The Impact of Machine Learning on Economics

@article{Athey2019TheIO,
  title={The Impact of Machine Learning on Economics},
  author={Susan Athey},
  journal={The Economics of Artificial Intelligence},
  year={2019}
}
  • S. Athey
  • Published 10 January 2018
  • Computer Science, Economics
  • The Economics of Artificial Intelligence
This paper provides an assessment of the early contributions of machine learning to economics, as well as predictions about its future contributions. It begins by briefly overviewing some themes from the literature on machine learning, and then draws some contrasts with traditional approaches to estimating the impact of counterfactual policies in economics. Next, we review some of the initial “off-the-shelf” applications of machine learning to economics, including applications in analyzing text… 

Machine Learning Methods That Economists Should Know About

TLDR
Newly developed methods at the intersection of ML and econometrics, methods that typically perform better than either off-the-shelf ML or more traditional econometric methods when applied to particular classes of problems, are highlighted.

Machine learning in policy evaluation: new tools for causal inference

TLDR
This article begins by reviewing popular supervised machine learning algorithms, including trees-based methods and the lasso, as well as ensembles, with a focus on the Super Learner, and introduces specific uses of machine learning for treatment effect estimation.

CATE meets ML

TLDR
This tutorial gives an overview of novel methods, explains them in detail, and applies them via Quantlets in real data applications to study the effect that microcredit availability has on the amount of money borrowed and if 401(k) pension plan eligibility has an impact on net financial assets.

CATE meets ML - Conditional Average Treatment Effect and Machine Learning

For treatment effects - one of the core issues in modern econometric analysis - prediction and estimation are two sides of the same coin. As it turns out, machine learning methods are the tool for

The Added Value of Machine Learning to Economics: Evidence from Revisited Studies

TLDR
It is found that ML-based methods for the ATE give estimates that deviate from original ones, which implies that these methods might improve causal inference from established methods to a great extent.

How is Machine Learning Useful for Macroeconomic Forecasting?

TLDR
It is concluded that Machine Learning is useful for macroeconomic forecasting by mostly capturing important nonlinearities that arise in the context of uncertainty and financial frictions.

Synthetic learner: model-free inference on treatments over time

A hybrid econometric-machine learning approach for relative importance analysis: Food inflation

TLDR
The purpose of this article is to propose a hybrid approach to assess relative importance and demonstrate its applicability in addressing policy priority issues, followed by a broader aim to introduce the possibility of conflation of ML and conventional econometrics to an audience of researchers in economics and social sciences.

Assessing Sensitivity of Machine Learning Predictions.A Novel Toolbox with an Application to Financial Literacy

TLDR
A general algorithm is proposed that assesses how the omission of an unobserved variable with high explanatory power could affect the predictions of the model and extends the usage of machine learning from pointwise predictions to inference and sensitivity analysis.

Discrete Choice Analysis with Machine Learning Capabilities

TLDR
This paper discusses capabilities that are essential to models applied in policy analysis settings and the limitations of direct applications of off-the-shelf machine learning methodologies to such settings, and identifies an area where machine learning paradigms can be leveraged.
...

References

SHOWING 1-10 OF 110 REFERENCES

Balanced Policy Evaluation and Learning

TLDR
A new, balance-based approach that makes the data look like the new policy but does so directly by finding weights that optimize for balance between the weighted data and the target policy in the given, finite sample, which is equivalent to minimizing worst-case or posterior conditional mean square error.

The State of Applied Econometrics - Causality and Policy Evaluation

TLDR
This paper discusses new research on identification strategies in program evaluation, with particular focus on synthetic control methods, regression discontinuity, external validity, and the causal interpretation of regression methods.

Doubly Robust Policy Evaluation and Learning

TLDR
It is proved that the doubly robust approach uniformly improves over existing techniques, achieving both lower variance in value estimation and better policies, and is expected to become common practice.

Counterfactual Prediction with Deep Instrumental Variables Networks

TLDR
A recipe for combining ML algorithms to solve for causal effects in the presence of instrumental variables -- sources of treatment randomization that are conditionally independent from the response is provided.

Doubly Robust Policy Evaluation and Optimization

TLDR
It is proved that the doubly robust estimation method uniformly improves over existing techniques, achieving both lower variance in value estimation and better policies, and is expected to become common practice in policy evaluation and optimization.

Machine Learning: An Applied Econometric Approach

TLDR
This work presents a way of thinking about machine learning that gives it its own place in the econometric toolbox, and aims to make them conceptually easier to use by providing a crisper understanding of how these algorithms work, where they excel, and where they can stumble.

Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning

TLDR
A new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy, based on an extension of the doubly robust estimator and a new way to mix between model based estimates and importance sampling based estimates.

Doubly Robust Off-policy Value Evaluation for Reinforcement Learning

TLDR
This work extends the doubly robust estimator for bandits to sequential decision-making problems, which gets the best of both worlds: it is guaranteed to be unbiased and can have a much lower variance than the popular importance sampling estimators.

Estimation Considerations in Contextual Bandits

TLDR
This work leverages parametric and non-parametric statistical estimation methods and causal effect estimation methods in order to propose new contextual bandit designs and shows how alternative design choices impact the learning performance and provides insights on why they do so.

Big Data: New Tricks for Econometrics

TLDR
A few tools for manipulating and analyzing big data such as decision trees, support vector machines, neural nets, deep learning, and so on may allow for more effective ways to model complex relationships.
...