Artificial Intelligence For Business: A.K. Swain

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 11

Artificial Intelligence for

Business

A.K. Swain

IIM Kozhikode
Knowledge Based Systems

• Incorporates high-quality, domain-


specific knowledge
• Contains heuristic knowledge
(possessed by knowledgeable person)
Heuristics

Represent informal knowledge, rule of


thumb, or shortcuts that allow knowledgeable
persons to quickly reach a solution to a
problem without having to perform a detailed
analysis of a particular situation.
Heuristics vs. Algorithmic
Alex is a prospective homebuyer, who arrives for a meeting with Ave, a residential building
contractor. Alex is carrying a set of architectural plans describing the design of a house. He
wants an estimate of the cost of the house before committing to employ Ave to build him the
house. A contractor typically determines the price of the house by performing a detailed cost
analysis. This involves carefully calculating the amount of material necessary to build the
house; calling a building supply warehouse to obtain material prices; evaluating quotations
from subcontractors on the cost of their labour; determining the appropriate contractors' fees;
allowing a reasonable contingency figure; and so forth. This process has the advantage of
nearly guaranteeing a correct result (assuming no computational errors are made) and
entails relatively little risk for the contractor. The disadvantage, however, is that this process
involves a significant amount of effort and time. However, Alex is leaving town that same
evening and needs a quotation before he leaves. Ave is an experienced contractor (an
expert), and as such, he has another option. He compares the size of this home to ones he
recently completed. By finding a home that has approximately the same living area, he can
obtain a rough estimate (based on his previous experience) for the price per square foot. He
then looks for differences between the homes that might raise or lower the estimate. These
differences might include additions like a swimming pool (raising his estimate by
Rs.1,50,000), modifications like tick kitchen cabinets instead of hard wood (increasing his
estimate by Rs.1,00,000), or deletions such as two bathrooms instead of three (decreasing
his estimate by Rs.60,000). After evaluating these differences, Ave is able to make an
estimate in only 30 minutes.
Knowledge Based Systems

• Definition (in general terms):


• A computerized system that uses domain
knowledge to arrive at a solution to a problem
within that domain. The solution is essentially the
same as one concluded by a person
knowledgeable about the domain, when
confronted with the same problem.
KB Systems: Characteristics

• The use of highly specific domain


knowledge
• The heuristics nature of the knowledge
employed instead of algorithmic
• The separation of the knowledge from how
it is used
KB Systems: Features

• KB systems excel at capturing, sharing, and


allowing users to apply it.
• KB systems are designed to solve problems
not to passively represent knowledge.
KB Systems: Advantages

• Wide distribution of scarce expertise


• Ease of modification
• Consistency of answers
• Perpetual accessibility
• Preservation of expertise
• Solution of problems involving incomplete data
• Explanation of solution.
KB Systems: Disadvantages

• Answers may not always be correct


• Limits not always recognized
• Lack of common sense
Types of Artificial Intelligence
Artificial Intelligence

Fuzzy Logic

Neural Networks
Knowledge Based Systems Soft Computing Methods

Probabilistic Systems

Evolutionary Computation
Expert System Case Based Constraint Based
Reasoning Reasoning

Model Based Evolutionary Evolution Genetic Genetic


Reasoning Programming Strategy Algorithms Programming

10
The END

IIM Kozhikode

You might also like