Srinagesh Gavirneni | Cornell University (original) (raw)

Papers by Srinagesh Gavirneni

Anchoring and Insufficient Adjustment (AIA) bias has been observed in many newsvendor experiments... more Anchoring and Insufficient Adjustment (AIA) bias has been observed in many newsvendor experiments, although a mathematical explanation for this behavior has previously eluded researchers. We show that risk aversion coupled with an implicit shortage cost, both of which are well-known components of newsvendor decisions, comprehensively explains this behavior. We construct combinations of a risk averse utility function and a shortage cost that explain the results from Schweitzer and Cachon , the first and the most-cited study in newsvendor experiments.

Management science, Jan 1, 1999

We incorporate information ow between a supplier and a customer in a two-echelon model that captu... more We incorporate information ow between a supplier and a customer in a two-echelon model that captures the capacitated setting of a typical supply chain. We consider three situations: (1) a traditional model where there is no information to the supplier prior to a demand to him except from past data; (2) the supplier has the information of the (s,S) policy used by the customer as well as the end-product demand distribution; and (3) the supplier has full information about the state of the customer. We show that order up-to policies continue to be optimal for models with information ow for the nite horizon, the in nite horizon discounted and the in nite horizon average cost cases. We develop solution procedures to compute the optimal parameters. Study of these three models enables us to understand the relationships between capacity, inventory and information at the supplier level and how they are a ected by customer S ? s values and end-item demand distribution. We estimate the savings at the supplier due to information ow and study when information is most bene cial.

Management Science, Jan 1, 2002

M any organizations have only recently recognized that sharing information with other members in ... more M any organizations have only recently recognized that sharing information with other members in their supply chain can lead to significant reduction in the total costs. Usu-ally these information flows are incorporated into existing operating policies at the various parties. In this paper ...

European Journal of Operational Research, Jan 1, 2001

We model co-operation in a typical production distribution setting that contains one capacitated ... more We model co-operation in a typical production distribution setting that contains one capacitated supplier producing and distributing a single product to many identical retailers who are facing iid end-item demands from the consumers. We consider three inventory allocation ...

Operations Research Letters, Jan 1, 2004

We consider the periodic review inventory control problem in which the purchasing cost of the pro... more We consider the periodic review inventory control problem in which the purchasing cost of the product changes, in a Markovian fashion, from one period to the next.

European journal of operational research, Jan 1, 2006

We consider a supply chain consisting of one supplier with finite production capacity and a retai... more We consider a supply chain consisting of one supplier with finite production capacity and a retailer facing independent and identically distributed demands from end-customers. Existing research advocates that, in a decentralized setting, the retailer and the supplier using stationary order up to policies is efficient. We show that in the presence of information sharing, the supply chain performance can be improved by the supplier offering fluctuating prices. We study two specific settings: (1) the supplier only knows the parameters of the retailerÕs inventory policy; and (2) the supplier knows the day-to-day inventory levels at the retailer as well. After establishing structure of optimal policies and developing efficient solution procedures, we perform an extensive computational study to determine the extent of the improvements realizable in the supply chain. We observed that for setting 1, an improvement was realized only when the end-customer demands were highly variable. Even then, the improvement in supply chain performance was less than 1%. Whereas, for setting 2, the improvement in supply chain performance averaged around 5.0% with a maximum of 16.3%.

Quantitative models for supply chain …, Jan 1, 1999

443 15.1 INTRODUCTION The industrial supplier-customer relations have undergone radical changes i... more 443 15.1 INTRODUCTION The industrial supplier-customer relations have undergone radical changes in recent years as the philosophy behind managing manufacturing systems con-tinues to be influenced by several Japanese manufacturing practices. As more organizations ...

IIE Transactions, Jan 1, 2001

We present an ecient solution method ± Direct Derivative Estimation (DDE) ± for computing optimal... more We present an ecient solution method ± Direct Derivative Estimation (DDE) ± for computing optimal order-up-to levels for a discrete time non-stationary inventory control model. We generalize a number of non-stationary inventory control models (which underlie larger models of supply chains) that include forecast updates, seasonality, information sharing, and exchange-ratē uctuations. This procedure is dierent from the existing ones in that it computes, in a recursive manner, the derivative of the cost function and not the cost function itself. It can also handle a much wider variety of¯uctuations in the problem parameters. In our computational testing it was found to be considerably faster than Dynamic Programming and In®nitesimal Perturbation Analysis.

