University of TehranAdvances in Industrial Engineering2783-174455420211001Supply Chain and Predictability of Return3233338616210.22059/aie.2021.330003.1803ENAsgarNoorbakhshDepartment of Financial Management, Faculty of Management and Accounting, Farabi Campus of University of Tehran, Qom, Iran.0000-0002-0106-8627RaminSoltaniDepartment of Financial Management, Faculty of Management and Accounting, Farabi Campus of University of Tehran, Qom, Iran.MahboubehAsadi MafiDepartment of Financial Management, Faculty of Management and Accounting, Farabi Campus of University of Tehran, Qom, Iran.Journal Article20210904Customer and supplier companies (which form a supply chain) have long-term economic relationships and affect each other. In this study, we answer to the question that “whether past returns of the customer (supplier) company can predict the future return of the supplier (customer) company”. To answer this question, we have investigated the predictability of return (or lead-lag relationship) at the industry-level in 10 supply chains of the Tehran Stock Exchange from March 2015 to March 2020 using the vector autoregression model. We found that a considerable numbers of supply chains, specifically, 6 out of 10 supply chains in our sample show the lead-lag relationship. In 3 supply chains, customer industry returns lead (or predict) supplier industry returns. Whereas, in other 3 supply chains, supplier industry returns lead customer industry returns. These observed lead-lag relationships (or predictable returns) across industries provide some evidence of inefficiency in the Tehran Stock Exchange. In addition, we can use these predictable returns to construct profitable trading strategies.University of TehranAdvances in Industrial Engineering2783-174455420211001Selection of the Most Effective Deliverables in the Sustainability of the Product Design and Development Process Group Employing Hybrid Delphi-GAHP and COCOSO Method3353668616510.22059/aie.2021.331892.1810ENDavoodOmidzadehDepartment of Industrial Engineering, Faculty of Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranAliBozorgi-AmiriSchool of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran.0000-0002-1180-9572Seyed MojtabaSajadiSchool of Strategy and Leadership, Faculty of Business and law, Coventry University, UK.FarzadMovahedi SobhaniDepartment of Industrial Engineering, Faculty of Engineering, Science and Research Branch, Islamic Azad University, Tehran, IranJournal Article20211006Over the past decade, establishing sustainability has become the center stage in manufacturing products as most elements of sustainability meaning economic, social and environmental pillars are improving. However, developing processes leading to product sustainability throughout its life cycle, especially in the new product development process groups, is still in its infancy. The present study focuses on ranking the product development process groups and identifying the most effective one in product sustainability through Delphi-GAHP and COCOSO methods. To carry out this task, product life cycle, the main new product design and development process groups, gateway planning, deliverable items, and product sustainability pillars have been introduced and the necessary data has been collected with the help of automotive industry experts. The most effective process group in product sustainability was selected and the deliverables in the selected process group were ranked to isolate the most effective deliverable item in product life cycle sustainability. Evidently in future research, the findings of this study can be employed in establishing sustainability in product development processes with developing the attributes and components of this new deliverable item.University of TehranAdvances in Industrial Engineering2783-174455420211001An Integrated Markovian Queueing-Inventory Model in a Single Retailer- Single Supplier Problem with Imperfect Quality and Destructive Testing Acceptance Sampling3674018616810.22059/aie.2021.332961.1812ENAmirAghsamiSchool of Industrial Engineering, K. N. Toosi University of Technology (KNTU), Tehran, Iran.0000-0003-0175-2979YaserSamimiSchool of Industrial Engineering, K. N. Toosi University of Technology (KNTU), Tehran, Iran.AbdollahAghaeiSchool of Industrial Engineering, K. N. Toosi University of Technology (KNTU), Tehran, Iran.Journal Article20211026This paper proposes a retailer-supplier queueing-inventory problem (RSQIP) in which the imperfect lots are investigated using a single sampling inspection plan. We integrate an M/M/m response queueing system for handling and responding to customers’ demands with a classical retailer-supplier inventory model considering defective items and inspection process for the first time. Customers whose demand is met leave the retailer system with exactly one item unless the inventory shortage occurs. The retailer places an order once the inventory level reaches an economic reorder point. The lead time is assumed exponential, and due to the imperfect incoming items, the retailer conducts a destructive acceptance sampling plan. The rate of inspection depends on the sample size. Provided that a lot is rejected, the supplier is required to provide a defect-free shipment. We present the stationary distribution of the number of demands in the response system. Then the joint stationary distribution of the order status and inventory level of the retailer is derived. Several performance measures and the expected total cost are presented steady-state, and a non-linear integer programming model is proposed to minimize the expected total cost. The results are numerically illustrated and reveal the convexity of the expected total cost. The optimal reorder point, order quantity, and the number of servers is computed for some numerical examples. A comprehensive sensitivity analysis is conducted to examine the effect of defective items, response system, and some important parameters on the entire developed model. Finally, useful managerial insights are presented.University of