I document that the right tail of the firm size distribution systematically thickens with economic development. To rationalize this fact, I develop a parsimonious idea search model in which both aggregate growth and the firm size distribution are endogenously determined. The model features an asymptotic balanced growth path along which Gibrat's law holds at each date, and the right tail of the firm size distribution thickens monotonically toward Zipf's law. The model also implies that policies favoring large firms can improve welfare by better utilizing the diffusion externalities arising from idea search.

Using a large international sample of firms, we examine the relation between carbon management ability (CMA) and firm-level climate risk exposure. We find that CMA is negatively associated with climate risk exposure. More importantly, we show that firms with high-CMA managers tend to achieve a reduction in climate risk exposure through enhancing regulatory compliance (evidenced by fewer stakeholder rights violations), reducing environmental, social, and governance-related controversies, investing in research and development, undertaking more investment in environmental initiatives, and cultivating a favorable corporate culture. Cross-sectional analyses indicate that the negative association between CMA and climate risk exposure is stronger for firms in carbon-intensive sectors and firms with a dedicated corporate sustainability committee. Further, we reveal that CMA exerts a greater influence on climate risk exposure in stakeholder-oriented countries and in countries that have signed the Paris Agreement. Finally, we reveal that firms with high-CMA managers tend to have better financial performance. Overall, our findings indicate that CMA plays a crucial role in driving firms towards more sustainable and responsible business practices, leading to better corporate performance and enhanced corporate reputation.

We examine competition between two-sided platforms in a sharing economy. In sharing economies, workers self-schedule their supply based on the wage they receive. The platforms compete for workers as well as consumers. To attract workers, platforms use diverse wage schemes, including fixed commission rate, dynamic commission rate, and fixed wage. We develop a model to examine the impacts of the self-scheduled nature of the supply on competing platforms and the role of the wage scheme in the platform competition. We find that the price competition between platforms is more intense in a sharing economy compared with an economy with a fixed supply of workers if and only if the platforms serve more consumers and workers in the sharing economy than in the traditional economy, regardless of the wage scheme employed by the platforms. Further, any of the three wage schemes can be the best for the platforms and the worst for consumers and workers, depending on the market characteristics. In markets where the competition is more fierce on the demand side than on the supply side, the fixed-wage scheme results in the highest profits for the platforms and lowest surpluses for consumers and workers. In contrast, in markets where the competition on the supply side is more competitive, when the supply is highly (mildly) more competitive, the fixed-commission-rate (dynamic-commission-rate) scheme generates the highest profits for platforms, leading to the lowest surpluses for consumers and workers and the lowest social welfare. The differential impacts of the wage scheme on the price (demand side) and quantity (supply side) competition explain our findings. This paper was accepted by Kartik Hosanagar, information systems. Supplemental Material: The e-companion is available at https://doi.org/10.1287/mnsc.2022.4302 .

ABSTRACT: We argue that reductions in shareholder taxes should lower the cost of equity capital more for financially constrained firms than for other companies. Consistent with this prediction, we find that, following the 1997 (TRA) and the 2003 (JGTRRA) cuts in U.S. individual shareholder taxes, financially constrained firms enjoyed larger reductions in their cost of equity capital than did other firms. The results are consistent with the incidence of the tax reductions falling mostly on firms with both pressing needs for capital and disproportionate ownership by individuals, the only shareholders who benefited from the legislations. The paper provides a partial explanation for the seemingly puzzling finding that, following the unprecedented 2003 reduction in dividend tax rates, non-dividend-paying firms outperformed dividend-paying firms. The results suggest that it was not dividend status that mattered, but financial constraint, a common attribute of non-dividend-paying companies. Data Availability: Data are available from public sources identified in the study.

Multi-echelon stochastic inventory models with known demand distributions have long underpinned supply chain coordination, yielding first-best policies in centralized systems and contract mechanisms that induce decentralized agents to implement these policies. We revisit the classic two-echelon inventory model in an online learning setting with unknown demand, which necessitates rethinking both inventory control and coordination strategies. This setting poses three key challenges: (i) the overall loss function may be non-convex, limiting the applicability of standard online convex optimization methods; (ii) the multi-echelon structure creates information asymmetry, as the upstream agent observes only order quantities—potentially distorted by downstream learning—rather than true consumer demand; and (iii) realized inventory levels may exceed desired targets, further complicating learning dynamics. To address these challenges, we develop algorithms that combine online optimization with low-switching mechanisms and augmented loss functions, enabling effective learning despite these complexities. In the centralized setting, our algorithm converges to the first-best policy with low regret. In the decentralized setting, we design an adaptive coordination mechanism that yields favorable individual regret guarantees while learning the optimal contract, thereby incentivizing agents to implement the first-best policy and minimizing overall system regret. Numerical experiments demonstrate that our approach consistently outperforms standard benchmarks such as explore-then-exploit and vanilla online gradient descent, highlighting its robustness and practical relevance for supply chain coordination under demand uncertainty.

Problem definition: Online retailing platforms are increasingly relying on personalized recommender systems to help guide consumer choice. An important but understudied question in such settings is how many products to include in a recommendation set. In this work, we study how the number of recommended products influences consumers’ search and purchase behavior in an online personalized recommender system within a retargeting setting. Methodology/results: Via a field experiment involving 1.6 million consumers on an online retailing platform, we causally demonstrate that consumers’ likelihood of purchasing any product from the recommendation set first increases then decreases as the number of recommended products increases. Importantly, as much as 64% of the decrease in purchase probability (i.e., the choice overload effect) can be attributed to a decrease in consumers’ likelihood of starting a search (i.e., clicking on any recommended product). We discuss the possible behavioral mechanisms driving these results and analyze how these effects could be heterogeneous across different product categories, price ranges, and timing. Managerial implications: This work presents real-world experimental evidence for the choice overload effect in online retailing platforms, highlights the important role of consumer search behavior in driving this effect, and sheds light on when and how limiting the number of options in a recommender system may be beneficial to online retailers. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0659 .

Cold start describes a commonly recognized challenge for online advertising platforms: with limited data, the machine learning system cannot accurately estimate the click-through rates (CTR) of new ads and, in turn, cannot efficiently price these new ads or match them with platform users. Traditional cold start algorithms often focus on improving the learning rates of CTR for new ads to improve short-term revenue, but unsuccessful cold start can prompt advertisers to leave the platform, decreasing the thickness of the ad marketplace. To address these issues, we build a data-driven optimization model that captures the essential trade-off between short-term revenue and long-term market thickness on the platform. Based on duality theory and bandit algorithms, we develop the shadow bidding with learning (SBL) algorithms with a provable regret upper bound of [Formula: see text], where K is the number of ads and d captures the error magnitude of the underlying machine learning oracle for predicting CTR. Our proposed algorithms can be implemented in a real online advertising system with minimal adjustments. To demonstrate this practicality, we have collaborated with a large-scale video-sharing platform, conducting a novel, two-sided randomized field experiment to examine the effectiveness of our SBL algorithm. Our results show that the algorithm increased the cold start success rate by 61.62% while compromising short-term revenue by only 0.717%. Our algorithm has also boosted the platform’s overall market thickness by 3.13% and its long-term advertising revenue by (at least) 5.35%. Our study bridges the gap between the theory of bandit algorithms and the practice of cold start in online advertising, highlighting the value of well-designed cold start algorithms for online advertising platforms. This paper was accepted by Gabriel Weintraub, revenue management and market analytics. Supplemental Material: Data and the online appendices are available at https://doi.org/10.1287/mnsc.2022.4550 .