Browsing by Author "Muluneh, Tilahun"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Possible Application of Data Mining Techniques to Target Potential Visa Card Users in Direct Marketing (The Case Of Dashen Bank S.C.)
    (Addis Ababa University, 2009-01) Muluneh, Tilahun; VNV, Manoj (Professor)
    Identifying customers who are more likely to respond to a product offering is an important issue in direct marketing. In direct marketing, data mining has been used extensively to identify potential customers for a new product (target selection). The final goal of this thesis is to build a model that helps to classify the book customers of DASHEN BANK S.C, according to their expected response to the direct marketing campaign. Since there are no predefined classes, that describe the customers of the bank according to their expected response to visa card offer, the researcher uses a clustering techniques that resulted in the appropriate number of clusters. Then, a predictive response model was developed to predict the degree of likelihood (as high, medium and low) that a customer is going to respond to a visa card offer. This predictive model achieved accuracy of 96.14%. For modeling purpose customers' data was gathered from DASHEN BANK S.C. Since irrelevant or redundant features result in bad model performance, data preparation like attribute selection was performed in order to determine the inputs to the model. Thus various data mining techniques and algorithms were used to implement each step of the modeling process and alleviate related difficulties. K-Means was used as a clustering algorithm to segment customers’ record into clusters with similar characters. Different parameters were used to run the clustering algorithm before reaching at segments that made business sense. J48 decision tree algorithm was used for classification purpose. In addition to those attributes that are believed by the experts to have high impact on customers probability to be the potential customer of the visa card service, this research found the attributes “Occupation” and “Accommodation” to have a big influence. Moreover, with respect to the attribute “Age” a new pattern was found.Generally the result of the study was encouraging, which reinforce the possible application of data mining solution to the banking industry, particularly in direct marketing campaign at the DASHEN BANK S.C.
  • No Thumbnail Available
    Item
    Possible Application of Data Mining Techniques to Target Potential Visa Card Users in Direct Marketing (The Case of Dash En Bank S.C.)
    (Addis Ababa University, 2009-01) Muluneh, Tilahun; VNV, Manoj (Prof.)
    Identifying customers who are more likely to res pond to a product offering is an important issue in direct marketing. In direct marketing, data mining has been used extensively to identify potential customers for a new product (target selection) . The final goal of this thesis is to build a model that helps to classify the book customers o f DASH EN BAN K SC, according to their expected response to the direct marketing campaign. Since there are no predefined classes, that describe the customers of the bank according to their expected response to visa card offer, the researcher uses a clustering techniques that resulted in the appropriate number of clusters. Then, a predictive response model was developed to predict the degree of likelihood (as high, medium and low) that a customer is go in g to respond to a visa card offer This predictive mod el achieved accuracy o f 96. 14%. For modeling purpose customers' data was gathered fro m DASHEN BAN K S .c. Since irrelevant or redundant features result in bad model performance, data preparation like attribute selection was performed in order to determine the inputs to the mo del. Thus various data mining techniques and algorithms were used to implement each step of the Modeling process and alleviate related difficulties . K-M answers used as a clustering algorithm to segment customers ' record into clusters with similar characters . Different parameters we re used to run the clustering algorithm be fore reaching at segments that made business sense. J4 8 decision tree algorithm was used for classification purpose. In addition to those attributes that are believed by the expert s to have high impact on customers probability to be the potential customer of the visa card service, this research found the attributes " Occupation" and " Accommodation" to have a big influence. Moreover, with respect to the attribute " Age" a new pattern was found . Generally the result of the stud y was encouraging, which reinforce the possible application of Data mining solution to the banking in dusty , particularly in direct marketing campaign at the DASH EN BANK S,c.