Abstract:
In today’s ever changing markets, maintaining an efficient and flexible supply chain is critical
for every enterprise, especially given the prevailing volatilities in the business environment with
constantly shifting and increasing consumer expectations. One of the key sources of uncertainty
in any production-distribution system is the product demand. Failure to account for significant
demand fluctuations could either lead to unsatisfied consumer demand translating to loss of
market share or excessively high inventory holding costs. The traditional demand models are
concerned with only improving forecast accuracy rather assessing uncertainty. Uncertainty
concern can help manage the risk associated with alternative plans. In this thesis a demand
model is developed considering the combined effect of price sensitivity and consumers’
valuation or satisfaction as a source of uncertainty. The uncertainty model is developed
considering consumers’ valuation, price, price sensitivity, the market size, wholesale price and
quantity ordered by the retailer on profit maximization. The retailer price and the order quantity
that the retailer places with the manufacturer are the decision variables and total profit is the
objective function which is to be maximized. Two meta-heuristics Genetic Algorithm and
Sequential Quadratic Programming are used to solve the non linear constrained form of objective
function as they can generate accurate result with a shorter computational time. Some numerical
examples have been presented to explain the model. The results obtained from these algorithms
and the results of the existing forecasting model of a renowned company were compared with
actual sales data and the algorithm results were found satisfactory.
