Çok ürünlü mali kayıp risk kısıtlı envanter problemi

In this thesis, we study the single period stochastic inventory (newsvendor) problem withdownside risk constraints. The aim in the classical newsvendor problem is maximizing theexpected profit. In the classical problem, the risk of earning less than the desired targetprofit or losing more than an acceptable level due to the randomness of demand is nottaken into account. In the literature, there are some models for maximizing the profit whilecontrolling the financial risk or for only controlling the financial risk. In this study, weutilize Value at Risk (VaR) and Conditional Value at Risk (CVaR) as the risk measures innewsvendor framework. In this study, we investigate the multi-product newsvendorproblem under VaR and CVaR constraints. Analytical results for two products areobtained. An approximation method for the N product problem is also developed. Effectsof the system parameters on the optimum product quantities are investigated numerically.In the second part of the thesis, the inventory problem with the objective of minimizingCVaR is analyzed. By using the LP representation of the CVaR problem, this model issolved for N products where the profit function has an arbitrary distribution function. Thenumerical studies are performed for both risk measures.