CREDIT SCORING. Your Overdraw Limit and our continued approval of your Requests for a Facility will be determined by your credit score. Your credit score will be assessed based on various matters including the information obtained from your use of Safaricom Services and the KCB M-PESA Service, M- Shwari Service and repayment history on your existing Overdraw Limit.
CREDIT SCORING. Your new limit will be awarded at the sole discretion of NCBA, as determined by your credit score. Your credit score will be assessed based on various factors including, but not limited to, your use of M- Pesa, the Services and your repayment history.
CREDIT SCORING. 10.1 The Customer’s Revolving Credit Facility Limit and Momentum’s continued approval of the Customer’s Requests for access to the Revolving Credit Facility funds will be determined by the Customer’s credit score or by any other means as Momentum deems fit from time to time at its sole discretion.
CREDIT SCORING. 10.1 You acknowledge and agree that details of your name, address and payment record may be submitted to a credit reference agency, and data in relation to you will be processed by and on behalf of us in connection with the site-works to help us to make decisions about your ability to pay for the site-works and supply of gas and/or electricity to your site(s). If you want to see what information the credit reference agencies hold about you, please contact them directly.
CREDIT SCORING. 15.1 The Dealer’s Facility Limit and Momentum’s continued approval of the Dealer’s Requests will be determined by the Dealer’s credit score or by any other means as Momentum deems fit from time to time at its sole discretion.
CREDIT SCORING. 5.2.1. Credit Scoring and provision of M-Pesa Merchant Loan Limit will be based on a score provided by the Bank Credit Scoring Engine embedded in the Loan Management Platform.
CREDIT SCORING. 9.1 The Customer’s Ezua Chapaa facility Limit and Momentum’s continued approval of the Customer’s Requests for access to the Ezua Chapaa facility funds will be determined by the Customer’s credit score or by any other means as Momentum deems fit from time to time at its sole discretion.
CREDIT SCORING. 9.1 The Customer’s Revolving Credit Facility Limit and PCUL’s continued approval of the Customer’s Requests for access to the Revolving Credit Facility funds will be determined by the Customer’s credit score or by any other means as PCUL deems fit from time to time at its sole discretion.
CREDIT SCORING. Generally, the following provisions relating to credit scoring will be followed by BNB USA. These provisions, however, may be modified by BNB USA over the term of the Agreement.
CREDIT SCORING. In example 1 we analyze a dataset containing information on 1000 consumers’ credits from a South German bank with a generalized additive model. The aim is to predict the probability that a client with certain covariates or risk factors will not pay back his credit. Therefore the response variable is the binary variable creditability (named y in the dataset) with y = 0 for creditworthy clients and y = 1 for not creditworthy clients. As covariates we have two continuous variables and 5 categorial variables (in effect coding) which are described in Table 1. Variable Description duration duration of the credit in months amount amount of credit in 1000DM account1 running account of the client with categories ”no running account” (account1=1), account2 ”good running account” (account2 = 1) and ”medium running account” (account1 = account2 = −1) payment payment of previous credits with categories ”good” (= 1) and ”bad” (= −1) intuse intended use with categories ”private” (= 1) and ”professional” (= −1) marstat marital status with categories ”married” (= 1) and ”living alone” (= −1) Table 1: Covariates in the credit scoring dataset. To analyze the data, we first define ggamm in the current session and store the data in a dataframe- object. > source("c:\\ggamm\\functions\\helpfunctions.r") > source("c:\\ggamm\\functions\\ggamm.r") > creditdata<-read.table("c:\\ggamm\\examples\\credit.raw",header=T) To make the names of the variables available directly, we attach the dataframe: > attach(creditdata) Now we combine the covariates that are to be modelled as P-splines and the categorial covariates in two different matrices: > smoothcovs<-cbind(duration,amount) > catcovs<-cbind(account1,account2,payment,intuse,marstat) Finally we call ggamm and store the estimation results in the object credit: > credit<-ggamm(dep=y,fix=catcovs,smooth=smoothcovs,family="binomial") As a result of this call, the following information is given on the screen: iteration: 1 relative changes in the regression coefficients: Inf relative changes in the variance parameters: 0.7858781 . iteration: 11 relative changes in the regression coefficients: 2e-006 relative changes in the variance parameters: 5.8e-006 variance of smooth1: 0.0045697637 variance of smooth2: 0.0156629498 beta0: -0.25677 beta1: -1.09241 beta2: 0.86104 beta3: -0.49619 beta4: -0.21911 beta5: -0.25864 In each iteration of the estimation process the relative changes in the parameters are computed and compared with the (possibly user...
