Transcript Neural Computing

Neural Networks
& a case with bankruptcy
prediction
By
Jinhwa Kim
Neural Computing: The Basics

2
Neural Computing is a problem solving
methodology that attempts to mimic
how human brain functions

Artificial Neural Networks (ANN)

A Field in Machine Learning
Neural Computing

Computing technology that mimic certain
processing capabilities of the human brain
Neural Computing = Artificial Neural Networks (ANNs)

Purpose of ANN is to simulate the thought process
of human brain

Inspired by the studies of human brain and the
nervous system
3
The Biology Analogy

Neurons: brain cells




4
Nucleus (at the center)
Dendrites provide inputs
Axons send outputs
Synapses increase or
decrease connection
strength and cause
excitation or inhibition of
subsequent neurons
Artificial Neural Networks (ANN)




5
A model that emulates a biological neural
network
Software simulations of the massively
parallel processes that involve processing
elements interconnected in a network
architecture
Originally proposed as a model of the human
brain’s activities
The human brain is much more complex
Artificial Neural Networks (ANN)
Three Interconnected Artificial Neurons
Biological
Soma
Dendrites
Axon
Synapse
Slow speed
Many neurons
(Billions)
6
Artificial
Node
Input
Output
Weight
Fast speed
Few neurons
(Dozens)
ANN Fundamentals

Components and Structure


“A network is composed of a number of processing elements
organized in different ways to form the network structure”
Processing Elements (PEs) – Neurons
Network


Structure of the Network

Figure 15.3
7
Collection of neurons (PEs) grouped in layers
Topologies / architectures – different ways to interconnect PEs
ANN Fundamentals

8
Figure 15.4
Learning in ANN
1.
2.
3.
Compute outputs
Compare outputs with
desired targets
Adjust the weights and
repeat the process
An Example
: Y = C*X
Find C iteratively
When X = 5, making Y = 10
1.
Set random value to C
2.
Increment/decrement C
until it reaches right
value
9
Neural Network Architecture

Feed forward Neural Network

10
Multi Layer Perceptron, - Two, Three, sometimes
Four or Five Layers
Testing







Test the network after training
Examine network performance: measure the
network’s classification ability
Black box testing
Do the inputs produce the appropriate outputs?
Not necessarily 100% accurate
But may be better than human decision makers
Test plan should include



11
Routine cases
Potentially problematic situations
May have to retrain
ANN Development Tools










12
NeuroSolutions
Statistica Neural Network Toolkit
Braincel (Excel Add-in)
NeuralWorks
Brainmaker
PathFinder
Trajan Neural Network Simulator
NeuroShell Easy
SPSS Neural Connector
NeuroWare
Benefits of ANN






13
Pattern recognition, learning, classification,
generalization and abstraction, and interpretation of
incomplete and noisy inputs
Character, speech and visual recognition
Can provide some human problem-solving
characteristics
Can tackle new kinds of problems
Fast prediction
Powerful hybrid systems
Limitations of ANN



14
Lack explanation capabilities
Limitations and expense of hardware
technology restrict most applications to
software simulations
Training time can be excessive and
tedious
ANN Demonstration

www.roselladb.com
NeuroSolutions
http://www.nd.com/neurosolutions/products/ns/nnandnsvideo.html

by NeuroDimentions, Inc.

www.nd.com




DMWizard
By Knowledge Based Systems, Inc.
Funded by US Army
www.roselladb.com
15
Business ANN Applications

Accounting



Finance










16
Identify tax fraud
Enhance auditing by finding irregularities
Signatures and bank note verifications
Foreign exchange rate forecasting
Bankruptcy prediction
Customer credit scoring
Credit card approval and fraud detection*
Stock and commodity selection and trading
Forecasting economic turning points
Pricing initial public offerings*
Loan approvals
…
Business ANN Applications

Human Resources



Management





Consumer spending pattern classification
Sales forecasts
Targeted marketing, …
Operations


17
Corporate merger prediction
Country risk rating
Marketing


Predicting employees’ performance and behavior
Determining personnel resource requirements
Vehicle routing
Production/job scheduling, …
A case study with NN(Neural Networks)
:Bankruptcy Prediction with NN

Based on a paper



NN Architecture



Published in Decision Support Systems, 1994
By Rick Wilson and Ramesh Sharda
Three-layer (input-hidden-output) MLP
Backpropagation (supervised) learning network
Training data


Small set of well-known financial ratios
Data available on bankruptcy outcomes

18
Moody’s industrial manual (between 1975 and 1982)
Bankruptcy Prediction with ANN

Application Design Specifics


Five Input Nodes
X1: Working capital/total assets
X2: Retained earnings/total assets
X3: Earnings before interest and taxes/total assets
X4: Market value of equity/total debt
X5: Sales/total assets
Single Output Node: Final classification for each firm



19
Bankruptcy or
Nonbankruptcy
Development Tool: NeuroShell
Bankruptcy Prediction with ANN
20
Bankruptcy Prediction with ANN

Training



Data Set: 129 firms
Training Set: 74 firms; 38 bankrupt, 36 not
Ratios computed and stored in input files for:



Parameters



Number of PEs
Learning rate and Momentum
Testing

Two Ways


21
The neural network
A conventional discriminant analysis program
Test data set: 27 bankrupt firms, 28 nonbankrupt firms
Comparison with discriminant analysis
Bankruptcy Prediction with ANN

Results

The neural network correctly predicted:



22
81.5 percent bankrupt cases
82.1 percent nonbankrupt cases
Accuracy of about 80 percent is usually
acceptable for this problem domain