These papers are working drafts of research which often appear in final form in academic journals. The published versions may differ from the working versions provided here.
SSRN Research Paper Series
The Social Science Research Network’s Research Paper Series includes working papers produced by Stanford GSB the Rock Center.
You may search for authors and topics and download copies of the work there.
New AI tools have the potential to change the way workers perform and learn, but little is known about their impacts on the job. In this paper, we study the staggered introduction of a generative AI-based conversational assistant…
Tropical deforestation for agriculture causes alarming CO2 emissions and loss of biodiversity and ecosystem services. To prevent this, various governments and multinational commodity-buyers offer a positive incentive for locals…
Digital goods can generate large benefits for consumers, but these benefits are largely unmeasured in the national accounts, including GDP and productivity. In this paper, we measure welfare gains from 10 popular digital goods…
Framework agreements (FAs) are procurement mechanisms used in private and public organizations by which a central procurement agency selects an assortment of products, typically through auctions, and then affiliated organizations…
This paper studies the stochastic linear bandit problem, where a decision-maker chooses actions from possibly time-dependent sets of vectors in ℝd and receives noisy rewards. The objective is to minimize regret, the difference…
I investigate the incentives for investing and operating grid-scale energy storage in electricity markets and the need for policies to complement investments with renewables. I develop a new dynamic equilibrium framework that…
The problem of how to genetically modify cells in order to maximize a certain cellular phenotype has taken center stage in drug development over the last few years (with, for example, genetically edited CAR-T, CAR-NK, and CAR-NKT…
Work in Progress
We explore the welfare implications of data-tracking technologies that enable firms to collect consumer data and use it for price discrimination. The model we develop centers around two features: competition between firms and…
Multi-armed bandit (MAB) algorithms are efficient approaches to reduce the opportunity cost of online experimentation and are used by companies to find the best product from periodically refreshed product catalogs. However, these…
We present a data-driven algorithm that advertisers can use to automate their digital ad-campaigns at online publishers. The algorithm enables the advertiser to search across available target audiences and ad-media to find the…
Predicting the responses of a cell under perturbations may bring important benefits to drug discovery and personalized therapeutics. In this work, we propose a novel graph variational Bayesian causal inference framework to predict…
Translating the relevance of preclinical models (in vitro, animal models, or organoids) to their relevance in humans presents an important challenge during drug development. The rising abundance of single-cell genomic data from…
Recent growing adoption of experimentation in practice has led to a surge of attention to multiarmed bandits as a technique to reduce the opportunity cost of online experiments. In this setting, a decision-maker sequentially…
With rising access to electronic health record data, application of artificial intelligence to create clinical risk prediction models has grown. A key component in designing these models is feature generation. Methods used to…
We study a Bayesian k -armed bandit problem in many-armed regime, when k ≥ √ T , with T the time horizon. We first show that subsampling is critical for designing optimal policies. Specifically, the standard UCB algorithm is sub…
We study actual bidding behavior when a new auction format gets introduced into the marketplace. More specifically, we investigate this question using a novel dataset on internet display advertising auctions that exploits a…
In repeated games, strategies are often evaluated by their ability to guarantee the performance of the single best action that is selected in hindsight, a property referred to as Hannan consistency, or no-regret. However, the…
Work in Progress
Online discussion platforms (often referred to as discussion boards) are designed for facilitating remote discussions between users. To stimulate engagement (e.g., participation in the discussion), these platforms offer arriving…