Caner Canyakmaz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Caner Canyakmaz has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Fikri Karaesmen
Koc University
3 shared publications - Tamer Boyacı
ESMT Berlin, 10178 Berlin, Germany
3 shared publications - Francis de Véricourt
European School of Management and Technology Berlin, 10178 Berlin, Germany
2 shared publications Süleyman Özekici
2 shared publications- Süleyman Özekici
Department of Industrial Engineering, Koc University, Istanbul, Turkey
1 shared publication
Latest Publications
- 19 August 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Beyond the Black Box: Unraveling the Role of Explainability in Human-Artificial Intelligence Collaboration
Explainable artificial intelligence (AI) models have been proposed to mitigate overreliance and underreliance on AI, which reduce the effectiveness of human-AI collaborative tools. Yet, empirical evidence is mixed, and the impact of explainable AI on the cognitive effort and fatigue of a decision maker (DM) is often overlooked. This paper offers a theoretical perspective on these issues. We develop an analytical model that incorporates the defining features of human and machine intelligence, capturing the limited but flexible nature of human cognition with imperfect machine recommendations. Crucially, we represent how AI-based explanations influence the DM’s belief in the algorithm’s predictive quality. Our results indicate that explainable AI has varying effects depending on the level of explainability provided. Although low explainability levels have no impact on decision accuracy and reliance behavior, they lessen the cognitive burden on the DM. In contrast, higher explainability levels enhance accuracy by improving overreliance but at the expense of increased underreliance. Further, the relative impact of explainability is higher when the DM is more cognitively constrained, when the decision task is sufficiently complex, or when the stakes are lower. Importantly, higher explainability levels can escalate the DM’s cognitive burden (and hence, overall processing time and fatigue) precisely when explanations are most needed (i.e., when the DM is pressed for time to complete a complex task and doubts the machine’s quality). Our study clarifies how explainability affects decision outcomes and cognitive effort, informing the design of effective human-AI systems across decision environments. This paper was accepted by Jeannette Song, operations management. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.07450 .
- 19 August 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Beyond the Black Box: Unraveling the Role of Explainability in Human-Artificial Intelligence Collaboration
Explainable artificial intelligence (AI) models have been proposed to mitigate overreliance and underreliance on AI, which reduce the effectiveness of human-AI collaborative tools. Yet, empirical evidence is mixed, and the impact of explainable AI on the cognitive effort and fatigue of a decision maker (DM) is often overlooked. This paper offers a theoretical perspective on these issues. We develop an analytical model that incorporates the defining features of human and machine intelligence, capturing the limited but flexible nature of human cognition with imperfect machine recommendations. Crucially, we represent how AI-based explanations influence the DM’s belief in the algorithm’s predictive quality. Our results indicate that explainable AI has varying effects depending on the level of explainability provided. Although low explainability levels have no impact on decision accuracy and reliance behavior, they lessen the cognitive burden on the DM. In contrast, higher explainability levels enhance accuracy by improving overreliance but at the expense of increased underreliance. Further, the relative impact of explainability is higher when the DM is more cognitively constrained, when the decision task is sufficiently complex, or when the stakes are lower. Importantly, higher explainability levels can escalate the DM’s cognitive burden (and hence, overall processing time and fatigue) precisely when explanations are most needed (i.e., when the DM is pressed for time to complete a complex task and doubts the machine’s quality). Our study clarifies how explainability affects decision outcomes and cognitive effort, informing the design of effective human-AI systems across decision environments. This paper was accepted by Jeannette Song, operations management. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2024.07450 .
