Screening Game Research Articles

Optimal Contract Design for a National Brand Manufacturer Under Store Brand Private Information

Problem definition: We study an optimal contract design problem for a national brand (NB) manufacturer, which sells her product via a retailer. The retailer may introduce his store brand (SB) with private cost information. The manufacturer estimates that the retailer’s SB cost may be high or low with certain probabilities and offers a menu of two-part tariff contracts to screen the retailer’s cost information. Methodology/results: Following the mechanism design theory, we formulate the problem as a two-stage screening game to analyze the strategic interaction between the two players under asymmetric information. Despite the complexity resulting from type-dependent reservation profit of the retailer, we derive the NB manufacturer’s optimal contracts analytically. We prove that there exists a unique threshold such that when the NB cost is below the threshold, the manufacturer offers both types of retailers incentive-compatible contracts; when the NB cost is above the threshold, the manufacturer offers a menu of contracts to shut down the low-type retailer and engage the high-type retailer only. Managerial implications: We find that when the NB product becomes more competitive (i.e., a higher quality or a lower cost), both the NB manufacturer and the retailer are better off. This result implies that under asymmetric information, the retailer has incentive to enhance the NB product quality or reduce its cost. Additionally, the private information is valuable to both members only when a contract without shutdown is offered. Moreover, such information is more valuable to both players when the NB product becomes more competitive. However, when SB quality improves or when SB cost decreases, the value of information may increase or decrease to both supply chain members. Finally, we derive a surprising result that under asymmetric information, the expected consumer surplus may increase because of a lower SB quality or a higher low-type SB cost. Funding: G. Xiao acknowledges financial support from the Research Grants Council of Hong Kong [General Research Fund Grant PolyU 15505621]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2021.0187 .

Deep Learning-Based ADHD and ADHD-RISK Classification Technology through the Recognition of Children’s Abnormal Behaviors during the Robot-Led ADHD Screening Game

Although attention deficit hyperactivity disorder (ADHD) in children is rising worldwide, fewer studies have focused on screening than on the treatment of ADHD. Most previous similar ADHD classification studies classified only ADHD and normal classes. However, medical professionals believe that better distinguishing the ADHD-RISK class will assist them socially and medically. We created a projection-based game in which we can see stimuli and responses to better understand children's abnormal behavior. The developed screening game is divided into 11 stages. Children play five games. Each game is divided into waiting and game stages; thus, 10 stages are created, and the additional waiting stage includes an explanation stage where the robot waits while explaining the first game. Herein, we classified normal, ADHD-RISK, and ADHD using skeleton data obtained through games for ADHD screening of children and a bidirectional long short-term memory-based deep learning model. We verified the importance of each stage by passing the feature for each stage through the channel attention layer. Consequently, the final classification accuracy of the three classes was 98.15% using bi-directional LSTM with channel attention model. Additionally, the attention scores obtained through the channel attention layer indicated that the data in the latter part of the game are heavily involved in learning the ADHD-RISK case. These results imply that for ADHD-RISK, the game is repeated, and children's attention decreases as they progress to the second half.

Deep-Learning-Based ADHD Classification Using Children's Skeleton Data Acquired through the ADHD Screening Game.

The identification of attention deficit hyperactivity disorder (ADHD) in children, which is increasing every year worldwide, is very important for early diagnosis and treatment. However, since ADHD is not a simple disease that can be diagnosed with a simple test, doctors require a large period of time and substantial effort for accurate diagnosis and treatment. Currently, ADHD classification studies using various datasets and machine learning or deep learning algorithms are actively being conducted for the screening diagnosis of ADHD. However, there has been no study of ADHD classification using only skeleton data. It was hypothesized that the main symptoms of ADHD, such as distraction, hyperactivity, and impulsivity, could be differentiated through skeleton data. Thus, we devised a game system for the screening and diagnosis of children's ADHD and acquired children's skeleton data using five Azure Kinect units equipped with depth sensors, while the game was being played. The game for screening diagnosis involves a robot first travelling on a specific path, after which the child must remember the path the robot took and then follow it. The skeleton data used in this study were divided into two categories: standby data, obtained when a child waits while the robot demonstrates the path; and game data, obtained when a child plays the game. The acquired data were classified using the RNN series of GRU, RNN, and LSTM algorithms; a bidirectional layer; and a weighted cross-entropy loss function. Among these, an LSTM algorithm using a bidirectional layer and a weighted cross-entropy loss function obtained a classification accuracy of 97.82%.