Interfaces, Jan 1, 2007

With the widening disconnect between inventory-control research and practice, people debate the v... more With the widening disconnect between inventory-control research and practice, people debate the value of incremental theory building. While practitioners make decisions in a complex and uncoordinated environment, researchers often adopt a simplistic environment for the sake ...

Policing: An International Journal of …, Jan 1, 2006

... The Authors. Arvind Verma, Department of Criminal Justice, Indiana University, Bloomington, I... more ... The Authors. Arvind Verma, Department of Criminal Justice, Indiana University, Bloomington, Indiana, USA. Srinagesh Gavirneni, Johnson Graduate School of Management, Cornell University, Ithaca, New York, USA. Abstract. ...

Decision Analysis, Jan 1, 2009

We conducted a newsvendor experiment in which (i) the subjects were presented with multiple piece... more We conducted a newsvendor experiment in which (i) the subjects were presented with multiple pieces of information that they could possibly use to anchor their decision and (ii) the subjects participated either as individuals or in groups of three. The primary objective was to ...

European journal of operational research, Jan 1, 1999

This paper extends the real options literature by discussing an investment problem, where a firm ... more This paper extends the real options literature by discussing an investment problem, where a firm has to determine optimal investment timing and optimal capacity choice at the same time under conditions of irreversible investment expenditures and uncertainty in future demand. After the project is installed with a certain maximum capacity, this capacity is fixed as an upper boundary to the output and cannot be adjusted later on. It turns out that, in the framework of this once and for all decision, uncertainty in future demand leads to an increase in optimal installed capacity. But on the other hand it causes investment to be delayed to an extent that even small uncertainty makes waiting and accumulation of further information the optimal decision for large ranges of demand. Limiting the capacity which may be installed weakens this extreme effect of uncertainty.

Proceedings of the 31st …, Jan 1, 1999

In this paper, we conduct sensitivity analysis on a ranking and selection procedure for making mu... more In this paper, we conduct sensitivity analysis on a ranking and selection procedure for making multiple comparisons of systems that have multiple performance measures. The procedure combines multiple attribute utility theory with ranking and selection to select the best configuration from a set of K configurations using the indifference zone approach. Specifically, we consider sensitivity analysis on the weights generated by the multiple attribute utility assessment procedure. We demonstrate our analysis on a simulation model of a large project that has six performance measures.

Interfaces, Jan 1, 2007

Schlumberger and its competitors use seismic surveying, the process of mapping subterranean rock ... more Schlumberger and its competitors use seismic surveying, the process of mapping subterranean rock formations with reflected sound waves, as an important first step in identification and recovery of oil and gas reserves. This complicated logistical operation commonly lasts two to six ...

Reliability, IEEE Transactions on, Jan 1, 1995

Production and Operations …, Jan 1, 2010

We report on the information gathering and decision making efforts of subjects involved in newsve... more We report on the information gathering and decision making efforts of subjects involved in newsvendor decision making. Previous research in this area identified significant biases (e.g. anchoring and insufficient adjustment) in inventory decisions, but was unable to identify specific thought processes that led to these biases. We overcome this by using a "think-aloud" approach and recording the thought processes underlying the subjects' eventual decisions. A protocol analysis of the transcripts revealed the following interesting insights. Most of the decision makers sought the very basic information, but failed to seek the additional, but non-trivial, information that could have significantly influenced their decision. A majority of the subjects struggled to deal with the abstractness of the business setting and were very keen to know information on the product type, industry setting, decisions taken in the past, competitor's situation, and vendor environment that they felt would have put them on a firmer footing. A large portion of the participants correctly identified the overage and underage costs that needed to be considered, but failed to convert that information into the optimal order quantity. This suggests that the mathematics involved is not as intuitive as perceived by the research community. Finally, the bias of the order quantity was significantly influenced by the specific type of risk (overage or underage) that was identified closer in time to the decision making point which indicates the presence of a recency effect. That is, if a subject first mentioned the risk of excess inventory followed by the risk of unsatisfied demand, then his/her order quantity was high. On the other hand, if a subject first mentioned the risk of unsatisfied demand followed by the risk of excess inventory, then his/her order quantity was low.

