opened a new credit card with the company within a specific 2-year period and did not have an existing home loan with the company. The binary target variable has a value of 1 if the customer then opened a home loan with the company within 12 months after opening the credit abstract","PeriodicalId":399104,"journal":{"name":"Strategic Advancements in Utilizing Data Mining and Warehousing Technologies","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114387621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.4018/978-1-60566-717-1.CH009
M. Khabbaz, K. Kianmehr, Mohammed Al-Shalalfa, R. Alhajj
This chapter takes advantage of using fuzzy classifier rules to capture the correlations between genes. The main motivation to conduct this study is that a fuzzy classifier rule is essentially an “if-then” rule that contains linguistic terms to represent the feature values. This representation of a rule that demonstrates the correlations among the genes is very simple to understand and interpret for domain experts. In this proposed gene selection procedure, instead of measuring the effectiveness of every single gene for building the classifier model, the authors incorporate the impotence of a gene correlation with other existing genes in the process of gene selection. That is, a gene is rejected if it is not in a significant correlation with other genes in the dataset. Furthermore, in order to improve the reliability of this approach, the process is repeated several times in these experiments, and the genes reported as the result are the genes selected in most experiments. This chapter reports test results on five datasets and analyzes the achieved results from biological perspective. DOI: 10.4018/978-1-60566-717-1.ch009
{"title":"An Integrated Framework for Fuzzy Classification and Analysis of Gene Expression Data","authors":"M. Khabbaz, K. Kianmehr, Mohammed Al-Shalalfa, R. Alhajj","doi":"10.4018/978-1-60566-717-1.CH009","DOIUrl":"https://doi.org/10.4018/978-1-60566-717-1.CH009","url":null,"abstract":"This chapter takes advantage of using fuzzy classifier rules to capture the correlations between genes. The main motivation to conduct this study is that a fuzzy classifier rule is essentially an “if-then” rule that contains linguistic terms to represent the feature values. This representation of a rule that demonstrates the correlations among the genes is very simple to understand and interpret for domain experts. In this proposed gene selection procedure, instead of measuring the effectiveness of every single gene for building the classifier model, the authors incorporate the impotence of a gene correlation with other existing genes in the process of gene selection. That is, a gene is rejected if it is not in a significant correlation with other genes in the dataset. Furthermore, in order to improve the reliability of this approach, the process is repeated several times in these experiments, and the genes reported as the result are the genes selected in most experiments. This chapter reports test results on five datasets and analyzes the achieved results from biological perspective. DOI: 10.4018/978-1-60566-717-1.ch009","PeriodicalId":399104,"journal":{"name":"Strategic Advancements in Utilizing Data Mining and Warehousing Technologies","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130570141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：