Evaluation of a game-based hearing screening program for identifying hearing loss in primary school-aged children

Objectives To evaluate a tablet-based hearing screening game in primary school aged children. To examine the prevalence of middle/outer ear pathology, hearing loss and spatial processing disorder in primary school aged children. Design The automated hearing test Sound Scouts was used as a screening tool, which measures hearing abnormalities through tests of speech-in-quiet/noise and tone-in-noise. Children who failed the screenings underwent follow up testing with pure tone audiometry, tympanometry, otoscopy, and the Listening in Spatialised Noise-Sentences test. Results of each test were compared to measure efficacy. Study Sample 1256 children aged 4–13 years from 8 primary schools. Results 111 children (8.84%) presented with evidence of middle/outer ear pathologies. 21 children (1.67%) had hearing loss in at least one ear. 30 children (2.52%) were diagnosed with spatial processing disorder. False positive rate was 5.01%, indicating that a relatively small proportion of the children who failed the screenings were subsequently shown to have normal auditory function. Conclusions A game based program testing sound detection and binaural speech processing can be effective in detecting undiagnosed hearing deficits, in large format school-based hearing screenings. Prevalence of hearing abnormalities in Victorian primary school aged children were established, highlighting the value of school hearing screening programs.

Program design and heterogeneous treatment effects of payments for environmental services

Payments for environmental service (PES) programs have been increasingly promulgated worldwide recently to secure broader environmental benefits and provide financial assistance to environmental custodians. This study highlights the incentive design of PES and ecosystem providers' behavioral responses using a standard principal-agent model. Based on a theoretical model characterized by a screening game, I establish a hypothesis that as long as the PES conditionality is implemented and enforced effectively, ecosystem service (ES) providers more likely to participate in the scheme perform better in terms of environmental resource conservation. An empirical analysis in this study uncovers heterogeneous treatment effects in favor of the ES providers whose propensity scores for scheme participation are relatively high. This result lends strong support to the hypothesis that the strict conditionality embedded in the PES scheme dissuades potential participants at a high risk of noncompliance from participating the program, which helps enhance the PES additionality.

Trichromatic enhanced dynamic color screening with a handheld gaming device

Beyond conventional isochromatic color plate screening, further quantification and classification has required substantial time and expense with the static Farnswell-Munsel 100 and Innova Rabin tests. Dynamic color screening games were developed for the Nintendo 3DS console.

SCREENING IN SPACE: RICH AND POOR CONSUMERS IN A LINEAR CITY

Unlike standard models of monopolistic screening (second-degree price discrimination), we consider a situation where consumers are heterogeneous not only vertically, in their willingness to pay, but also horizontally, in their tastes or "addresses'' a la Hotelling's Linear City. For such a screening game, a novel model is composed. We formulate the game as an optimization program, prove the existence of equilibria, develop a method to calculate equilibria, and characterize their properties. Namely, the solution structure of the resulting menu of contracts can be either a "chain of envy'' like in usual screening or a number of disconnected chains. Unlike usual screening, "almost all'' consumers get positive informational rent. Importantly, the model can be extended to oligopoly screening.

Coordination of a two-level supply chain with contracts

We consider the coordination of planning decisions of a single product in a supply chain composed of one supplier and one retailer, by using contracts. We assume that the retailer has the market power: he can impose his optimal replenishment plan to the supplier. Our aim is to minimize the supplier’s cost without increasing the retailer’s cost. To this end, the supplier (or a trusted third party) proposes to the retailer a contract, which is made of a replenishment plan and a side payment. This side payment compensates the increase of cost of the retailer due to the fact that the proposed replenishment plan may have a cost larger than the retailer’s optimal replenishment plan. We evaluate how much the supplier can gain by using contracts under several scenarios which depend on the side payment coverage. From a theoretical point of view, in all the scenarios, contracts may decrease the cost of the supplier by an arbitrarily large factor. We perfom experiments which measures the gain that can be obtained in practice on various instances types. If side payments are allowed, experiments show that the use of contracts decreases significantly the cost of the supplier, and that side payments on the holding costs are sufficient. We show that if there is no side payment, or if there is no constraint on the side payment, then the problem can be solved in polynomial time. On the contrary, if the side payment is limited to the holding costs of the retailer, then the problem is NP-hard. We extend this study to the case where the information is asymmetric (the supplier—or the trusted third entity—does not know all the costs of the retailer): in this case, the situation is modelled by a screening game.

