Now is an era of highest demand uncertainty,
higher supply risk and increasing competitive intensity and thus supply chain
excellence determines the organizations ability to integrate the entire
spectrum of end to end processes from raw material acquisition to delivery of
final finished product to the customer. This end to end process can be enhanced
by increased visibility across the process many organizations attempt to
increase their information source of real time data by sharing the real time
information with supply chain partners. Supply chain partners have explored
various ways in order to better manage information to make better business
decisions. One of those ways includes artificial intelligence (AI).
In case of inventory planning and control,
inventory is maintained in order to fulfil the uncertain demands of the
customers and they incur substantial costs and thus it can be said that the
firm’s success depends on its ability to control and plan inventory at minimum
cost. In AI we can have tools such as an expert system, which can replace the
sound judgment and intellect of experienced inventory managers and deal with
the unexpected, is better suited to handling inventory control and planning
decisions. In 1986 Dr Allen developed an expert system called the Inventory
Management Assistant. The IMA had improved the inventory management effectively
by 8-18% by reducing inventory errors.
Another application of AI techniques to inventory
control was included in the study of Teodorovic et al (2002) who developed
Fuzzy logic rules to make online inventory control decisions.
When it comes to Transportation and network
design the problems become intrinsically combinatorial and for which global
optimal solutions are difficult to find. Different problems such as the TSP,
the vehicle routing and scheduling problem, the minimum spanning tree problem,
the freight consolidation problem, and the intermodal connection problem ,road
network design, gas distribution pipeline network design, parking space
utilisation, traffic assignment, and ramp metering in freeway networks . In
such cases Genetic Algorithm (GA) serves the purpose. Another AI technique that
has emerged as one of the popular one is the ant colony optimization algorithm.
This algorithm was used successfully to handle well known network design
problems such as the TSP, the vehicle routing problem, and the minimum spanning
tree problem (Dorigo and Gambardella 1997, Bullnheimer et al. 1999, Shyu et al.
GA and Ant colony optimization algorithm are the
general algorithmic framework that can be applied to a wide set of different
combinatorial optimisation problems with relatively few modifications to make
them adapted to a specific transportation network design problem.
They are more flexible than the traditional OR
techniques and accommodate variations in the transportation problem structure.
In case of purchasing and supply management, a
make or buy decision is based on weighting the options of goods producers or
suppliers or to purchase from the external source of suppliers to better
utilize the firms given resources. The
make or buy decisions needs to consider various What-ifs like:
volume of goods does the company expect to produce?
much capital investment is needed to produce goods or render services?
much risk is involved in developing new products or innovating technology to
stay competitive in the market?
the product that the company is considering making reached its peak demand or
the maturity stage of its life cycle?
And in order to answer these above questions the
make or buy decision calls for systematic decision aid tools. In 2002 Humphreys
et al developed an expert system that could assist the purchasing manager in
evaluating the performance of prospective suppliers, enhancing information
exchange among the purchasing personnel and reducing the time to make the
make-or-buy decision. Also, Kim et al.
proposed an agent-based purchasing system to automate the online purchasing
process involved in the acquisition of shoe materials from the global supply
On the similar line in the year 2004 Cheung et
al developed a hybrid agent-and knowledge-based system to evaluate online bids
and the performance of the bid winning suppliers in fulfilling orders.
Nissen and Sengupta in 2006 proposed intelligent
software agents that could automate the processes of searching for prospective
suppliers through online catalogues, evaluating suppliers with respect to multiple
attributes, screening qualified suppliers and completing the purchase order .
Now day’s companies generally have e portals and
e tendering for online purchase orders from the suppliers. This simplifies the
purchasing process and increases transparency.
In case of the reverse supply chain the network
design is concerned with establishing an infrastructure to manage reverse
channel which consists of final users, collectors and remanufacturers and in
this category many AI approaches have been utilized and among all those GA is
the most preferred approach. GA is employed to obtain a near optimal solution
for the proposed model. The computational experimentation explores the
trade-offs between (i) the inventory holding and shipment consolidation costs and
(ii) the location costs and customer service (measured in terms of ease of
access to collection centres).