arXiv subjects

Denis Nekipelov

Publications and source records attributed to Denis Nekipelov.

18 recordsLinked to original sources

arXiv2026

Random Set Quantile Estimation of Partially Identified Discrete Response Models

Semiparametric discrete choice models are widely applied in economics, yet a fundamental tension arises when covariates are discrete as regression coefficients that are point identified under continuous regressors may become only partially identified. We show that this is not merely an identification problem but creates serious estimation pathologies. Classical estimators, including the maximum score estimator of Manski (1975), not only have population maximizers that are outer regions of the identified set (Komarova (2013)) but also converge to a random set drawn from a finite collection of deterministic regions that partition that outer region. To resolve this failure, we introduce the Random Set Quantile (RSQ) estimator which extracts the $\tau$-quantile of the classical estimator for $\tau \in (1/2,1)$. We prove this result for a class of widely used models, which includes binary/multinomial choice and discrete outcome panel data models. This construction is consistent and locally robust across the full parameter space, including precisely those configurations where classical estimators break down. A feasible implementation based on the $m$-out-of-$n$ bootstrap inherits both properties. We apply the methodology to the 2019 UK General Election, where the discrete support of Brexit-related covariates generates the partial identification our theory analyzes.

econ.EM↗

arXiv2024

Statistical Inference of Optimal Allocations I: Regularities and their Implications

In this paper, we develop a functional differentiability approach for solving statistical optimal allocation problems. We derive Hadamard differentiability of the value functions through analyzing the properties of the sorting operator using tools from geometric measure theory. Building on our Hadamard differentiability results, we apply the functional delta method to obtain the asymptotic properties of the value function process for the binary constrained optimal allocation problem and the plug-in ROC curve estimator. Moreover, the convexity of the optimal allocation value functions facilitates demonstrating the degeneracy of first order derivatives with respect to the policy. We then present a double / debiased estimator for the value functions. Importantly, the conditions that validate Hadamard differentiability justify the margin assumption from the statistical classification literature for the fast convergence rate of plug-in methods.

econ.EM↗

arXiv2024

Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict?

The advent of generative AI (GenAI) technology produces transformative impact on the content creation landscape, offering alternative approaches to produce diverse, high-quality content across media, thereby reshaping online ecosystems but also raising concerns about market over-saturation and the potential marginalization of human creativity. Our work introduces a competition model generalized from the Tullock contest to analyze the tension between human creators and GenAI. Our theory and simulations suggest that despite challenges, a stable equilibrium between human and AI-generated content is possible. Our work contributes to understanding the competitive dynamics in the content creation industry, offering insights into the future interplay between human creativity and technological advancements in GenAI.

cs.GT↗

arXiv2023

Sharp and Robust Estimation of Partially Identified Discrete Response Models

Semiparametric discrete choice models are widely used in a variety of practical applications. While these models are point identified in the presence of continuous covariates, they can become partially identified when covariates are discrete. In this paper we find that classical estimators, including the maximum score estimator, (Manski (1975)), loose their attractive statistical properties without point identification. First of all, they are not sharp with the estimator converging to an outer region of the identified set, (Komarova (2013)), and in many discrete designs it weakly converges to a random set. Second, they are not robust, with their distribution limit discontinuously changing with respect to the parameters of the model. We propose a novel class of estimators based on the concept of a quantile of a random set, which we show to be both sharp and robust. We demonstrate that our approach extends from cross-sectional settings to classical static and dynamic discrete panel data models.

econ.EM↗

arXiv2023

How Bad is Top-$K$ Recommendation under Competing Content Creators?