Feasibility of TOWI as a cognitive training video game for children

Abstract Playing video games has not only become a ubiquitous pastime, but evidence suggests that it can also improve certain cognitive functions. This opportunity has led developers to create games whose goal is to provide tools related to cognitive training. However, several methodological problems have been observed regarding the interpretation of the effects encountered in cognitive training tools which, among other reasons, may stem from an incomplete understanding of how participants interact with the software. In this sense, a first step is to study how children react and engage in games in different contexts and whether any evidence of change after playing the games is encountered. Here, we evaluate the feasibility of using TOWI, a set of video games threaded together by a common narrative, as a cognitive training tool. Children played TOWI for several weeks at school or at their home. Cognitive performance before and after playing TOWI was compared using standardized neuropsychological tools as well as some cognitive screening games included as part of the TOWI platform. We found similar patterns of use in school and home as well as by boys and girls. Despite the exploratory nature of the current study, we found significant changes in several neuropsychological measures. We discuss the results in terms of the potential strengths that TOWI has as a training tool as well as in relation to the many pitfalls that lay ahead to achieve evidence of cognitive improvement, not only for TOWI, but for any tool developed for cognitive training.

Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning

Large-scale screening for potential threats with limited resources and capacity for screening is a problem of interest at airports, seaports, and other ports of entry. Adversaries can observe screening procedures and arrive at a time when there will be gaps in screening due to limited resource capacities. To capture this game between ports and adversaries, this problem has been previously represented as a Stackelberg game, referred to as a Threat Screening Game (TSG). Given the significant complexity associated with solving TSGs and uncertainty in arrivals of customers, existing work has assumed that screenees arrive and are allocated security resources at the beginning of the time-window. In practice, screenees such as airport passengers arrive in bursts correlated with flight time and are not bound by fixed time-windows. To address this, we propose an online threat screening model in which the screening strategy is determined adaptively as a passenger arrives while satisfying a hard bound on acceptable risk of not screening a threat. To solve the online problem, we first reformulate it as a Markov Decision Process (MDP) in which the hard bound on risk translates to a constraint on the action space and then solve the resultant MDP using Deep Reinforcement Learning (DRL). To this end, we provide a novel way to efficiently enforce linear inequality constraints on the action output in DRL. We show that our solution allows us to significantly reduce screenee wait time without compromising on the risk.

A game-theoretic analysis to defend against remote operating system fingerprinting

Remote Operating System (OS) Fingerprinting is a precursory step for launching attacks on the Internet. As a precaution against potential attacks, a remote machine can take a proactive counter-strategy to deceive fingerprinters. This is done by normalizing or mystifying the distinguishing behaviors in the packets. However, the unified modification causes a significant performance degradation to benign clients. Using a game-theoretic approach, we propose a selective and dynamic mechanism for counter-fingerprinting. We analyze the interaction between a fingerprinter and a target by modeling the problem as a signaling game and name it Defense-Game. Here, the defender observes the attacker’s actions and takes moves accordingly. We derive the Nash equilibrium strategy profiles based on the information gain analysis and propose a defense mechanism named Strategic-Defender. Our game-theoretic approach appropriately distinguishes a fingerprinter from a benign client and mystifies packets to confuse the fingerprinter, while minimizing the side effects on benign clients. The performance analysis shows that the defense mechanism can reduce the probability of success of the fingerprinter significantly, without deteriorating the overall performance of other clients. Later, we restructure the game as a screening game where the attacker plays as the follower so that it can recognize the type of the target and act accordingly. We name the game Attack-Game and solve it for the equilibrium strategies. We evaluate the performance of Strategic-Defender when the attacker takes actions according to the optimal results of Attack-Game. The evaluation results show that the attacker’s payoff may increase a bit, however, it is still too low to succeed.

Disclosure and Discovery with fairness

Two standard results in the litigation literature are that an informed party will not make a costly voluntary disclosure in a screening game and that the uninformed party will not engage in costly discovery in the signaling game. Both of these results rely on the assumption that the party making the offer can extract the entire surplus of settlement from the party receiving the offer. If the recipient of the offer has a demand for fairness, then the equilibrium offer will contain some monetary surplus. However, if utility is a continuous function of the surplus contained in the offer, the standard results from the literature are unchanged. Even though the equilibrium offer contains some surplus, it still pins the recipient of the offer to her dispute level of utility. As a result, the recipient of the offer will not engage in a costly transfer of information. The standard results can be overturned if the perceived fairness of the offer is a discontinuous function of the surplus it contains. In this model offers are coded as either fair or unfair, where all unfair offers impose a fixed utility penalty on the recipient if she accepts it. In such a model, the recipient of the offer will obtain a utility surplus (relative to her dispute level of utility) if the offer is perceived as fair. If this surplus is large enough, she will be willing to initiate a costly transfer of information.

