Production and stock management under manufacturer and customer driven substitution

Töre, Nurşen
In this thesis, the stock management problem of a manufacturer is studied in the presence of product substitution flexibility. The study consists of two parts. In the first part, the manufacturer's joint production scheduling and product substitution decisions are analyzed. It is assumed that there are multiple substitutable items and for each item, and inventory is kept separately. If upon demand arrival, stock is not available, then demand is backordered. Depending on the inventory level, it is possible to meet the demand via a substitute item. However, it takes a time and cost to substitute the item with another one. The production and substitution decisions are given dynamically over time depending on the net inventory level of the products. It is shown that for the two-product setting optimal production policy is characterized by a hedging point and a switching curve, and the substitution policies are characterized by threshold substitution levels. For the two-product setting the benefit of substitution, and the value of stock level information are quantified. For the multiple item setting, several heuristics are proposed. Through numerical analysis, the conditions under which each heuristic performs well are identified. In the second part of the thesis, the manufacturer's response to substitution behavior of the customer is studied. The manufacturer can manipulate the customer's substitution behaviour by price and availability of the products. The manufacturer decides on the optimal stock levels, the initial price of the products, and the market markdown price after the demand is realized. It is assumed there are two substitutable products and for each item, initial stock levels are determined separately. Since the products the manufacturer produces are similar, uniform pricing is used. Then according to price determined by the manufacturer, random demands for products occur. After the initial selling period, price is updated, that results in customer demand shift to the other product. The customer's initial demand and the demand spill-over due to price and stock-out based substitution are characterized through the Representative Consumer Theorem framework. We adopt a two-phase solution methodology where in the first we determine the optimal price after the demand realization, and then determine the initial price and stock levels. While doing so we gain an understanding on how the manufacturer should determine the optimal prices. To determine the initial price and the stock levels, we offer a solution approach for finding the KKT points of the corresponding model. Through numerical analysis, we obtain insights on how stock levels are determined, how the price decisions and the profit respond to the substitution behavior of the customers. Finally, through numerical analysis we quantify the value of exploiting the stockout based substitution via markdown pricing, and the value of the optimal solution.


Comparison of methods for robust parameter design of products and processes with an ordered categorical response
Bacanlı Karabulut, Gonca; Köksal, Gülser; Department of Industrial Engineering (2013)
Robust design of products or processes with categorical response has more momentous role in industrial experiments for quality improvements, because ordinal categorical quality characteristics are encountered more frequent than continuous ones in industry. In this study, five optimization methods for an ordered categorical response are compared with each other: Logistic Regression Model Optimization (LRMO), Accumulation Analysis (AA), Weighted Signal-to-noise Ratio (WSNR), Scoring Scheme (SS), and Weighted ...
Product-line planning under uncertainty
Karakaya, Şakir; Köksal, Gülser; Department of Industrial Engineering (2018)
This study addresses the problem of multi-period mix of product-lines under a product- family, which incorporates launching decisions of new products, capacity expansion decisions and product interdependencies. The problem is modelled as a two-stage stochastic program with recourse in which price, demand, production cost and cannibalisation effect of new products are treated as uncertain parameters. The solution approach employs the Sample Average Approximation based on Monte Carlo bounding technique and mu...
Workload smoothing in assembly lines
İmat, Sadullah; Azizoğlu, Meral; Department of Industrial Engineering (2014)
In this thesis, we consider a simple assembly line balancing problem with fixed number of workstations and predefined cycle time. Our objective is to minimize the sum of the squared deviations of the workstation loads from the cycle time. We first present pure integer nonlinear programming model and then convert the model into mixed integer linear program. We develop several optimality properties and bounding mechanisms, and use them in our branch and bound algorithm. The results of our computational study ...
The Critical success factors for manufacturing execution systems (mes) adoption in Turkey defense industry: an industrial case study
Yavuz, Hasan; Akçomak, İbrahim Semih; Department of Science and Technology Policy Studies (2018)
The main objective of this thesis is to investigate the Critical Success Factors (CSFs) of Manufacturing Execution Systems (MES) adoption using the case of a Turkish defense industry firm with both a quantitative and a qualitative research design. After the critical factors that are used in the adoption and implementation assessment in different countries and sectors are determined in the literature, about one hundred questionnaires and five interviews are conducted at a defense industry firm. The thesis dr...
A Remanufacturing system with imperfect sorting: deterministic and probabilistic models
Tan, Merve; Bakal, İsmail Serdar; Yüksel Özkaya, Banu; Department of Industrial Engineering (2018)
In this study, we focus on inaccurate sorting process with classification errors in a reverse supply chain comprising a remanufacturer and a collector under deterministic demand in a single time period. The collector acquires used items from end-users and the remanufacturer reproduces them to serve the deterministic demand of remanufactured products. There are two sources of uncertainty: uncertain quality of used items and uncertain quality of sorted items due to imperfect testing. Used items are categorize...
Citation Formats
N. Töre, “Production and stock management under manufacturer and customer driven substitution,” Ph.D. - Doctoral Program, Middle East Technical University, 2014.