Machine Learning: An Applied Econometric Approach
By Sendhil Mullainathan, Jann Spiess. 2017
1,678 citations recorded by the source corpus.
Machines are increasingly doing “intelligent” things. Face recognition algorithms use a large dataset of photos labeled as having a face or not to estimate a function that predicts the presence y of a face from pixels x. This similarity to econometrics raises questions: How do these new empirical tools fit with what we know? As empirical economists, how can we use them? We present a way of thinking about machine learning that gives it its own place in the econometric toolbox. Machine learning not only provides new tools, it solves a different problem. Specifically, machine learning revolves around the problem of prediction, while many economic applications revolve around parameter estimation. So applying machine learning to economics requires finding relevant tasks. Machine learning algorithms are now technically easy to use: you can download convenient packages in R or Python. This also raises the risk that the algorithms are applied naively or their output is misinterpreted. We hope 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—and thus where they can be most usefully applied.
Subfields: Global and Planetary Change, Management Science and Operations Research, Renewable Energy, Sustainability and the Environment, Statistics and Probability, Economics & Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Global and Planetary Change
- A. Fagereng
- G. Natvik
- Markku V. J. Maula
- Ahmed El-Shafie
- Sam Corbett-Davies
- Sharad Goel
- W. Stam
- David Sculley
In Management Science and Operations Research
- M. Ugur Gudelek
- Omer Berat Sezer
- A. Ozbayoglu
- Mitsuru Igami
- A. Fagereng
- G. Natvik
- Markku V. J. Maula
- Alán Aspuru-Guzik
In Renewable Energy, Sustainability and the Environment
In Statistics and Probability
- Susan Athey
- Sharad Goel
- Sam Corbett-Davies
- Matthew D. Hoffman
- David Watson
- Stefan Wager
- A. Fagereng
- G. Natvik
In Economics & Operations Research
- A. Ozbayoglu
- M. Ugur Gudelek
- Mitsuru Igami
- A. Fagereng
- G. Natvik
- Markku V. J. Maula
- W. Stam
- David Watson
Citations in the corpus
- Measurement and Fairness (2019, background): “Despite the name, predictive validity is not the same as out-of-sample prediction [29, 47].”
- Underspecification Presents Challenges for Credibility in Modern Machine Learning (2020, background): “, 2020), economics (Mullainathan and Spiess, 2017; Athey, 2017), public policy (Kleinberg et al.”
- Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, background): “Mullainathan and Spies [9] surveyed the prediction process in general from an econometric perspective.”
- Deep Learning for Financial Applications : A Survey (2020, background): “[6] studied the ML implementations from a high level and econometric point of view.”
- LBS Research Online (2021, positive): “Mullainathan and Spiess (2017) provide a good overview of this nascent literature, and highlight work such as Kleinberg et al. (2017) who show that using an algorithm to help guide decisions regarding bail, can help relative to a counterfactual where the judge’s judgment could be clouded by the…”
- The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning (2018, background): “Nevertheless, recent work at the intersection of machine learning and causal inference (Hill, 2011; Jung et al., 2018; Mullainathan and Spiess, 2017) offers hope for gains.”
- Can Technology Solve the Principal-Agent Problem? Evidence from China’s War on Air Pollution (2020, positive): “Specifically, we train an artificial neural network (ANN) and predict the pre-automation PM10 levels, assuming that the postautomation relationships between PM10, AOD, and weather conditions can be carried to the preautomation period (see Mullainathan and Spiess (2017) for method discussion).”
- Macroeconomic forecast accuracy in a data‐rich environment (2019, neutral): “Ng and Perron (1996) and Ng and Perron (2001) also document similar evidence.”
- On cross-validated Lasso in high dimensions (2016, neutral): “[33] Mullainathan, S.”
- Machine learning and AI in marketing – Connecting computing power to human insights (2020, neutral): “Similarly, machine learning methods may also improve the performance of instrumental variable regressions (Mullainathan & Spiess, 2017).”
- Predictably Unequal? The Effects of Machine Learning on Credit Markets (2020, neutral): “Academic economists also increasingly rely on such techniques (e.g., Belloni et al., 2014; Varian, 2014; Kleinberg et al., 2017; Mullainathan and Spiess, 2017; Chernozhukov et al., 2017; Athey and Imbens, 2017).”