Papers

We study the route-set allocation problem between end nodes in capacity-constrained flow networks with transfer costs. We introduce an origin–destination (OD) bidding language, in which a participant bids for bounded conic combinations of inlet–outlet–quantity licences and the mechanism performs the routing through a network-flow optimising winner-determination problem. We then study payment rules for the OD mechanism. Under a restricted model with openly and uniformly priced sources and bidders who are indifferent to the source of the gas, the Vickrey–Clarke–Groves (VCG) payment is core-stable; the key structural fact is that in this regime some optimal aggregate flows never use a physical pipe in both directions, so the winner-determination problem reduces to a single-commodity network flow whose value is submodular in the set of active bidders. If source access is allowed to depend on the individual consumer – a realistic feature, e.g. when gas deals are embedded in bilateral political bargaining – the reduction fails and VCG payments may lie strictly outside the core. For this general model we propose a dual (nodal) pricing rule derived from the shadow prices of the flow-conservation constraints, and prove it is always core-stable, at the cost of dominant-strategy incentive compatibility. Illustrative examples accompany each result.

Social scientists routinely convert text into covariates like topic shares, ideal points or sentiment scores, and insert them into statistical models of interest. This two-step design is convenient, but it is rarely guided by theory: little tells the analyst which text-based covariates to construct or include. Each approach embodies contestable measurement choices, and competing operationalizations of the same construct can support different conclusions, so a single research question gives rise to a menu of competing regression models. Which text constructed covariates belong in a model, and in what functional form, is thus a problem of model uncertainty. We propose spike-and-slab generalized additive models (SSGAMs), which jointly select covariates and determine whether their effects are linear or nonlinear. We illustrate the approach with the communication of a powerful unelected institution, asking which of 45 competing text indicators from 224 monthly European Central Bank press conferences, spanning late 2002 to mid-2025, track professional inflation expectations. A sparse set is selected; widely used alternatives, and every tested nonlinear effect, carry no incremental information.

Pediatric vaccine procurement for low- and lower-middle-income countries (LICs and LMICs) requires long-term coordination across heterogeneous vaccine markets, competing stakeholder objectives, and uncertain demand, yet tenders are currently scheduled as a series of independent renewals. We extend the Hypothetically Coordinated Vaccine Market (HCVM) framework to schedule multi-year tenders with flexible lengths and all-unit quantity discounts, and compare three objectives: a balanced coordinatingentity model (UG), a social-benefit model that minimizes missed doses (SB), and a producer profit-maximizing model (MP). Using UNICEF ten-year demand forecasts and 30 demand replications across six discount scenarios, we find that the procurement objective, not demand variability, drives cost-to-tender and schedule complexity. Quantity discounts favor large producers, concentrating the market and increasing supply chain vulnerability. Discount effectiveness depends on market maturity rather than valency: pentavalent and hexavalent vaccines are already near their price floor, and among monovalent vaccines only rotavirus responds to discounts, whereas HPV and PCV remain too expensive to compete. Removing pentavalent and hexavalent vaccines from the procurement pool sharply increases missed doses. These results give planners practical guidance on objective selection, discount design, and protecting access to combination vaccines.

We study two hypotheses for how a human role in production could persist despite growing AI capabilities. Humans might have a durable advantage in taste, designing better products even as AI agents automate routine tasks, or consumers might intrinsically prefer that humans have a hand in production. In our experiment, participants act as producers, designing computer games with an AI coding agent, and as consumers who buy them. Across three studies (N = 1,025), we find no evidence for either hypothesis. Games designed by an AI on its own outperform those of human producers, including both amateurs and professional creatives. Human producers do not anticipate the AI's advantage. Revealing whether a game is human-designed does not raise consumers' willingness to pay for the product.

We study whether stock disclosures by recognizable investors generate abnormal market reactions beyond the reactions produced by comparable but non-recognizable managers. We define the Buffett effect as the incremental abnormal return to a disclosed new position that is attributable to the public recognition of the disclosing investor. We construct a recognition index from Wikipedia pageviews and ProQuest news mentions. Using data from 2000 to 2025 we compare market reaction to disclosures of 24 recognizable discretionary funds with disclosures of 24 matched control funds. New-position disclosures by recognizable managers generate a positive disclosure premium over the filing date and the following trading days, and the premium increases with investor recognition. We construct calendar-time portfolios that mechanically copy each group's disclosed purchases and find that copying the most recognized investors earns a significant alpha that persists for months and does not reverse. The evidence is most consistent with an entangled attention-information channel: investor recognition directs scarce investor attention toward selected disclosures, and the information revealed in those disclosures is then capitalized into prices.