Content creators compete for exposure on recommendation platforms, and such strategic behavior leads to a dynamic shift over the content distribution. However, how the creators' competition impacts user welfare and how the relevance-driven recommendation influences the dynamics in the long run are still largely unknown. This work provides theoretical insights into these research questions. We model the creators' competition under the assumptions that: 1) the platform employs an innocuous top-$K$ recommendation policy; 2) user decisions follow the Random Utility model; 3) content creators compete for user engagement and, without knowing their utility function in hindsight, apply arbitrary no-regret learning algorithms to update their strategies. We study the user welfare guarantee through the lens of Price of Anarchy and show that the fraction of user welfare loss due to creator competition is always upper bounded by a small constant depending on $K$ and randomness in user decisions; we also prove the tightness of this bound. Our result discloses an intrinsic merit of the myopic approach to the recommendation, i.e., relevance-driven matching performs reasonably well in the long run, as long as users' decisions involve randomness and the platform provides reasonably many alternatives to its users.

cs.GT↗

arXiv2022

Bias-Variance Games

Firms engaged in electronic commerce increasingly rely on predictive analytics via machine-learning algorithms to drive a wide array of managerial decisions. The tuning of many standard machine learning algorithms can be understood as trading off bias (i.e., accuracy) with variance (i.e., precision) in the algorithm's predictions. The goal of this paper is to understand how competition between firms affects their strategic choice of such algorithms. To this end, we model the interaction of two firms choosing learning algorithms as a game and analyze its equilibria. Absent competition, players care only about the magnitude of predictive error and not its source. In contrast, our main result is that with competition, players prefer to incur error due to variance rather than due to bias, even at the cost of higher total error. In addition, we show that competition can have counterintuitive implications -- for example, reducing the error incurred by a firm's algorithm can be harmful to that firm -- but we provide conditions under which such phenomena do not occur. In addition to our theoretical analysis, we also validate our insights by applying our metrics to several publicly available datasets.

cs.GT↗

arXiv2022

Mechanism Redesign

This paper develops the theory of mechanism redesign by which an auctioneer can reoptimize an auction based on bid data collected from previous iterations of the auction on bidders from the same market. We give a direct method for estimation of the revenue of a counterfactual auction from the bids in the current auction. The estimator is a simple weighted order statistic of the bids and has the optimal error rate. Two applications of our estimator are A/B testing (a.k.a., randomized controlled trials) and instrumented optimization (i.e., revenue optimization subject to being able to do accurate inference of any counterfactual auction revenue).

cs.GT↗

arXiv2022

Learning from a Learning User for Optimal Recommendations

In real-world recommendation problems, especially those with a formidably large item space, users have to gradually learn to estimate the utility of any fresh recommendations from their experience about previously consumed items. This in turn affects their interaction dynamics with the system and can invalidate previous algorithms built on the omniscient user assumption. In this paper, we formalize a model to capture such "learning users" and design an efficient system-side learning solution, coined Noise-Robust Active Ellipsoid Search (RAES), to confront the challenges brought by the non-stationary feedback from such a learning user. Interestingly, we prove that the regret of RAES deteriorates gracefully as the convergence rate of user learning becomes worse, until reaching linear regret when the user's learning fails to converge. Experiments on synthetic datasets demonstrate the strength of RAES for such a contemporaneous system-user learning problem. Our study provides a novel perspective on modeling the feedback loop in recommendation problems.

cs.LG↗

arXiv2021

Learning the Optimal Recommendation from Explorative Users

We propose a new problem setting to study the sequential interactions between a recommender system and a user. Instead of assuming the user is omniscient, static, and explicit, as the classical practice does, we sketch a more realistic user behavior model, under which the user: 1) rejects recommendations if they are clearly worse than others; 2) updates her utility estimation based on rewards from her accepted recommendations; 3) withholds realized rewards from the system. We formulate the interactions between the system and such an explorative user in a $K$-armed bandit framework and study the problem of learning the optimal recommendation on the system side. We show that efficient system learning is still possible but is more difficult. In particular, the system can identify the best arm with probability at least $1-δ$ within $O(1/δ)$ interactions, and we prove this is tight. Our finding contrasts the result for the problem of best arm identification with fixed confidence, in which the best arm can be identified with probability $1-δ$ within $O(\log(1/δ))$ interactions. This gap illustrates the inevitable cost the system has to pay when it learns from an explorative user's revealed preferences on its recommendations rather than from the realized rewards.