An Innovative Mobile Game for Screening of Pediatric PTSD: a Study in Primary Care Settings.

Childhood is a developmental period associated with high risk of posttraumatic stress disorder (PTSD). Available validated pencil-and-paper diagnostic tools can be difficult for younger children to engage with given format and length. This study investigated psychometric properties of a briefer, more interactive game version of the Child PTSD Symptom Scale for DSM-5 (CPSS-5). Participants (n = 49) were children attending primary care appointments between 8 to 12years of age who were exposed to a DSM-5 Criterion A trauma. Participants completed the 6-item screening version of the CPSS-5 delivered in mobile tablet game format (the CPSS-5 Screen Team Game) and a self-report version of the full CPSS-5 (CPSS-5-SR) before their medical appointments. The mobile game showed adequate internal consistency (α = 0.79), was significantly positively correlated to the total CPSS-5-SR (r = .74, p < .001, n = 49), and with the total of the six identical items of the CPSS-5-SR (r = .79, p < .001, n = 49), demonstrating good convergent validity. Receiver operating characteristic (ROC) analyses revealed a cut-off score of 9 on the screening game as indicative of probable PTSD. Implementation of this screening game into primary care settings could be a low-burden method to greatly increase the detection of pediatric PTSD for referral to appropriate integrated care interventions.

Security Design in Non-Exclusive Markets with Asymmetric Information

We revisit the classic problem of a seller (e.g. firm) who is privately informed about her asset and needs to raise funds from uninformed buyers (e.g. investors) by issuing securities backed by her asset cash flows. In our setting, buyers post menus of contracts to screen the seller, but the seller cannot commit to accept contracts from only one buyer, i.e., markets are non-exclusive. We show that an equilibrium of this screening game always exists, it is unique and features semi-pooling allocations for a wide range of parameters. In equilibrium, the seller tranches her asset cash flows into a debt security (senior tranche) and a levered-equity security (junior tranche). Whereas the seller of a high quality asset only issues her senior tranche, the seller of a low quality asset issues both tranches but to distinct buyers. Consistent with this, whereas the senior tranche is priced at pooling valuation, the junior tranche is priced at low valuation. Our theory's positive predictions are consistent with recent empirical evidence on issuance and pricing of mortgage-backed securities, and we analyze its normative implications within the context of recent reforms aimed at enhancing transparency of financial markets.

Performance of a screening game on children and adults with and without binocular suppression

A rapid screening version of the PDI Check near vision game on the autostereoscopic barrier screen of the Nintendo 3DS aims to quickly estimate monocular visual acuity, stereopsis and deuteranopia without the need for occluder or goggles. We try to find ocular suppression since the dynamic acuity optotypes are presented with binocular rivalry.

Performance of a Quick Screening Version of the Nintendo 3DS PDI Check Game in Patients With Ocular Suppression.

To evaluate the ability of the PDI Check (PDI Check LLC, Anchorage, AK) near vision screening game to assess monocular acuity, stereopsis, suppression, and color. Children and adults consented to perform the PDI Check Quick Screening game following conventional near testing of patched Rosenbaum acuity, Titmus Fly stereo, Worth 4-dot, and Ishihara color. Time to complete each test and preferred method were recorded. A total of 77 patients (5 to 63 years old) attempted all tests. There was a positive correlation between the PDI Check and conventional tests for all visual tasks. Using previously determined instrument referral criteria, sensitivity/specificity was determined for right acuity (67%/91%), left acuity (55%/94%), stereopsis (87%/95%), red-green color (80%/99%), and ocular suppression (58%/98%). Screening time was 202 ± 96 versus 99 ± 42 seconds for the PDI Check and the game was preferred by 87%. The PDI Check provided a valid assessment of near vision in less than half the time of conventional testing without patches or goggles. This Quick Screening version may help eye technicians and physicians with time efficiency in the frequent task of near visual assessment. [J Pediatr Ophthalmol Strabismus. 2019;56(4):234-237.].

An empirical analysis of litigation with discovery: The role of fairness

We conduct an experimental analysis of discovery in both the signaling and screening games, where in both games an uninformed defendant may engage in costly discovery. Under the theory, the defendant should invoke the costly discovery procedure in the screening game, but not in the signaling game. In the later part of the screening game, discovery is invoked in 73% of all negotiations, which is strongly in the direction implied by theory. However, rather than lowering the defendant's expected cost, discovery is approximately a breakeven proposition. The reasons are that the defendant cannot, as implied by theory, extract the entire surplus from settlement with his offer and because there are excess disputes not predicted by the theory. In the signaling game we find, contra the theory, that discovery is invoked about 61% percent of the time, and this behavior persists into the later rounds of the experiment. While invoking discovery is predicted to reduce his payoff, the effect on the defendant's cost is not statistically different from zero. The offers the defendant receives after invoking discovery contain surplus not predicted under the theory. Thus, in both games, fairness appears to be important in explaining deviations from the theoretical predictions.