Generative AI makes options cheap and shifts the bottleneck of creative work from generating options to screening them. We argue that AI's value depends on whether its options arrive before or after the team's screen. In our model, early options compete for a place in the portfolio; late options arrive after that competition and are kept unscreened. In a preregistered experiment, we randomly assigned 148 three-person teams to five schedules of access to the same language model during a product-design task with timed search and selection stages. Moving the same 15 minutes of access from search to selection lowered expert-rated creativity by 0.62 standard deviations, although teams used the model at similar rates. Platform logs locate the difference at the screen. Early access enlarged the pool of ideas fivefold, and teams pruned it. Late-access teams reached the screen with the same small pool as teams without AI and then searched again, devoting 29% of their selection-stage queries to generating new options, compared with 11% for teams with access throughout. Late access added breadth, not quality: these teams submitted 73% more proposals than did teams without AI. Language-model judges detected the benefit of access but not the cost of late timing.

When producers in a network compete in quantities, an innovator's profit contains none of the change in allocative efficiency that its innovation causes, whether a gain or a loss, because its own choices are optimal and other effects on its profit are transfers. A process innovator also forgoes its own and downstream markups on the output its innovation adds at a fixed allocation, worth 14 to 26 percent of its cost saving for U.S. public firms in 2015. For innovators accounting for 68 percent of sales, the change in allocative efficiency exceeds a tenth of the private return. In a Markov R&D game, reallocation of R&D across firms is likewise external to the innovator. Rivals' profits and market values can misstate the welfare cost of business stealing from them even in sign. With estimated spillovers, the social return to R&D is 5.39 times the private return, against 2.53 in output-based accounting with estimated business stealing, mainly because that accounting credits the innovator with its rivals' lost sales.

We build a labor market in which AI systems enter as workers: they apply for jobs, pass screenings, get hired, and get dismissed, alongside humans. Firms post vacancies, workers search with friction, and product demand slopes downward. Across 30 seeded runs per configuration, AI entry at 70% of the human wage raises unemployment by 4.1 percentage points (95% CI 3.5 to 4.6) and leaves 12.2 fewer humans employed (CI 10.5 to 13.9). Layoffs dominate when AI is much cheaper than humans: the layoff margin accounts for 7.2 of the lost jobs and reduced hiring for 5.0, though most dismissed workers find work again. A wider price gap reduces displacement, because cheap AI makes firms expand: at price parity, with zero dismissals, the unemployment effect is largest at 9.2 points (CI 8.6 to 9.9), all of it through hiring. That parity result survives cutting AI applications from five per period to one. Demand elasticity decides how many workers AI displaces. Screening changes who gets hired and leaves the displacement total unchanged.

Bus operations are inherently unstable—buses initially dispatched at equal headways will inevitably end up bunching up. This issue exacerbates passenger waiting times, creates load imbalances between buses, and undermines service reliability. Reinforcement learning (RL) has proven highly effective for mitigating bus bunching and outperforms traditional model-based approaches. However, existing RL approaches require agents to continuously interact with the environment, which potentially disrupts the bus system before effective policies are learned. This paper proposes an Offline Graph-based Multi-agent Actor-Critic (Offline-GMAC) method that trains bus holding policies using only readily available logged GPS data collected during normal uncontrolled operations, thereby eliminating the need for disruptive online interaction or exploration. The method employs general graph neural networks for multi-agent credit assignment. A key innovation of our method is a data augmentation scheme that synthesizes unperformed holding actions from historical uncontrolled bus trajectories. The scheme exploits the equivalence between stochastic link travel time delays and deliberate holding interventions. Under mild assumptions, we prove that the 1-Wasserstein distance between synthesized and target state transition distributions is bounded above by a term that scales linearly with the standard deviation of link travel times plus a tunable synthesis-dependent term. Evaluations using real-world bus data demonstrate that the proposed offline method achieves performance comparable to, and in some cases, even better than its online counterpart.