cs.LG↗

arXiv2021

Regularized Orthogonal Machine Learning for Nonlinear Semiparametric Models

This paper proposes a Lasso-type estimator for a high-dimensional sparse parameter identified by a single index conditional moment restriction (CMR). In addition to this parameter, the moment function can also depend on a nuisance function, such as the propensity score or the conditional choice probability, which we estimate by modern machine learning tools. We first adjust the moment function so that the gradient of the future loss function is insensitive (formally, Neyman-orthogonal) with respect to the first-stage regularization bias, preserving the single index property. We then take the loss function to be an indefinite integral of the adjusted moment function with respect to the single index. The proposed Lasso estimator converges at the oracle rate, where the oracle knows the nuisance function and solves only the parametric problem. We demonstrate our method by estimating the short-term heterogeneous impact of Connecticut's Jobs First welfare reform experiment on women's welfare participation decision.

math.ST↗

arXiv2020

Privacy-aware identification

The paper redefines econometric identification under formal privacy constraints, particularly differential privacy (DP). Traditionally, econometrics focuses on point or partial identification, aiming to recover parameters precisely or within a deterministic set. However, DP introduces a fundamental challenge: information asymmetry between researchers and data curators results in DP outputs belonging to a potentially large collection of differentially private statistics, which is naturally described as a random set. Due to the finite-sample nature of the DP notion and mechanisms, identification must be reinterpreted as the ability to recover parameters in the limit of this random set. In the DP setting this limit may remain random which necessitates new theoretical tools, such as random set theory, to characterize parameter properties and practical methods, like proposed decision mappings by data curators, to restore point identification. We argue that privacy constraints push econometrics toward a broader framework where randomness and uncertainty are intrinsic features of identification, moving beyond classical approaches. By integrating DP, identification, and random sets, we offer a privacy-aware identification.

econ.EM↗

arXiv2020

Inference from Auction Prices

Econometric inference allows an analyst to back out the values of agents in a mechanism from the rules of the mechanism and bids of the agents. This paper gives an algorithm to solve the problem of inferring the values of agents in a dominant-strategy mechanism from the social choice function implemented by the mechanism and the per-unit prices paid by the agents (the agent bids are not observed). For single-dimensional agents, this inference problem is a multi-dimensional inversion of the payment identity and is feasible only if the payment identity is uniquely invertible. The inversion is unique for single-unit proportional weights social choice functions (common, for example, in bandwidth allocation); and its inverse can be found efficiently. This inversion is not unique for social choice functions that exhibit complementarities. Of independent interest, we extend a result of Rosen (1965), that the Nash equilbria of "concave games" are unique and pure, to an alternative notion of concavity based on Gale and Nikaido (1965).

cs.GT↗

arXiv2019

Dashboard Mechanisms for Online Marketplaces

This paper gives a theoretical model for design and analysis of mechanisms for online marketplaces where a bidding dashboard enables the bid-optimization of long-lived agents. We assume that a good allocation algorithm exists when given the true values of the agents and we develop online winner-pays-bid and all-pay mechanisms that implement the same outcome of the algorithm with the aid of a bidding dashboard. The bidding dashboards that we develop work in conjunction with the mechanism to guarantee that bidding according to the dashboard is strategically equivalent (with vanishing utility difference) to bidding truthfully in the sequential truthful implementation of the allocation algorithm. Our dashboard mechanism makes only a single call to the allocation algorithm in each stage.

cs.GT↗

arXiv2017

Efficiency Guarantees from Data

Analysis of efficiency of outcomes in game theoretic settings has been a main item of study at the intersection of economics and computer science. The notion of the price of anarchy takes a worst-case stance to efficiency analysis, considering instance independent guarantees of efficiency. We propose a data-dependent analog of the price of anarchy that refines this worst-case assuming access to samples of strategic behavior. We focus on auction settings, where the latter is non-trivial due to the private information held by participants. Our approach to bounding the efficiency from data is robust to statistical errors and mis-specification. Unlike traditional econometrics, which seek to learn the private information of players from observed behavior and then analyze properties of the outcome, we directly quantify the inefficiency without going through the private information. We apply our approach to datasets from a sponsored search auction system and find empirical results that are a significant improvement over bounds from worst-case analysis.