- 14 February 2024
- Published by Elsevier in International Journal of Production Economics
- Vol. 270
Risk management through financial hedging in inventory systems with stochastic price processes
- 14 February 2024
- Published by Elsevier in International Journal of Production Economics
- Vol. 270
Risk management through financial hedging in inventory systems with stochastic price processes
- Top Cited Papers
- 1 February 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 70 (2) , 1258-1275
Human and Machine: The Impact of Machine Input on Decision Making Under Cognitive Limitations
The rapid adoption of artificial intelligence (AI) technologies by many organizations has recently raised concerns that AI may eventually replace humans in certain tasks. In fact, when used in collaboration, machines can significantly enhance the complementary strengths of humans. Indeed, because of their immense computing power, machines can perform specific tasks with incredible accuracy. In contrast, human decision makers (DMs) are flexible and adaptive but constrained by their limited cognitive capacity. This paper investigates how machine-based predictions may affect the decision process and outcomes of a human DM. We study the impact of these predictions on decision accuracy, the propensity and nature of decision errors, and the DM’s cognitive efforts. To account for both flexibility and limited cognitive capacity, we model the human decision-making process in a rational inattention framework. In this setup, the machine provides the DM with accurate but sometimes incomplete information at no cognitive cost. We fully characterize the impact of machine input on the human decision process in this framework. We show that machine input always improves the overall accuracy of human decisions but may nonetheless increase the propensity of certain types of errors (such as false positives). The machine can also induce the human to exert more cognitive efforts, although its input is highly accurate. Interestingly, this happens when the DM is most cognitively constrained, for instance, because of time pressure or multitasking. Synthesizing these results, we pinpoint the decision environments in which human-machine collaboration is likely to be most beneficial. This paper was accepted by Jeannette Song, operations management. Supplemental Material: The data files and online appendices are available at https://doi.org/10.1287/mnsc.2023.4744 .
- 1 February 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 70 (2) , 1258-1275
Top Cited PapersHuman and Machine: The Impact of Machine Input on Decision Making Under Cognitive Limitations
The rapid adoption of artificial intelligence (AI) technologies by many organizations has recently raised concerns that AI may eventually replace humans in certain tasks. In fact, when used in collaboration, machines can significantly enhance the complementary strengths of humans. Indeed, because of their immense computing power, machines can perform specific tasks with incredible accuracy. In contrast, human decision makers (DMs) are flexible and adaptive but constrained by their limited cognitive capacity. This paper investigates how machine-based predictions may affect the decision process and outcomes of a human DM. We study the impact of these predictions on decision accuracy, the propensity and nature of decision errors, and the DM’s cognitive efforts. To account for both flexibility and limited cognitive capacity, we model the human decision-making process in a rational inattention framework. In this setup, the machine provides the DM with accurate but sometimes incomplete information at no cognitive cost. We fully characterize the impact of machine input on the human decision process in this framework. We show that machine input always improves the overall accuracy of human decisions but may nonetheless increase the propensity of certain types of errors (such as false positives). The machine can also induce the human to exert more cognitive efforts, although its input is highly accurate. Interestingly, this happens when the DM is most cognitively constrained, for instance, because of time pressure or multitasking. Synthesizing these results, we pinpoint the decision environments in which human-machine collaboration is likely to be most beneficial. This paper was accepted by Jeannette Song, operations management. Supplemental Material: The data files and online appendices are available at https://doi.org/10.1287/mnsc.2023.4744 .
- 1 January 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Manufacturing & Service Operations Management
- Vol. 25 (1) , 266-287
Queueing Systems with Rationally Inattentive Customers
Problem definition: Classical models of queueing systems with rational and strategic customers assume queues to be either fully visible or invisible, while service parameters are known with certainty. In practice, however, people only have “partial information” on the service environment, in the sense that they are not able to fully discern prevalent uncertainties. This is because assessing possible delays and rewards is costly, as it requires time, attention, and cognitive capacity, which are all limited. On the other hand, people are also adaptive and endogenously respond to information frictions. Methodology: We develop an equilibrium model for a single-server queueing system with customers having limited attention. Following the theory of rational inattention, we assume that customers optimize their learning strategies by deciding the type and amount of information to acquire and act accordingly while internalizing the associated costs. Results: We establish the existence and uniqueness of a customer equilibrium when customers allocate their attention to learn uncertain queue lengths and delineate the impact of service characteristics. We provide a complete spectrum of the impact of information costs on throughput and show numerically that throughput might be nonmonotone. This is also reflected in social welfare if the firm’s profit margin is high enough, although customer welfare always suffers from information costs. Managerial implications: We identify service settings where service firms and social planners should be most cautious for customers’ limited attention and translate our results to advisable strategies for information provision and service design. For example, we recommend firms to avoid partial hindrance of queue-length information when a low-demand service is not highly valued by customers. For a popular service that customers value reasonably highly, however, partial hindrance of information is particularly advisable. Academic/practical relevance: We propose a microfounded framework for strategic customer behavior in queues that links beliefs, rewards, and information costs. It offers a holistic perspective on the impact of information prevalence (and information frictions) on operational performance and can be extended to analyze richer customer behavior and complex queue structures, rendering it a valuable tool for service design. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2021.1032 .