Pregnancy can disrupt schooling before infant care begins. We use monthly histories from the National Longitudinal Survey of Youth 1997 to study school interruptions during pregnancy and after childbirth and whether students later return to school or earn a diploma or GED. We jointly model conception and sustained interruptions in enrollment, allowing persistent unobserved differences to affect both processes. Under the timing-of-events identifying assumptions, pregnancy raises the monthly interruption rate to nearly four times the rate without pregnancy. Interruption rates are elevated before delivery and remain elevated afterward. After an interruption, students already exposed to pregnancy return to school and earn a diploma or GED less often within two years. These findings show that schooling disruption is already present during pregnancy, before the additional demands of infant care begin.

Who should give up compute for AI safety research: customers or capability research? Safety paid for by customers delays no capability. Safety paid for by research slows the frontier, which gives knowledge more time to accumulate but postpones what a finished frontier provides. In a frontier-takeoff model, the cheaper source at a given allocation is set by a threshold in demand capacity. Demand capacity is the share of compute customers can use once the frontier is finished. Research should pay too only when demand capacity lies below the threshold. Where the threshold sits depends on how fast the value of customer services diminishes. In the calibration it rises with the service budget, because each further unit taken from customers costs them more. Safety paid for by customers should come early: its ratio to customer compute falls over the takeoff unless safety productivity rises fast. In a calibration with a tight service budget, early customer-funded safety lowers the probability of catastrophe from 75 to 51 percent. That is within one point of the best rule found that may also slow research.

We examine business models that could support frontier AI companies' valuations and the public evidence of plans to earn income beyond selling model access. Reverse cash-flow calculations for OpenAI and Anthropic yield combined year-ten revenue requirements of \$2.79 trillion or \$733 billion, depending on financial assumptions. Public documents identify proposed payments and ownership interests that could supply additional income, such as through partnerships on pharmaceuticals, robotics, or materials science. We discuss how these arrangements relate to firm boundaries and value capture.

Aggregate linear demand systems can be micro-founded by a population of heterogeneous consumers making discrete choices. They can also be extended to incorporate income effects. I prove these results and show how to structurally estimate this class of models using only market-level data. The distribution of consumer preferences is recovered by disciplining the corner solutions with aggregate terms only. This approach allows for the same richness of Berry, Levinsohn, and Pakes (1995) [BLP] while retaining the analytical and computational advantages of linear demand: it does not require exogenously fixing market size, allows for heterogeneity in choice sets, and results in a flexible substitution matrix which varies endogenously as different consumers enter/exit the market. The discrete-choice microfoundation facilitates welfare analysis and the flexible measurement of markups an cost pass-throughs, among a wide range of other applications.

AI shopping assistants increasingly influence which products consumers consider. We study retail assortment planning under AI mediation, where a retailer chooses a catalog, an AI intermediary forms a customer-facing shortlist, and the customer chooses from that shortlist according to a multinomial logit model. We consider both deterministic mediation, in which the AI follows a fixed segment-specific ranking, and stochastic mediation based on the Plackett-Luce model. Empirically, we construct a dataset of product rankings from leading AI models, estimate Plackett-Luce ranking models, and evaluate their predictive performance on held-out assortments. Combining these estimates with synthetic customer preferences, we find that accounting for AI mediation can materially change optimal assortments and revenue. Across the tested capacity configurations, ignoring mediation yields mean revenue losses between 2.52% and 11.37% relative to the PL optimum. A much simpler deterministic plug-in, based only on the ordering of fitted AI utilities, performs substantially better, with mean losses of at most 0.53%. Motivated by this performance, we study assortment optimization under deterministic mediation. We characterize its computational complexity and show that, for any fixed number of customer segments, the problem admits a fully polynomial-time approximation scheme.

I study how intermediary liquidity affects mortgage resolution using 1.9 million Ginnie Mae buyout options from 2019 to 2022. When funding markets froze in 2020, nonbank issuers repurchased far fewer delinquent loans than depositories servicing loans in the same pools and, within the same issuer and month, shifted repurchases away from large balances, the loans that require the most cash. About $19 billion of repurchases were delayed, and most were completed later. A model of rationing by value per dollar of cash explains this pattern and shows that borrower information is most valuable when funding is intermediate.