cs.GT↗

arXiv2017

Learning and Trust in Auction Markets

In this paper, we study behavior of bidders in an experimental launch of a new advertising auction platform by Zillow, as Zillow switched from negotiated contracts to using auctions in several geographically isolated markets. A unique feature of this experiment is that the bidders in this market are real estate agents that bid on their own behalf, not using third-party intermediaries. To help bidders, Zillow also provided a recommendation tool that suggested a bid for each bidder. Our main focus in this paper is on the decisions of bidders whether or not to adopt the platform-provided bid recommendation. We observe that a significant proportion of bidders do not use the recommended bid. Using the bid history of the agents we infer their value, and compare the agents' regret with their actual bidding history with results they would have obtained following the recommendation. We find that for half of the agents not following the recommendation, the increased effort of experimenting with alternate bids results in increased regret, i.e., they get decreased net value out of the system. The proportion of agents not following the recommendation slowly declines as markets mature, but it remains large in most markets that we observe. We argue that the main reason for this phenomenon is the lack of trust in the platform-provided tool. Our work provides an empirical insight into possible design choices for auction-based online advertising platforms. While search advertising platforms (such as Google or Bing) allow bidders to submit bids on their own, many display advertising platforms (such as Facebook) optimize bids on bidders' behalf and eliminate the need for bids. Our empirical analysis shows that the latter approach is preferred for markets where bidders are individuals, who don't have access to third party tools, and who may question the fairness of platform-provided suggestions.

cs.GT↗

arXiv2016

A/B Testing of Auctions

For many application areas A/B testing, which partitions users of a system into an A (control) and B (treatment) group to experiment between several application designs, enables Internet companies to optimize their services to the behavioral patterns of their users. Unfortunately, the A/B testing framework cannot be applied in a straightforward manner to applications like auctions where the users (a.k.a., bidders) submit bids before the partitioning into the A and B groups is made. This paper combines auction theoretic modeling with the A/B testing framework to develop methodology for A/B testing auctions. The accuracy of our method %, assuming the auction is directly comparable to ideal A/B testing where there is no interference between A and B. Our results are based on an extension and improved analysis of the inference method of Chawla et al. (2014).

cs.GT↗

arXiv2015

Econometrics for Learning Agents

The main goal of this paper is to develop a theory of inference of player valuations from observed data in the generalized second price auction without relying on the Nash equilibrium assumption. Existing work in Economics on inferring agent values from data relies on the assumption that all participant strategies are best responses of the observed play of other players, i.e. they constitute a Nash equilibrium. In this paper, we show how to perform inference relying on a weaker assumption instead: assuming that players are using some form of no-regret learning. Learning outcomes emerged in recent years as an attractive alternative to Nash equilibrium in analyzing game outcomes, modeling players who haven't reached a stable equilibrium, but rather use algorithmic learning, aiming to learn the best way to play from previous observations. In this paper we show how to infer values of players who use algorithmic learning strategies. Such inference is an important first step before we move to testing any learning theoretic behavioral model on auction data. We apply our techniques to a dataset from Microsoft's sponsored search ad auction system.

cs.GT↗

arXiv2014

Mechanism Design for Data Science

Good economic mechanisms depend on the preferences of participants in the mechanism. For example, the revenue-optimal auction for selling an item is parameterized by a reserve price, and the appropriate reserve price depends on how much the bidders are willing to pay. A mechanism designer can potentially learn about the participants' preferences by observing historical data from the mechanism; the designer could then update the mechanism in response to learned preferences to improve its performance. The challenge of such an approach is that the data corresponds to the actions of the participants and not their preferences. Preferences can potentially be inferred from actions but the degree of inference possible depends on the mechanism. In the optimal auction example, it is impossible to learn anything about preferences of bidders who are not willing to pay the reserve price. These bidders will not cast bids in the auction and, from historical bid data, the auctioneer could never learn that lowering the reserve price would give a higher revenue (even if it would). To address this impossibility, the auctioneer could sacrifice revenue optimality in the initial auction to obtain better inference properties so that the auction's parameters can be adapted to changing preferences in the future. This paper develops the theory for optimal mechanism design subject to good inferability.

cs.GT↗