Manufacturing & Service …, Jan 1, 1999

We consider a stochastic, capacitated production-inventory model in which the customer provides i... more We consider a stochastic, capacitated production-inventory model in which the customer provides information about the expected timing of future orders to the supplier. We allow for randomness in customer order arrivals as well as the quantity demanded, but work under the ...

Operations Research Letters, Jan 1, 2001

We consider a capacitated supply chain in which the supplier has the information of the (s,S) pol... more We consider a capacitated supply chain in which the supplier has the information of the (s,S) policy used by the retailer as well as the end-customer demand distribution. For the resulting inventory control problem at the supplier, optimal policies and structural properties were ...

Interfaces, Jan 1, 2004

In its efforts to provide automated meter-reading services to the utility industry, Schlumberger ... more In its efforts to provide automated meter-reading services to the utility industry, Schlumberger faces the problem of deploying receivers efficiently. In a geographic region, the problem is to install the minimum number of receivers on existing utility poles so that all wireless meters in that region can transmit their readings to at least one. Schlumberger first encountered this large-scale problem in a project it ran for Illinois Power. It found solving this problem manually very time consuming, and it had no ability to evaluate the robustness of the resulting solution. We proposed and implemented an optimization-based approach that reduced the duration and cost of implementations. In addition, we gave planners the ability to answer what-if questions.

Production and Operations …, Jan 1, 2008

N ew developments in corporate information technology such as enterprise resource planning system... more N ew developments in corporate information technology such as enterprise resource planning systems have significantly increased the flow of information among members of supply chains. However, the benefits of sharing information can vary depending on the supply chain structure and its operational characteristics. Most of the existing research has studied the impact of sharing downstream information (e.g., a manufacturer sharing information with its suppliers). We evaluate the benefits of sharing upstream yield information (e.g., a supplier sharing information with the manufacturer) in a two-stage serial supply chain in which the supplier has multiple internal processes and is faced with uncertain output due to yield losses. We are interested in determining when the sharing of the supplier's information is most beneficial to the manufacturer. After proposing an orderup-to type heuristic policy, we perform a detailed computational study and observe that this information is most beneficial when the supplier's yield variance is high and when end-customer demand variance is low. We also find that the manufacturer's backorder-to-holding cost ratio has little, if any, impact on the usefulness of information.

Anchoring and Insufficient Adjustment (AIA) bias has been observed in many newsvendor experiments... more Anchoring and Insufficient Adjustment (AIA) bias has been observed in many newsvendor experiments, although a mathematical explanation for this behavior has previously eluded researchers. We show that risk aversion coupled with an implicit shortage cost, both of which are well-known components of newsvendor decisions, comprehensively explains this behavior. We construct combinations of a risk averse utility function and a shortage cost that explain the results from Schweitzer and Cachon , the first and the most-cited study in newsvendor experiments.

Management science, Jan 1, 1999

We incorporate information ow between a supplier and a customer in a two-echelon model that captu... more We incorporate information ow between a supplier and a customer in a two-echelon model that captures the capacitated setting of a typical supply chain. We consider three situations: (1) a traditional model where there is no information to the supplier prior to a demand to him except from past data; (2) the supplier has the information of the (s,S) policy used by the customer as well as the end-product demand distribution; and (3) the supplier has full information about the state of the customer. We show that order up-to policies continue to be optimal for models with information ow for the nite horizon, the in nite horizon discounted and the in nite horizon average cost cases. We develop solution procedures to compute the optimal parameters. Study of these three models enables us to understand the relationships between capacity, inventory and information at the supplier level and how they are a ected by customer S ? s values and end-item demand distribution. We estimate the savings at the supplier due to information ow and study when information is most bene cial.

Management Science, Jan 1, 2002

M any organizations have only recently recognized that sharing information with other members in ... more M any organizations have only recently recognized that sharing information with other members in their supply chain can lead to significant reduction in the total costs. Usu-ally these information flows are incorporated into existing operating policies at the various parties. In this paper ...

European Journal of Operational Research, Jan 1, 2001

We model co-operation in a typical production distribution setting that contains one capacitated ... more We model co-operation in a typical production distribution setting that contains one capacitated supplier producing and distributing a single product to many identical retailers who are facing iid end-item demands from the consumers. We consider three inventory allocation ...

Operations Research Letters, Jan 1, 2004

We consider the periodic review inventory control problem in which the purchasing cost of the pro... more We consider the periodic review inventory control problem in which the purchasing cost of the product changes, in a Markovian fashion, from one period to the next.

