Corpus ID: 222125220

On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach

@article{Komiyama2020OnSD,
  title={On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach},
  author={Junpei Komiyama and Shunya Noda},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.01079}
}
We analyze statistical discrimination using a multi-armed bandit model where myopic firms face candidate workers arriving with heterogeneous observable characteristics. The association between the worker's skill and characteristics is unknown ex ante; thus, firms need to learn it. In such an environment, laissez-faire may result in a highly unfair and inefficient outcome---myopic firms are reluctant to hire minority workers because the lack of data about minority workers prevents accurate… Expand
Early-Career Discrimination: Spiraling or Self-Correcting?
Do workers from social groups with comparable productivity distributions obtain comparable lifetime earnings? We study how a small amount of early-career discrimination propagates over time whenExpand
Endogenous Learning, Persistent Employer Biases, and Discrimination
I present a statistical discrimination model of the labor market in which employers are initially uncertain about the productivity of worker groups and endogenously learn about it through theirExpand

References

SHOWING 1-10 OF 87 REFERENCES
Mostly Exploration-Free Algorithms for Contextual Bandits
TLDR
Surprisingly, it is found that a simple greedy algorithm can be rate optimal if there is sufficient randomness in the observed contexts (covariates) and it is proved that this is always the case for a two-armed bandit under a general class of context distributions that satisfy a condition the authors term covariate diversity. Expand
A general equilibrium model of statistical discrimination
TLDR
A general equilibrium model with endogenous human capital formation in which ex ante identical groups may be treated differently in equilibrium due to informational externalities is considered, consistent with "reverse discrimination" as a remedy against discrimination. Expand
Endogenous Inequality in Integrated Labor Markets with Two-Sided Search
We consider a market with "red" and "green" workers, where labels are payoff irrelevant. Workers may acquire skills. Skilled workers search for vacancies, while firms search for workers. A uniqueExpand
Culture, Information, and Screening Discrimination
We show that discrimination can occur even when it is common knowledge that underlying group characteristics do not differ and when employers do not prefer same-group candidates. When employers canExpand
Will Affirmative-Action Policies Eliminate Negative Stereotypes?
A key question concerning affirmative action is whether the labor-market gains it brings to minorities can continue without it becoming a permanent fixture in the labor market. The authors argue thatExpand
An Economic Argument for Affirmative Action
This article presents a model involving employers and two classes of workers, alike except for labels. Employers choose whom to hire and workers choose whether to invest in training. At oneExpand
The Statistical Theory of Racism and Sexism
My recent book, Inflation Policy and Unemployment Theory, introduces what is called the statistical theory of racial (and sexual) discrimination in the labor market.' The theory fell naturally out ofExpand
The Theory of Discrimination
A Search Model of Statistical Discrimination
We offer a search-theoretic model of statistical discrimination, in which firms treat identical groups unequally based on their occupational choices. The model admits symmetric equilibria in whichExpand
Early-Career Discrimination: Spiraling or Self-Correcting?
Do workers from social groups with comparable productivity distributions obtain comparable lifetime earnings? We study how a small amount of early-career discrimination propagates over time whenExpand
...
1
2
3
4
5
...