TehranAdvances in Industrial Engineering2783-174455420211001Providing an Optimal Model in Modeling the Dependence Structure of the Elements of Financial Systems Using an Approach Based on Vine-Copula Functions. (Case Study: Market and Industry Indices at Tehran Stock Exchange)4034328616910.22059/aie.2022.336312.1818ENMohammad SadeghZarrin NalDepartment of Accounting and Finance, Faculty of Humanities and Social Sciences,Yazd University, Yazd, Iran.HojjatollahSadeqiDepartment of Accounting and Finance, Faculty of Humanities and Social Sciences,Yazd University, Yazd, Iran.0000-0001-5852-4198Journal Article20211227Identification of the structure of dependence among different elements of a financial system has long been a hot topic to researchers due to its impact on the financial asset risk assessment. Currently, the capital market is one of the key financial systems in Iran’s economy, making the understanding and identification of its intra-system associations a major concern to investors and investment managers who seek to forecast the future conditions. Accordingly, the present research investigates and models the dependence structure of different market indices of the Tehran Stock Exchange (TSE), as a representative of the country’s financial system, and the indices referring to the active industries in the TSE, as a component of the financial system. We herein investigated a total of 10 market indices and 31 other indices referring to the most significant active industries in the TSE. The mentioned industries were clustered based on three distinctive scenarios. Considering the number of components and the abnormal structure of their distributions and also taking into account the importance of marginal distributions in the assessment of the system component dependence structure model, we found the copula functions as a useful tool for expressing the dependence between different variables. The results were then studied using the Vuong’s test. The outcomes indicated that the C-Vine functions can generate very good fits to the dependence structures among various industry indices. Moreover, the best fits could be explained using the t-student family of the copula functions.University of TehranAdvances in Industrial Engineering2783-174455420211001Targeted Vaccination for Covid-19 Based on Machine Learning Model: A Case Study of Jobs' Prioritization4334468617010.22059/aie.2022.336859.1819ENMohammad AminAmaniSchool of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran.MohammadrezaGhafariSchool of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran.Mohammad MahdiNasiriSchool of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran.0000-0001-9813-1233Journal Article20220104Today, the spread of the coronavirus has affected many models of life. Despite making some vaccines such as AstraZeneca, Pfizer-BioNTech, and Moderna, vaccination has not been widely used. Due to the lack of vaccines in sufficient numbers, COVID-19 vaccination is usually performed in several phases. Using machine learning methods can be influential in selecting the nominated groups to achieve an acceptable level of immunity called herd immunity. The approach of this article is to introduce the high-risk occupational groups that are most exposed to the coronavirus to the vaccination phasing is done effectively, to provide the fastest immunity. The Genetic algorithm was employed to feature selection for getting appropriate performance in the predictive model. The machine learning regression algorithms, such as decision tree, random forest, and logistic regression, were utilized to build a predictive model, in which random forest with 88.3 % accuracy is selected by comparison among other algorithms for this purpose. The different jobs' categories priorities were determined due to the feature importance based on coefficients to get the vaccine, which this help to reduce the covid 19 deaths.University of TehranAdvances in Industrial Engineering2783-174455420211001Capacitated Sustainable Resilient Closed-Loop Supply Chain Network Design: A Heuristics Algorithm4474798617110.22059/aie.2022.333393.1813ENAbolghasemYousefi-BabadiSchool of Industrial Engineering, College of Engineering, University of Tehran, Tehran, Iran.0000-0002-3635-6282NiloofarSoleimaniDepartment of Industrial Engineering, Yazd University, Yazd, IranDavoodShisheboriDepartment of Industrial Engineering, Yazd University, Yazd, IranJournal Article20211103Consideration of environmental and social issues in addition to economic ones is a critical strategy that companies pay special attention to designing their supply chain. A resilient system prevents organizations from being surprised by catastrophic disruptions and critical conditions and eliminates high unwanted costs. In this study, a mixed-integer mathematical programming model is proposed to design a sustainable and resilient closed-loop supply chain network. Since suppliers are the most important external players, the slightest probability of disruptions can have a significant impact on chain performance. Accordingly, applying efficient strategies can be very helpful for coping with them. Also, because of the uncertain nature of some input parameters, the P-robust optimization method has been used to tackle them. An efficient algorithm has been carried out beside a heuristic method based on the strategic variables relaxation to solve the model. A case study of a lighting projectors industry has been conducted to evaluate the efficiency of the proposed approach. Finally, sensitivity analysis is performed on critical parameters of the problem. By solving the example, it is seen that 3 primary suppliers and 3 backups are selection, and 3 production centers, 2 collection centers and 1 repair, recycling and disposal centers have been established. The value of the economic objective function is equal to 565.857552 monetary units (MU). The CL-SCN environmental score is 658.07, while it is 608.93 in the social dimension. Eventually, the value of the final multi-objective function is equal to 0.658.