European journal of operational research, Jan 1, 2006

We consider a supply chain consisting of one supplier with finite production capacity and a retai... more We consider a supply chain consisting of one supplier with finite production capacity and a retailer facing independent and identically distributed demands from end-customers. Existing research advocates that, in a decentralized setting, the retailer and the supplier using stationary order up to policies is efficient. We show that in the presence of information sharing, the supply chain performance can be improved by the supplier offering fluctuating prices. We study two specific settings: (1) the supplier only knows the parameters of the retailerÕs inventory policy; and (2) the supplier knows the day-to-day inventory levels at the retailer as well. After establishing structure of optimal policies and developing efficient solution procedures, we perform an extensive computational study to determine the extent of the improvements realizable in the supply chain. We observed that for setting 1, an improvement was realized only when the end-customer demands were highly variable. Even then, the improvement in supply chain performance was less than 1%. Whereas, for setting 2, the improvement in supply chain performance averaged around 5.0% with a maximum of 16.3%.

Quantitative models for supply chain …, Jan 1, 1999

443 15.1 INTRODUCTION The industrial supplier-customer relations have undergone radical changes i... more 443 15.1 INTRODUCTION The industrial supplier-customer relations have undergone radical changes in recent years as the philosophy behind managing manufacturing systems con-tinues to be influenced by several Japanese manufacturing practices. As more organizations ...

IIE Transactions, Jan 1, 2001

We present an ecient solution method ± Direct Derivative Estimation (DDE) ± for computing optimal... more We present an ecient solution method ± Direct Derivative Estimation (DDE) ± for computing optimal order-up-to levels for a discrete time non-stationary inventory control model. We generalize a number of non-stationary inventory control models (which underlie larger models of supply chains) that include forecast updates, seasonality, information sharing, and exchange-ratē uctuations. This procedure is dierent from the existing ones in that it computes, in a recursive manner, the derivative of the cost function and not the cost function itself. It can also handle a much wider variety of¯uctuations in the problem parameters. In our computational testing it was found to be considerably faster than Dynamic Programming and In®nitesimal Perturbation Analysis.

Interfaces, Jan 1, 2007

With the widening disconnect between inventory-control research and practice, people debate the v... more With the widening disconnect between inventory-control research and practice, people debate the value of incremental theory building. While practitioners make decisions in a complex and uncoordinated environment, researchers often adopt a simplistic environment for the sake ...

Policing: An International Journal of …, Jan 1, 2006

... The Authors. Arvind Verma, Department of Criminal Justice, Indiana University, Bloomington, I... more ... The Authors. Arvind Verma, Department of Criminal Justice, Indiana University, Bloomington, Indiana, USA. Srinagesh Gavirneni, Johnson Graduate School of Management, Cornell University, Ithaca, New York, USA. Abstract. ...

Decision Analysis, Jan 1, 2009

We conducted a newsvendor experiment in which (i) the subjects were presented with multiple piece... more We conducted a newsvendor experiment in which (i) the subjects were presented with multiple pieces of information that they could possibly use to anchor their decision and (ii) the subjects participated either as individuals or in groups of three. The primary objective was to ...

European journal of operational research, Jan 1, 1999

This paper extends the real options literature by discussing an investment problem, where a firm ... more This paper extends the real options literature by discussing an investment problem, where a firm has to determine optimal investment timing and optimal capacity choice at the same time under conditions of irreversible investment expenditures and uncertainty in future demand. After the project is installed with a certain maximum capacity, this capacity is fixed as an upper boundary to the output and cannot be adjusted later on. It turns out that, in the framework of this once and for all decision, uncertainty in future demand leads to an increase in optimal installed capacity. But on the other hand it causes investment to be delayed to an extent that even small uncertainty makes waiting and accumulation of further information the optimal decision for large ranges of demand. Limiting the capacity which may be installed weakens this extreme effect of uncertainty.

Proceedings of the 31st …, Jan 1, 1999

In this paper, we conduct sensitivity analysis on a ranking and selection procedure for making mu... more In this paper, we conduct sensitivity analysis on a ranking and selection procedure for making multiple comparisons of systems that have multiple performance measures. The procedure combines multiple attribute utility theory with ranking and selection to select the best configuration from a set of K configurations using the indifference zone approach. Specifically, we consider sensitivity analysis on the weights generated by the multiple attribute utility assessment procedure. We demonstrate our analysis on a simulation model of a large project that has six performance measures.

