Intelligent DecisionMaking Support Systems (iDMSS)

Dr. Saeed Shiry

Amirkabir University of Technology Computer Engineering & Information Technology Department

Introduction

An i-DMSS extends traditional DSS by incorporating techniques to supply intelligent behaviors and utilizing the power of modern computers to support and enhance decision making.

Intelligent System

Intelligent systems should be able to:

(i) learn or understand from experience; (ii) make sense out of ambiguous or contradictory messages; (iii) respond quickly and successfully to a new situation; (iv) use reasoning in solving problems and directing conduct effectively; (v) deal with perplexing situations; (vi) understand and infer in ordinary, rational ways; (vii) apply knowledge to manipulate the environment; (viii) think and reason; and (ix) recognize the relative importance of different elements in a situation.

Examples of Intelligent Algorithms

Artificial Neural Networks (ANN) Inductive Learning Case-based Reasoning and Analogical Reasoning Genetic Algorithms Fuzzy Logic

Neural Computing

Neural Computing is a problem solving methodology that attempts to mimic how our brains function.

Knowledge representations based on

Massive parallel processing Fast retrieval of large amounts of information The ability to recognize patterns based on historical cases

Neural Computing = Artificial Neural Networks (ANNs)

Artificial Neural Networks

ANN can help to automate complex decision making Neural networks learn from past experience and improve their performance levels Machine learning: Methods that teach machines to solve problems, or to support problem solving, by applying historical cases

Example: Loan Approval decision Making

Loan approval decision making use many variables: Customers income, employment history, credit history, outstanding debts, and so on. Capturing them in a software is difficult. Fast decision making on loans is beneficial: make decision while customer is still in the office! A neural network was trained to recognize patterns of successful and unsuccessful loans based on past history. The NN is fed with risk, the interest rate, customer data, and other variables. A NN can quickly recommend approval or denial of a loan. It can also detect Fraud.

Limitations of Neural Networks

Do not perform well at tasks that are not done well by people Lack explanation capabilities Limitations and expense of hardware technology restrict most applications to software simulations Training times can be excessive and tedious Usually requires large amounts of training and test data

Neural Network Fundamentals

Components and Structure

Processing Elements Network Structure of the Network

Processing Information by the Network

Inputs Outputs Weights Summation Function

Neural Network Application Development

ANN Application Development Process

Data Collection and Preparation

Collect data and separate into a training set and a test set

Use training cases to adjust the weights

Neural Network Preparation

Learning rate (high or low) Threshold value for the form of the output Initial weight values Other parameters

Choose the network's structure (nodes and layers) Select initial conditions Transform training and test data to the required format

Training the Network

Present the training data set to the network Adjust weights to produce the desired output for each of the inputs

Several iterations of the complete training set to get a consistent set of weights that works for all the training data

Testing

Test the network after training Examine network performance: measure the networks 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

Routine cases Potentially problematic situations

May have to retrain

Neural Computing Paradigms

Decisions the builder must make Size of training and test data Learning algorithms Topology: number of processing elements and their configurations Transformation (transfer) function Learning rate for each layer Diagnostic and validation tools

Results in the Network's Paradigm

NN Development Tools

Braincel (Excel Add-in) NeuralWorks Brainmaker PathFinder Trajan Neural Network Simulator NeuroShell Easy SPSS Neural Connector MatLab

Application and properties of Neural Networks

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 Robust Fast Flexible and easy to maintain Powerful hybrid systems

Neural Computing Use

Accounting Finance Human Resources Management Marketing Operations

Neural Network Credit Authorizer Construction Process

Step 1: Collect data

Step 2: Separate data into training and test sets

Step 5: Deploy developed network application

Bankruptcy Prediction with Neural Networks

Paradigm: Three-layer network, back-propagation Training data: Small set of well-known financial ratios Data available on bankruptcy outcomes Supervised network Training time not to be a problem

Application Design

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

Bankruptcy or Nonbankruptcy

Development Tool: NeuroShell

Architecture of the Bankruptcy Prediction Neural Network

Bankrupt 0

X3 Nonbankrupt 1

X4 X5

Results

ANN did better predicting 22 out of the 27 actual cases Discriminant analysis predicted only 16 correctly Error Analysis Five bankrupt firms misclassified by both methods Similar for nonbankrupt firms Neural network at least as good as conventional Accuracy of about 80 percent is usually acceptable for neural network applications

Stock Market Prediction System with Modular Neural Networks

Accurate Stock Market Prediction - Complex Problem Several Mathematical Models - Disappointing Results Fujitsu and Nikko Securities: TOPIX Buying and Selling Prediction System

The System

Input: Several technical and economic indexes Several modular neural networks relate past indexes, and buy / sell timing Prediction system

Modular neural networks Very accurate

Home Work 4
Read and write a summary for 2 papers out of following:

Following Paper From: Clinical Decision Support Systems intelligent Decision-making Support Systems Data Mining and Clinical Decision Support System Following paper from : Encyclopedia of Decision Making and Decision Support Technologies Neural Network Time Series Forecasting Using Recency Weighting

The Summary should be written in Persian. Hand over it to Papers TA by next week.