Operational Investment and Capital Structure Under Asset-Based Lending

Problem definition: Banks commonly use asset-based lending (ABL) to provide loans collateralized by a borrower firm’s inventory. We study the implications of ABL by examining how banks should determine asset-based loan terms based on firms’ operational characteristics (e.g., inventory salvage value and demand uncertainty) and how firms should make inventory stocking and capital structure decisions under asset-based borrowing constraints. Academic/practical relevance: Despite its widespread use for lending to small firms and those with large inventory investments, such as retailers, ABL has not been well studied in the literature. Methodology: We analyze ABL using a stylized single-period screening game of incomplete information between a business owner and a bank. The bank offers a menu of loans, where each loan offer is characterized by an interest rate and inventory advance rate. The owner then decides the inventory level and the mix of debt and equity with which to finance the firm’s operations. Our model captures the practical features of ABL, for example, the bank does not have the full knowledge of the firm’s demand prospects, and the inventory advance rate leads to a credit limit that increases in the firm’s inventory investment. Results: We show that ABL enables the bank to mitigate information asymmetry by screening firms and thereby controlling each firm type’s order quantity and leverage. We also obtain hypotheses describing the equilibrium loan contracts, capital structure, inventory investment, and bankruptcy outcomes. For instance, leverage leads to overinvestment resulting from the equity decision being endogenous to the model. Moreover, inventory advance rates are more sensitive to firms’ operational characteristics than interest rates. Managerial implications: Our study sheds light on the operational and financial implications of ABL by demonstrating how managers should make inventory and capital structure decisions while interacting with asset-based lenders. The online appendix is available at https://doi.org/10.1287/msom.2017.0670 .

Risk-Aversion and B2B Contracting Under Asymmetric Information: Evidence from Managed Print Services

Managed print service (MPS) is a type of information technology infrastructure service that provides centralized management of companies’ printing device fleets. In this paper, we estimate the provider’s risk preference in MPS using a proprietary data set from Xerox Corporation. We adopt a structural approach in our empirical analysis by modeling the contracting and usage processes of MPS as a two-stage screening game and building econometric models based on the equilibrium contracts and print volumes. Our econometric models have a unique hierarchical structure that allows clustering of printers with the same contracts in the same company, thereby capturing the B2B nature of MPS. We find that Xerox exhibits risk aversion in MPS contracting and provide institutional details of Xerox’s commission holdback policy that may cause the observed risk aversion. In the counterfactual analysis, we demonstrate the significance of the provider’s risk aversion and the implications of the commission holdback policy on equilibrium contracts, the expected earnings of Xerox and customer companies, and their preferences for printer models. The E-companion is available at https://doi.org/10.1287/opre.2017.1673 .

A complete characterization of equilibria in an intrinsic common agency screening game

We characterize the complete set of equilibrium allocations to an intrinsic common agency screening game as the set of solutions to self-generating optimization programs. We provide a complete characterization of equilibrium outcomes for regular environments by relying on techniques developed elsewhere for aggregate games and for the mechanism design delegation literature. The set of equilibria include those with non-differentiable payoffs and discontinuous choices, as well as equilibria that are smooth and continuous in types. We identify one equilibrium, the maximal equilibrium, which is the unique solution to a self-generating optimization program with the largest (or ``maximal'') domain, and the only equilibrium that is supported with bi-conjugate (i.e., least-concave) tariffs. The maximal equilibrium exhibits a n-fold distortion caused by each of the n principal's non-cooperative behavior in over-harvesting the agent's information rent. Furthermore, in any equilibrium, over any interval of types in which there is full separation, the agent's equilibrium action corresponds to the allocation in the maximal equilibrium. Under reasonable conditions, the maximal equilibrium maximizes the agent's information rent within the class of equilibrium allocations. When the principals' most-preferred equilibrium allocation differs from the maximal equilibrium, we demonstrate that the agent's choice function exhibits an interval of bunching over the worst agent types, and elsewhere corresponds with the maximal allocation. The optimal region of bunching trades off the principals' desire to constrain inefficient n-fold marginalizations of the agent's rent against the inefficiency of pooling agent types.