Predict ‘kicks’ or bad purchases using Carvana – Cleaned and Sampled.jmp file. Create a validation data set with 50% of the data. Use Decision Tree, Regression and Neural Network approached for building predictive models. Perform a comparative analysis of the three competing models on validation data set. Write down your final conclusions on which model performs the best, what is the best cut-off to use, and what is the ‘value-added’ from conducting predictive modeling? Upload the saved file with the assignment. I created 6 models for this project, which are DT1, DT2, Reg1, Reg2, Reg3, and NN. After testing, the parameters I used to predict “IsBadBuy” in all my models are: PurchDate, Auction, VehicleAge, Transmission, WheelType, VehOdo, All “MMRs”, VehBCost, IsOnlineSale, and WarrantyCost. Those parameters together can help me get better models (i.e. ROC Area > 0.7) I used the cut-off of 0.6, because after trying out other cut-offs such as 0.5, 0.7, and 0.8, the results were either “I’m eliminating too many Good Buys”, or “I’m accepting too many Bad Buys”. As we know, both of the situations will affect the business (i.e. if we want stronger confident of the model, we will have too many 0s in the result, which means we may accept more Bad Buys in accident). Finally, I decided to use 0.6 as my cut-off to balance the situation. The best model I chose is Reg2 (Forward regression model). I have two reasons: First, Reg2 has the largest ROC Area in the Logistic Fit compression (Saved as “Lodistic1~6”), which is 0.7478; Second, it has a relatively low (the second smallest) number in the FalseNegative box from the Contingency Table among all models. For my second reason, I didn’t use overall accuracy because I think the FalseNegative will damage the business more than FalsePossitive does. Because accidentally having a BadBuy will cost the company to do all require and fix job. For the Value-added calculation, as we can see in the Contingency tables (Saved as...

...SEGMENTATION WITH NEURALNETWORK
B.Prasanna Rahul Radhakrishnan
Valliammai Engineering College Valliammai Engineering College
prakrish_2001@yahoo.com krish_rahul_1812@yahoo.com
Abstract:
Our paper work is on Segmentation by Neuralnetworks. Neuralnetworks computation offers a wide range of different algorithms for both unsupervised clustering (UC) and supervised classification (SC). In this paper we approached an algorithmic method that aims to combine UC and SC, where the information obtained during UC is not discarded, but is used as an initial step toward subsequent SC. Thus, the power of both image analysis strategies can be combined in an integrative computational procedure. This is achieved by applying “Hyper-BF network”. Here we worked a different procedures for the training, preprocessing and vector quantization in the application to medical image segmentation and also present the segmentation results for multispectral 3D MRI data sets of the human brain with respect to the tissue classes “ Gray matter”, “ White matter” and “ Cerebrospinal fluid”. We correlate manual and semi automatic methods with the results.
Keywords: Image analysis, Hebbian learning rule, Euclidean metric, multi spectral image segmentation, contour tracing.
Introduction:
Segmentation can be defined as the identification of...

...Group 2
Forest Cover Type
Prediction
ATUL JENA
RAJAT JAIN
SAHIL LALWANI
SAGNIK MAZUMDER
SHRADHA SANTUKA
Business Problem
To predict the forest cover type (the predominant kind of tree
cover) from strictly cartographic variables (as opposed to
remotely sensed data)
7 Cover types
Spruce/f
r
Lodgepol
e Pine
Ponderos
a Pine
Cottonwo
od/
Willow
Aspen
DouglasFir
Krummh
olz
Getting familiar with data
The source
Forest Cover data
set
Training set
15120
observation
s
Test set
565892
observation
s
Getting familiar with data
Description of attributes
40 soil types ( 0= absence or 1= presence )
Elevation, Aspect
Slope
4 areas of wilderness ( 0= absence or 1= presence )
Horizontal distance to Hydrology and Vertical distance to hydrology
HIllshade (9am/noon/3pm)
Horizontal distance to roadways
Horizontal distance to firepoints
Pre-Processing
Filter:
Excludes certain observations such as extreme outliers and errant data
Default filtering method: standard deviation from mean
Cut-off was set to 3 standard deviation (1637 observations filtered)
Data partition
Partition allocation:
Training 70% Validation 30% Test 0%
No. of observations:
Training 9433
Validation 4050
Pre-Processing (contd.)
Transformation
Used to stabilise variance, remove non-linearity, improve additivity and
counter non-normality
Default method: Maximum normal
Reduces skewness
Variable selection
Helps reduce the number of...

...creating decision trees on the laptop, I started to inform myself about possible supporting tools that can be used. As I am using an Apple MacBook, I found out that the software “XMind” cannot just help for drawing decision trees, but also for developing flowing charts, mind maps or to-do-lists. I thought about using Microsoft Excel as a tool for sorting the data. However, I finally looked up the necessary information in the given table without using any automatic sorting function, as for me, it was easier to manually type the data into MS Excel.
After installing the software and reading the task description, I realized that the tool is pretty easy to use and that it is very helpful in structuring information, as I will explain later on in this write-up. When creating the decisiontree I started with entering the existing data. By analyzing the data in a first view you can directly see that the first and last name does not have any influence on the loan grant respectively the loan amount, which seems to be self-explaining. It makes sense to start with the node with the highest number of different characteristics. This way the tree will become clearer. That’s why I started with the distinction of the age and afterwards chronologically with the loan type, the ability to pay and finally the past payment record. The loan amount that already includes the information whether a loan was granted (loan amount...

