Artificial Intelligence and Decision Support Systems

Genetic Algorithms

Intelligent Agents

• An artificial intelligence system that can move around your network performing repetitive tasks independently, adapting itself to your preferences
• An intelligent agent is like a travel agent in that it performs tasks that you stipulate

Artificial Intelligence

&

Decision Support Systems

• An AI system that mimics the survival-of-the-fittest process to generate better solutions
• They are used by business executives to help them decide which combination of projects a firm should invest in
• Used in the garment industry to help solve the problem of laying out pieces of the garment and cutting fabric to ensure as little waste as possible.
• Used to determine the optimal configuration of fiber optic cable in a network that may include as many as 100,000 connection points
• Three evolutionary phases : selection, cross-over and mutation

FOUR TYPES OF INTELLIGENT AGENTS

• Buyer agents or shopping bots
• User or personal agents
• Monitoring-and-surveillance or predictive agents
• Data-mining agents

Uses of DSS

Expert Systems

Introduction

Decision Support Systems

Example of Expert System

• Decide where to spend advertising dollars
• Forecast market and sales trends
• Analyze consumer behavior
• Analyze drug interactions
• Develop airline schedules
• Price products

Conclusion

• Also called “knowledge-based systems” or “performance support systems”
• Captures human expertise and then applies reasoning capabilities to problems and offers advice in the form of a conclusion
• Useful for:

1. Diagnostic or “what’s wrong” problems

2. Prescriptive or “what should we do” problems

• A highly flexible and interactive system that is designed to support decision making when the problem is not structured
• Decision support systems help you analyze, but you must know how to solve the problem, and how to use the results of the analysis

• Decision making plays a key role in managerial work.
• Managers often have to consider large amounts of data, extract and synthesize only relevant information, and make decisions that will benefit the organization.
• As the amount of available data grows, so does the need for computer-based aids to assist managers in their decision-making process.

Components of DSS

IT can help you be an effective decision maker by assisting you in decision-making tasks with:

• Decision support systems (DSS)
• Group decision support systems (GDSS)
• Geographic information systems (GIS)

DSS Vs Expert Systems

COMPUTER-AIDED DECISION SUPPORT

• Data Management - allows you to store and access information i.e., data warehouse or relational database
• Model Management - allows you to store and access models i.e., ANOVA or regression analysis
• User Interface Management - allows you to easily manipulate, ask questions, and interpret responses of models i.e., Microsoft Excel, SPSS, STORM, in-house

ADVANCED FORMS OF DSS:

• GDSS (Group Decision Support Systems)
• GIS (Geographic Information Systems)

A DSS augments or assist you in making the decision, but you must know how to reason through the problem and proceed

An Expert System only requires that you input the facts and symptoms of the problem – it contains the know-how for solving the problem (based on human expertise)

IT can help you be an effective decision maker by performing tasks for you with AI using:

• Expert systems
• Neural networks
• Genetic algorithms
• Intelligent agents

People in an Expert System

• Domain Expert
• The person who knows how to solve the problem without the aid of IT
• Sometimes called SMEs (subject matter experts)
• Knowledge Engineer
• The person who builds the expert system
• Knowledge Worker
• The person who uses the expert system to solve a problem

IT in an Expert System

Thank

You !

Types of Decisions

Artificial Intelligence

This is

• Knowledge base
• Stores the rules of the expert system
• Knowledge acquisition
• Used to capture and enter the rules
• Inference engine
• Takes the problem facts and searches the knowledge base for rules that fit
• User interface
• Used to run the consultation

Brian Rego

Sireesha Yakkali

Aditya Das

Renu Aggarwal

Krutika Reddy

Agenda

• Whereas DSS systems augment business brain power, AI imitates human thinking and behavior
• Robots are a form of AI: Mechanical devices equipped with simulated human senses and the capability of taking action on its own
• Eg.-a robot lawn mower, called the Lawn-Nibbler, cuts your lawn intelligently avoiding obstacles

signing off !

STRUCTURED DECISIONS

• Set of steps that if followed in a particular way will always yield the correct answer
• Doesn’t involve any feel or intuition
• Easily programmed – inputs, processing, outputs

NON-STRUCTURED DECISIONS

• One for which there are no rules or criteria that will guarantee a good solution
• Usually have several “right” answers
• Both controllable and uncontrollable variables

• Decision Support Systems
• Artificial Intelligence
• Expert systems
• Neural networks
• Genetic algorithms
• Intelligent agents

RECURRING DECISIONS

• One that happens repeatedly and, often, periodically (daily, monthly, annually)
• Usually based on the same set of rules each time

NON-RECURRING DECISIONS

Ad-hoc or one that you make infrequently

• Usually based on different criteria for determining the best solution each time

Phases of Decision Making

Neural Networks

Types of AI systems used in business

• A type of AI system capable of learning because it’s patterned after the human brain
• In business, they are used in: securities trading, credit-card fraud detection, real estate appraisal, evaluating loan applications, target marketing, etc.

• Intelligence – find or recognize a problem, need, or opportunity
• Design – consider possible ways of solving the problem
• Choice – weigh the merits of each solution
• Implementation – carry out the solution

They can

• Expert systems
• Neural networks
• Genetic algorithms
• Intelligent agents

What Expert Systems Can Do

Uses of Artificial Intelligence

• Handle massive amounts of information
• Reduce errors
• Reduce costs
• Improve customer service
• Provide consistency in decision making
• Maintain an organization’s knowledge asset

• Learn and adjust to new circumstances on their own
• Take part in massive parallel processing
• Function without complete information
• Cope with huge volumes of information
• Analyze nonlinear relationships

70% of Top 500 Companies use AI as part of their Decision Support

• By financial analysts:
• For managing assets and investing in stocks
• By hospitals:
• For scheduling staff and diagnosing illnesses
• By credit card companies:
• For detecting credit card fraud
• By police and security organizations:
• For predicting criminal behavior patterns

What Expert Systems Can't Do

• Handle all types of domain expertise
• Solve problems other than those for which they are designed
• Apply common sense or judgment to a problem