Mental accounting is usually explained by self-control, and two-stage budgeting by separable preferences. We propose a third explanation based on sellers' market power. A consumer who commits to spend a fixed number of dollars in a category has unit-elastic demand, so a seller in that category gains nothing by restricting quantity. A consumer who instead targets a fixed physical quantity has perfectly inelastic demand, a case that a monopolist can exploit. We characterize the commitments that remove a seller's incentive to mark up prices, and show that the fixed dollar budget is the least restrictive. We then show that what matters is budget rigidity rather than separability of preferences. A consumer who re-optimizes her category budget when prices change is insulated from market power only if categories are substitutes; a rigid budget insulates her in every case. Mental accounting can therefore be read as a commitment device against markups, a rationale that is separate from the self-control motive in the existing literature.

After decades of microfinance expansion and despite charging higher interest rates, moneylenders continue to exist alongside microfinance institutions (MFIs). We develop a dynamic model with ex post moral hazard, in which borrowers use MFI loans for production and can rely on moneylenders for bridge loans after shocks to repay MFIs and preserve future access to MFI credit. We then study how MFI competition shapes the coexistence between MFIs and moneylenders. The effect of competition on MFI credit is ambiguous: it may weaken repayment incentives or replace moneylenders as bridge lenders. By contrast, competition unambiguously reduces moneylender credit. In a village-level randomized expansion in Bangladesh, stratified by baseline MFI presence, one additional MFI reduces the number of moneylender loans by roughly 30-40% two to three years later, with no detectable effect on MFI or overall borrowing. This suggests that, in markets where MFIs rely primarily on the threat of exclusion to induce repayment and moneylenders provide emergency finance, gains from additional MFI entry may be greater in less saturated areas.

Employers in Germany argue that collective agreements restrict their flexibility concerning working hours. Using data from the IAB Establishment Panel for the years 2008 to 2024, we investigate working-time adjustments after exit from collective bargaining. We find that exit is associated with only a modest increase in weekly working hours of around 0.3 to 0.6 per cent using fixed-effects and event-study models, corresponding to eight to thirteen additional minutes per week. This adjustment occurs shortly after leaving collective bargaining coverage. We further find no evidence that other margins of working-time adjustment, such as Saturday or Sunday work, are used more extensively after exit. In contrast to previous survey evidence, our findings call into question that working-hours constraints are one of the main drivers of exit from collective bargaining coverage.

Evidence that pricing algorithms collude comes from markets in which every seller runs the same algorithm. We ask what happens when they do not. Four language models from four providers, each at its cheapest tier, price in a four-firm logit Bertrand market without communication, in every homogeneous, two-by-two and fully mixed composi- tion (11 cells, 20 runs, 200 periods). Collusion is a property of the model: Claude and Gemini markets reach 72 to 79 percent of the monopoly rent, DeepSeek markets 24 percent, and GPT markets none, though GPT prices drift above the monopoly level rather than toward competition. Mixing does not reduce collusion by itself. Markets containing Gemini, which opens at the highest price and settles highest, are more col- lusive than the homogeneous markets they are built from; markets containing Claude, which opens lower and follows its rivals down, are less so; and only the fully mixed market is significantly less collusive than the average homogeneous one. Stability de- pends on the least stable participant: two GPT firms suffice to keep any market from converging. Inside mixed markets the rent is shared in a transitive order, DeepSeek over Claude over Gemini over GPT, that inverts the anchor ranking. The model that raises the price collects the least of the rent, as the price-leadership model predicts.

Can a regulator promise both a risk ceiling and a development deadline when safety productivity is unknown? A ceiling below the final model's unprotected hazard requires a minimum stock of safety knowledge, so both promises hold only if weak research can be ruled out. Learning first and then replaying development, with spare compute in safety, comes close to that minimum. In a calibration with only state risk, constant safety yield, and full knowledge transfer, it needs only 3.3 percent more productivity than the necessary bound. Customer services pay for the guarantee. Rules that fix compute allocation fix dates, not risk.