Interfaces, Jan 1, 2007

Schlumberger and its competitors use seismic surveying, the process of mapping subterranean rock ... more Schlumberger and its competitors use seismic surveying, the process of mapping subterranean rock formations with reflected sound waves, as an important first step in identification and recovery of oil and gas reserves. This complicated logistical operation commonly lasts two to six ...

Reliability, IEEE Transactions on, Jan 1, 1995

Production and Operations …, Jan 1, 2010

We report on the information gathering and decision making efforts of subjects involved in newsve... more We report on the information gathering and decision making efforts of subjects involved in newsvendor decision making. Previous research in this area identified significant biases (e.g. anchoring and insufficient adjustment) in inventory decisions, but was unable to identify specific thought processes that led to these biases. We overcome this by using a "think-aloud" approach and recording the thought processes underlying the subjects' eventual decisions. A protocol analysis of the transcripts revealed the following interesting insights. Most of the decision makers sought the very basic information, but failed to seek the additional, but non-trivial, information that could have significantly influenced their decision. A majority of the subjects struggled to deal with the abstractness of the business setting and were very keen to know information on the product type, industry setting, decisions taken in the past, competitor's situation, and vendor environment that they felt would have put them on a firmer footing. A large portion of the participants correctly identified the overage and underage costs that needed to be considered, but failed to convert that information into the optimal order quantity. This suggests that the mathematics involved is not as intuitive as perceived by the research community. Finally, the bias of the order quantity was significantly influenced by the specific type of risk (overage or underage) that was identified closer in time to the decision making point which indicates the presence of a recency effect. That is, if a subject first mentioned the risk of excess inventory followed by the risk of unsatisfied demand, then his/her order quantity was high. On the other hand, if a subject first mentioned the risk of unsatisfied demand followed by the risk of excess inventory, then his/her order quantity was low.

Manufacturing & Service …, Jan 1, 1999

We consider a stochastic, capacitated production-inventory model in which the customer provides i... more We consider a stochastic, capacitated production-inventory model in which the customer provides information about the expected timing of future orders to the supplier. We allow for randomness in customer order arrivals as well as the quantity demanded, but work under the ...

Operations Research Letters, Jan 1, 2001

We consider a capacitated supply chain in which the supplier has the information of the (s,S) pol... more We consider a capacitated supply chain in which the supplier has the information of the (s,S) policy used by the retailer as well as the end-customer demand distribution. For the resulting inventory control problem at the supplier, optimal policies and structural properties were ...

Interfaces, Jan 1, 2004

In its efforts to provide automated meter-reading services to the utility industry, Schlumberger ... more In its efforts to provide automated meter-reading services to the utility industry, Schlumberger faces the problem of deploying receivers efficiently. In a geographic region, the problem is to install the minimum number of receivers on existing utility poles so that all wireless meters in that region can transmit their readings to at least one. Schlumberger first encountered this large-scale problem in a project it ran for Illinois Power. It found solving this problem manually very time consuming, and it had no ability to evaluate the robustness of the resulting solution. We proposed and implemented an optimization-based approach that reduced the duration and cost of implementations. In addition, we gave planners the ability to answer what-if questions.

Production and Operations …, Jan 1, 2008

N ew developments in corporate information technology such as enterprise resource planning system... more N ew developments in corporate information technology such as enterprise resource planning systems have significantly increased the flow of information among members of supply chains. However, the benefits of sharing information can vary depending on the supply chain structure and its operational characteristics. Most of the existing research has studied the impact of sharing downstream information (e.g., a manufacturer sharing information with its suppliers). We evaluate the benefits of sharing upstream yield information (e.g., a supplier sharing information with the manufacturer) in a two-stage serial supply chain in which the supplier has multiple internal processes and is faced with uncertain output due to yield losses. We are interested in determining when the sharing of the supplier's information is most beneficial to the manufacturer. After proposing an orderup-to type heuristic policy, we perform a detailed computational study and observe that this information is most beneficial when the supplier's yield variance is high and when end-customer demand variance is low. We also find that the manufacturer's backorder-to-holding cost ratio has little, if any, impact on the usefulness of information.