- 1 January 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Manufacturing & Service Operations Management
- Vol. 25 (1) , 266-287
Queueing Systems with Rationally Inattentive Customers
Problem definition: Classical models of queueing systems with rational and strategic customers assume queues to be either fully visible or invisible, while service parameters are known with certainty. In practice, however, people only have “partial information” on the service environment, in the sense that they are not able to fully discern prevalent uncertainties. This is because assessing possible delays and rewards is costly, as it requires time, attention, and cognitive capacity, which are all limited. On the other hand, people are also adaptive and endogenously respond to information frictions. Methodology: We develop an equilibrium model for a single-server queueing system with customers having limited attention. Following the theory of rational inattention, we assume that customers optimize their learning strategies by deciding the type and amount of information to acquire and act accordingly while internalizing the associated costs. Results: We establish the existence and uniqueness of a customer equilibrium when customers allocate their attention to learn uncertain queue lengths and delineate the impact of service characteristics. We provide a complete spectrum of the impact of information costs on throughput and show numerically that throughput might be nonmonotone. This is also reflected in social welfare if the firm’s profit margin is high enough, although customer welfare always suffers from information costs. Managerial implications: We identify service settings where service firms and social planners should be most cautious for customers’ limited attention and translate our results to advisable strategies for information provision and service design. For example, we recommend firms to avoid partial hindrance of queue-length information when a low-demand service is not highly valued by customers. For a popular service that customers value reasonably highly, however, partial hindrance of information is particularly advisable. Academic/practical relevance: We propose a microfounded framework for strategic customer behavior in queues that links beliefs, rewards, and information costs. It offers a holistic perspective on the impact of information prevalence (and information frictions) on operational performance and can be extended to analyze richer customer behavior and complex queue structures, rendering it a valuable tool for service design. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2021.1032 .
- 1 June 2019
- Published by Elsevier in International Journal of Production Economics
- Vol. 212, 139-152
An inventory model where customer demand is dependent on a stochastic price process
- 1 June 2019
- Published by Elsevier in International Journal of Production Economics
- Vol. 212, 139-152
An inventory model where customer demand is dependent on a stochastic price process
- 21 December 2017
- Published by Emerald Publishing in Foundations and Trends® in Technology, Information and Operations Management
- Vol. 11 (1-2) , 107-123
Minimum-Variance Hedging for Managing Risks in Inventory Models with Price Fluctuations
We consider the financial hedging of a random operational cash flow that arises in inventory operations with price and demand uncertainty. We use a variance minimization approach to find a financial portfolio that would minimize the total variance of operational and financial returns. For inventory models that involve continuous price fluctuations and price-dependent demand that arrives in continuous time, we characterize the minimum-variance hedging policies and numerically illustrate their effectiveness.
- 21 December 2017
- Published by Emerald Publishing in Foundations and Trends® in Technology, Information and Operations Management
- Vol. 11 (1-2) , 107-123
Minimum-Variance Hedging for Managing Risks in Inventory Models with Price Fluctuations
We consider the financial hedging of a random operational cash flow that arises in inventory operations with price and demand uncertainty. We use a variance minimization approach to find a financial portfolio that would minimize the total variance of operational and financial returns. For inventory models that involve continuous price fluctuations and price-dependent demand that arrives in continuous time, we characterize the minimum-variance hedging policies and numerically illustrate their effectiveness.