We study differences in economic outcomes by perceived skin tone among African Americans using full-count U.S. decennial census data from the late-19th and early-20th centuries. Comparing children coded as "Black" or "Mulatto" by census enumerators and linking these children across population censuses, we first document large gaps in educational attainment and income among African Americans with darker and lighter perceived skin tones. To disentangle the drivers of these gaps, we identify all 35,992 families in which enumerators assigned same-gender siblings different Black/Mulatto classifications. Relative to sisters coded as Mulatto, sisters coded as Black had lower educational attainment, were less likely to marry, and had less-educated, likely lower-earning husbands. These patterns are consistent with more severe contemporaneous discrimination against African American women with darker perceived skin tones. In contrast, we find similar educational attainment, marital outcomes, and incomes among differently-classified brothers. Men perceived as African Americans of any skin tone faced similar contemporaneous discrimination, consistent with the "one-drop" racial classification rule that grouped together individuals with any known Black ancestry. Lower incomes for African American men perceived as having darker skin tone in the general population were driven by differences in opportunities and resources that varied across families, likely reflecting the impacts of historical or family-level discrimination.

Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values. Stated-preference economics has faced this problem for decades. It judges survey responses without knowing the true value, through a framework of validity and related concepts: content, construct, and criterion validity, reliability, incentive compatibility, and consequentiality. We argue that this framework is a general method for evaluating language models, and we set out what each concept means for LLM evaluation. We demonstrate the approach using a published water-quality stated preference economic valuation survey (Vossler et al. 2023) administered to six models. In this economic application, the validity tests take the form of predictions from economic theory: demand should slope down, and willingness to pay should respond to the scope of the good and to income. The tests separate the models sharply. Two older models fail the most basic test at a household income level of \$75,000, and the two newest pass every test of theoretical validity we can score, but diverge on convergent validity. Passing validity tests shows that a model's answers are coherent, not that they are correct.

This paper extends Goodwin's (1967) predator-prey growth-cycle model to incorporate the negative impact of Opioid Use Disorder (OUD) on labor productivity. Using U.S. state-level data for 1998–2019, we first document that deteriorations in the labor share are followed by rising drug-induced mortality. We then build this link into the model through a novel discrete-choice mechanism in which the probability of OUD decreases with the wage share, so when real wages fail to keep pace with productivity growth, opioid use rises. This behavioral health channel feeds back into the economy through a productivity damage function. Applying the existence part of the Andronov-Hopf bifurcation theorem, we show that the resulting three-dimensional nonlinear system admits a limit cycle, as confirmed by our numerical simulations. Along the cycle, rising OUD paradoxically raises the employment rate, as falling productivity requires more labor per unit of output; across steady states, however, higher OUD prevalence is associated with a lower employment rate, consistent with evidence that opioid use disorder reduces labor force participation. Moreover, our numerical experiments show that OUD sensitivity to income widens fluctuations, while productivity sensitivity to OUD counterintuitively compresses them through a self-correcting feedback that speeds the recovery of the wage share. Policies that weaken the link between income and OUD, such as stronger social safety nets, stabilize the resulting dynamics.

We introduce a class of demand models for market-level data. The models can be estimated by linear instrumental variables regression while accommodating substitution patterns far richer than the logit and nested logit models they embed. They are built from closed-form inverse market share functions through a generator analogous to McFadden's generalized extreme value generating function, but acting on market shares. Constructive results allow arbitrary nesting structures, including overlapping nests and partial membership, yielding inverse-share analogs of generalized extreme value models. The class is consistent with utility maximization and strictly larger than the class of regular additive random utility models.

I estimate firm-level capital-, labor-, and material-augmenting productivity for Chinese manufacturing, 1998–2008, and the effect of state-owned enterprise (SOE) privatization on each. Results show technological change is strongly biased toward capital and labor. Private firms operate above SOEs on capital and labor, but below on materials. Privatization raises labor-augmenting productivity right after the transition, a front-loaded gain that fades on the full panel but persists among 1998 incumbents. It leaves capital-augmenting productivity no higher and modestly lowers materials. The SOE sector's catch-up runs through restructuring of the plants the state kept, with exit of overstaffed plants adding to the labor gain.

