1762 WordsMay 6, 20158 Pages

First of all, I would like to mention that it is more reasonable to compare the models that are based on the same data, so I tried to use the same variables and the same missing value treatment approach (excluding decision tree) to all of the models.
All the 3 models showed a performance of nearly the same quality, according to the various lift charts produced and presented in the further parts of the report.
However, the difference becomes more evident on the % captured response and the most efficient and useful model turns out to be the logistic regression model.
It is described in a greater detail in part 4 of this report.
This ROC plot indicates that the logistic regression is also efficient in terms of trade-off between sensitivity and specificity, however it is accompanied by the neural network this time.
In our case, the sensitivity is the proportion of bad customers predicted by the model, while specificity is the proportion of good customers predicted as bad customers.
Nonetheless, this logistic regression model has some limitations.
Missing values treatment – because the model does not treat missing values in the best way by default, you need to be careful with determining the method of treatment by yourself.
This logistic regression model is not very good at showing relationships between variables, so during the preliminary analysis stage, other software programmes were used to assist in this.
As no model can ensure the 100% sensitivity, this model can

Related

## Linear Regression Model

1029 Words | 5 PagesDue in class Feb 6 UCI ID_____________________________ MultipleChoice Questions (Choose the best answer, and briefly explain your reasoning.) 1. Assume we have a simple linear regression model: . Given a random sample from the population, which of the following statement is true? a. OLS estimators are biased when BMI do not vary much in the sample. b. OLS estimators are biased when the sample size is small (say 20 observations)

## Regression Model Essay

1120 Words | 5 Pages1. Qeach brand t=β0+β1*PMinute Maid t+β2*PTropicana t+β3*PPrivate label t+ueach brand t Q: quantity P: price By running the above regression model for each brand, we got the following elasticity matrix and the figures for “V” and “C.” Note that we used the average price and quantity for P and Q to calculate each brand’s elasticity. Price Elasticity | Tropicana | Minute Maid | Private Label | Tropicana | -3.4620441 | 0.40596537 | 0.392997566 | Minute Maid | 1.8023329 | -4.26820251 | 0.765331803

## The Presidential Model Of The United States

985 Words | 4 Pagesas opposed to the presidential model of the United States might solve problem of having a low approval of the government. In the US we have the presidential model. The presidential model has single head of state that is the face of the country, plays a very small role in day to governing of the country and head of government who actually runs the government, executive that is responsible for day to day governing of a particular society. In the case of United States, President Barack Obama holds both

## Analysis on Inflation Regression Model

5737 Words | 23 PagesAnalysis on Inflation Regression Model Done by: Hassan Kanaan & Fahim Melki Presented to: Dr. Gretta Saab Due on: Tuesday, January 25, 2011 Outline: I. Introduction A. Definition of Variables B. Type of Variables II. Background and Literature Review A. Inflation and Unemployment B. Inflation and Oil Prices C. Inflation and GDP D. Inflation and Money Supply III. Analysis A. SPSS 17 analysis B. E-Views 5 analysis IV. Conclusion and Recommendation V. Indexes

## Stages Of Hierarchical Multiple Regression Model

1343 Words | 6 Pageshierarchical multiple regression was conducted with Partner’s Body Type as the dependent variable. Age was entered at stage one of the regression and Body Type and Relationship Status were entered at stage two. The variables were entered in this order since people are more likely to be in a relationship as they get older, thus we wanted to determine if the other variables had a unique contribution that was not already accounted for by age. The hierarchical multiple regression revealed that at stage

## The Health Belief Model Of The United States

1367 Words | 6 Pages3. Overview of the Health Belief Model The Health Belief model is a psychological construct that is used to predict health behavior (see Figure 1). The two components of the model that are used to predict behavior are the perception of the threat and the perception of the benefits and barriers to taking action to reduce the threat. The perception of the threat is composed of two elements: the perception of seriousness of the threat and the perception of the susceptibility to the threat (Sharafkhani

## My Regression Model Is A Simple Additive Linear Regression

1475 Words | 6 Pageslegislators in a state legislator was to see if states have to pick and choose: more minority legislators or more women legislators, based on the way candidates get elected according to the state rules. I would expect to see that states with more black legislators have fewer women legislators and vice versa. My regression model is a simple additive linear regression. I use one dummy variable (South). The rest of my variables are numeric, or percentages. I expect the regressions to show a positive

## Multiple Regression Model Essay

2133 Words | 9 PagesProject: Multiple Regression Model Introduction Today’s stock market offers as many opportunities for investors to raise money as jeopardies to lose it because market depends on different factors, such as overall observed country’s performance, foreign countries’ performance, and unexpected events. One of the most important stock market indexes is Standard & Poor's 500 (S&P 500) as it comprises the 500 largest American companies across various industries and sectors. Many people put

## The Simple Linear Regression Model

1243 Words | 5 Pageslinear regression model; throughout two variables, the predictor variable (independent) and one response variable (dependent) will be used to explain the models. In so doing, it explains the underlying assumptions when fitting both variables into models and statistical tools. In addition to findings from statistical analyses, this report communicates in clear terms the significance of data on the retention rate (%) and the graduation rate (%) for the sample of 29 online colleges in the United States

## Project Complexity Based On A Multiple Regression Model Essay

1436 Words | 6 Pagesrequired to develop a project of average project complexity, based on the adjustment method, which is based on a multiple regression model. Project complexity: the complexity of project developed measured based on different factors that incorporates, platform design, body style, and powertrain into overall index (European projects had the highest complexity index overall, while united states and Japanese projects decreased complexity) Adjusted engineering hours: the number of hours required to develop a

### Linear Regression Model

1029 Words | 5 Pages### Regression Model Essay

1120 Words | 5 Pages### The Presidential Model Of The United States

985 Words | 4 Pages### Analysis on Inflation Regression Model

5737 Words | 23 Pages### Stages Of Hierarchical Multiple Regression Model

1343 Words | 6 Pages### The Health Belief Model Of The United States

1367 Words | 6 Pages### My Regression Model Is A Simple Additive Linear Regression

1475 Words | 6 Pages### Multiple Regression Model Essay

2133 Words | 9 Pages### The Simple Linear Regression Model

1243 Words | 5 Pages### Project Complexity Based On A Multiple Regression Model Essay

1436 Words | 6 Pages