Page 466 -

Chapter 11 Managing Knowledge 465

The strategy used to search through the knowledge base is called the
inference engine. Two strategies are commonly used: forward chaining and
backward chaining (see Figure 11.6).
In forward chaining, the inference engine begins with the informa-
tion entered by the user and searches the rule base to arrive at a conclusion.
The strategy is to fire, or carry out, the action of the rule when a condition is
true. In Figure 11.6, beginning on the left, if the user enters a client’s name with
income greater than $100,000, the engine will fire all rules in sequence from
left to right. If the user then enters information indicating that the same client
owns real estate, another pass of the rule base will occur and more rules will
fire. Processing continues until no more rules can be fired.
In backward chaining, the strategy for searching the rule base starts with a
hypothesis and proceeds by asking the user questions about selected facts until
the hypothesis is either confirmed or disproved. In our example, in Figure 11.6,
ask the question, “Should we add this person to the prospect database?” Begin on
the right of the diagram and work toward the left. You can see that the person
should be added to the database if a sales representative is sent, term insurance is
granted, or a financial adviser visits the client.

Examples of Successful Expert Systems
Expert systems provide businesses with an array of benefits including
improved decisions, reduced errors, reduced costs, reduced training time, and
higher levels of quality and service. Con-Way Transportation built an expert
system called Line-haul to automate and optimize planning of overnight ship-
ment routes for its nationwide freight-trucking business. The expert system
captures the business rules that dispatchers follow when assigning drivers,
trucks, and trailers to transport 50,000 shipments of heavy freight each night
across 25 states and Canada and when plotting their routes. Line-haul runs on
a Sun computer platform and uses data on daily customer shipment requests,
available drivers, trucks, trailer space, and weight stored in an Oracle database.
The expert system uses thousands of rules and 100,000 lines of program code
written in C to crunch the numbers and create optimum routing plans for
++
95 percent of daily freight shipments. Con-Way dispatchers tweak the routing
plan provided by the expert system and relay final routing specifications to
field personnel responsible for packing the trailers for their nighttime runs.
Con-Way recouped its $3 million investment in the system within two years
by reducing the number of drivers, packing more freight per trailer, and reduc-
ing damage from rehandling. The system also reduces dispatchers’ arduous
nightly tasks.
Although expert systems lack the robust and general intelligence of human
beings, they can provide benefits to organizations if their limitations are well
understood. Only certain classes of problems can be solved using expert sys-
tems. Virtually all successful expert systems deal with problems of classifica-
tion in limited domains of knowledge where there are relatively few alterna-
tive outcomes and these possible outcomes are all known in advance. Expert
systems are much less useful for dealing with unstructured problems typically
encountered by managers.
Many expert systems require large, lengthy, and expensive development
efforts. Hiring or training more experts may be less expensive than building an
expert system. Typically, the environment in which an expert system operates
is continually changing so that the expert system must also continually change.

MIS_13_Ch_11 Global.indd 465 1/17/2013 2:30:05 PM