...DecisionTree Analysis
Choosing Between Options
by Projecting Likely Outcomes
Decision Trees are useful tools for helping you to choose between several courses of action.
They provide a highly effective structure within which you can explore options, and investigate the possible outcomes of choosing those options. They also help you to form a balanced picture of the risks and rewards associated with each possible course of action. This makes them particularly useful for choosing between different strategies, projects or investment opportunities, particularly when your resources are limited.
How to Use the Tool
You start a DecisionTree with a decision that you need to make. Draw a small square to represent this on the left hand side of a large piece of paper, half way down the page. From this box draw out lines towards the right for each possible solution, and write a short description of the solution along the line. Keep the lines apart as far as possible so that you can expand your thoughts.
At the end of each line, consider the results. If the result of taking that decision is uncertain, draw a small circle. If the result is another decision that you need to make, draw another square. Squares represent decisions, and circles represent uncertain outcomes. Write the decision or factor above the square or circle. If you have...

...day to day job of a Network Manager at Bellsouth there are many decisions which have to be made. One such decision opportunity arose about one week ago. The question was what to do with a major cable which is in the way of a guard rail that the Department of Transportation is installing. In this paper, the decision on what to do with this cable will be solved using a decisiontree. The discussion will include the major factors involved in making the decision and also show how the final decision was made.
Decisiontree
The decisiontree is an effective way to make a business decision; because you can write out multiple alternatives and different options that will go along with these alternatives. To show how effective the decisiontree is, this paper will demonstrate how a Network Manager at Bellsouth will handle a situation that has come about due to the Department of Transportation (DOT) needing to add a guardrail to a road in which a major cable is in the way.
When using a decisiontree one should start with the question, which in this case is what to do with the major cable. Then branch out from there with at least two options of what to do next. In this case there are three options: one would be to work with the...

...ARTIFICIAL NEURALNETWORKS
ABSTRACT:
“Human Brain,” the most intelligent device on the Earth, is the driving force the ever progressive nature of the Human Species. This is only the reason why _Homo sapien_ has built variety of intelligent devices like supercomputers which can do billions and trillions of calculations each second. But still Human is not able to build a device which can actually mimic its brain. This idea of imitating human brain gave a new area of research known as Artificial NeuralNetworks (ANN).
INTRODUCTION:
The vision of making a device which could think like the human mind has always been the part of Science Fiction since time immemorial. In this process the first unforgettable breakthrough came with the concept of ‘The Analytical Engine’ which was developed by Charles Babbage in the mid 19th century. Since then the evolution of computers has taken various leaps. Today in the 21st century we are working with Supercomputer. The moulding of a simple calculator into a Supercomputer has been very startling. But still we have not completely achieved the main objective. This is a reference to Artificial NeuralNetwork which is altogether an emerging field.
WHAT IS AN ARTIFICIAL NEURALNETWORK?
The only NeuralNetwork we are aware of as of now is the Brain. Human is on his path to develop such a system...

...ARTIFICIAL NEURALNETWORK: USE IN MANAGEMENT
Neuron Transfer Function:
The transfer function of a neuron is chosen to have a number of properties which either enhance or simplify the network containing the neuron. Crucially, for instance, any multilayer perceptron using a linear transfer function has an equivalent single-layer network; a non-linear function is therefore necessary to gain the advantages of a multi-layernetwork. Types of neuron transfer function
• Pure Linear Transfer Function
• Hard Limit Transfer Function
• Log Sigmoid Transfer Function
NeuralNetwork Structures:
• Feed Forward Network - Information flow is unidirectional, information processing is parallel, memory less, cannot modify output based on error
• Recurrent ( or feedback) Network – Information travelling in both directions, learn from mistakes, dynamic in nature
• Feed Forward Back Propagation Network
How ANN Functions?
ANN functions through learning. Like human beings, ANN works by learning from its past experiences and mistakes. ANN is inspired by the learning processes that take place in biological systems.
utomating this are:
• Saving quality time
• Saving resources in terms of human resources and finance
• Eliminating human error
• Leveraging technology
• Having fairness in the process
The framework proposed extracts data from...

...Linear programming is a modeling technique that is used to help managers make logical and informed decisions. All date and input factors are known with certainty. Linear program models are developed in three different steps:
Formulation
Solution
Interpretation
The formulation step deals with displaying the problem in a mathematical form. Once that is developed the solution stage solves the problem and finds the variable values. During the interpretation stage the sensitivity analysis gives managers the opportunity to answer hypothetical questions regarding the solutions that are generated.
There are four basic assumptions of linear programming and they are as follows:
Certainty
Proportionality
Additivity
Divisibility
Linear programming is the development of modeling and solution procedures which employ mathematical techniques to optimize the goals and objectives of the decision-maker. Programming problems determine the optimal allocation of scarce resources to meet certain objectives. Linear Programming Problems are mathematical programming problems where all of the relationships amongst the variables are linear.
Components of a LP Formulation are as follows:
Decision Variables
Objective Function
Constraints
Non-negativity Conditions
Decision variables represent unknown quantities. The solutions for these terms are what we would like...