The answers to many economic questions depend on the slope and curvature of demand. Estimating demand for differentiated products entails a trade-off between flexibility and scalability. Existing nonparametric approaches face a curse of dimensionality in the number of products. I develop a scalable nonparametric approach using market-level data that overcomes this curse through economically motivated restrictions embedded in many standard models. Simulations and an application to the U.S. beer market demonstrate flexibility in demand slope and curvature, with consequential differences in counterfactual price responses. Estimation in the application takes seconds, versus several hours for a random coefficient nested logit model.

Non-governmental organizations often compete for funding while valuing similar social outcomes. Fundraising may expand total giving to a cause or redirect a given funding pool toward the focal organization. This paper studies how cross-organizational purpose alignment changes the composition of such competition. The analysis separates two effects of fundraising: marginal lift in aggregate funding and marginal shift of funding between organizations. Incomplete alignment creates a wedge between an NGO's marginal mission return and the aggregate mission return that is proportional to shift minus lift. When NGOs choose among fundraising technologies, greater purpose alignment shifts effort toward the relatively lift-intensive technology. Relative to the aggregate mission benchmark, incompletely aligned NGOs choose portfolios that are too shift-intensive. A uniform restriction on fundraising may change total effort but cannot generally correct this composition distortion; correcting the portfolio requires changing relative incentives across technologies. A simple microfoundation interprets cause promotion as lift and organization promotion as shift. Productivity differences preserve reallocation when it raises mission output, while organization-specific benefits restore rivalry even under complete alignment. The model therefore predicts how a common purpose changes the form of competition even when its effect on the level of competition is ambiguous.

An organization may bind future decision makers through a commitment over its own lifespan. This paper studies that choice for philanthropic foundations. A foundation may commit to terminate, commit to institutional continuity, or leave termination to future discretion. Discretion preserves state-contingent stopping. Perpetuity instead raises investment in foundation-specific organizational capital whose return is partly lost upon termination. A terminal commitment limits excessive continuation when future governing bodies obtain private benefits from organizational survival. A canonical model yields nonempty regions in which each regime is optimal, while a finite-horizon extension endogenizes the terminal date. Perpetuity is optimal when organizational capital is sufficiently productive relative to the cost of continuing in bad states; discretion is optimal when stopping flexibility is valuable and governance is aligned; a finite lifespan is optimal when survival incentives create sufficiently costly entrenchment. Organizational lifespan is therefore a distinct commitment margin.

Classical growth theory places physical productivity at the center of economic growth. In modern service-based economies, however, growth increasingly means creating higher-valued products rather than increasing output quantities. This paper develops a theory of value growth based on a socially and institutionally sustained value scale. The framework unifies value creation, finance, and distribution and offers an account of major patterns in US economic history. The proposed framework is intended as a new approach to macroeconomic analysis and policy making.

Algorithmic recommendations can help participants navigate large matching markets. For example, recommendations for school and college choices may reduce information frictions and disparities in access to high-performing programs. At scale, however, recommenders in capacity-constrained settings can be self-defeating: if they steer too many users toward the same items, then even users who were originally predicted to have a high chance of matching to an item may not, due to increased competition. In this paper, we formalize this phenomenon of recommendation-induced congestion; motivated by the NYC high school match, we show that naive recommendations can cause sharp decreases in program acceptance rates, most affecting applicants with the fewest nearby options. Next, we propose and theoretically analyze a congestion-aware, bilevel optimize-and-simulate approach to allocate recommendations and improve match outcomes safely, in equilibrium. Finally, we deploy this approach in the 2025-26 admissions cycle of the NYC high school match, aiming to reduce disparities by highlighting personalized lists of nearby, high-performing programs where an applicant has a high predicted offer likelihood. In a randomized controlled trial, we find that 16.4% of treatment applicants ranked a recommended program, versus 10.5% of control applicants who ranked a program they would have been recommended (57% relative increase; $p$=0.011); 5.6% of treatment applicants matched to such a program, versus 3.3% of control applicants (71% relative increase; $p$=0.071); further, no treatment applicant was rejected from a recommended program. Our findings suggest that recommenders should be analyzed and designed as market-shaping interventions.