Machine learning and behavioral economics for personalized choice architecture

Emir Hrnjic; Nikodem Tomczak

arxiv: 1907.02100 · v1 · pith:ORQSBAIPnew · submitted 2019-07-03 · 💰 econ.GN · cs.LG· q-fin.EC

Machine learning and behavioral economics for personalized choice architecture

Emir Hrnjic , Nikodem Tomczak This is my paper

Pith reviewed 2026-05-25 09:23 UTC · model grok-4.3

classification 💰 econ.GN cs.LGq-fin.EC

keywords machine learningbehavioral economicschoice architecturepersonalized interventionsnudgespredictive modelspolicy decisions

0 comments

The pith

Machine learning can design personalized behavioral nudges by sampling individual psychological traits.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Behavioral economics introduced nudges and choice architecture that work at the population level but often fail to generalize to individuals. The paper explores how machine learning and artificial intelligence can address weak generalization by building models with stronger predictive power. This combination supports the design of personalized interventions that augment individual decision-making and inform policy. The approach depends on sampling enough personalized traits and psychological variables. If the assumption holds, interventions move from averages to tailored designs.

Core claim

The paper claims that ML and AI can work with behavioral economics to support and augment decision-making and inform policy decisions by designing personalized interventions, assuming that enough personalized traits and psychological variables can be sampled.

What carries the argument

Personalized choice architecture created by ML models that incorporate sampled individual psychological variables to achieve stronger predictive power than population-level nudges.

If this is right

Personalized interventions can achieve stronger effects at the individual level than standard nudges.
Policy decisions can draw on individual-level predictions rather than averages.
Decision support tools can be tailored using ML to augment personal choices.
Models trained on psychological data can alleviate the weak generalization problem of behavioral interventions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Privacy rules may need revision if psychological variable sampling becomes standard for policy.
Field trials could directly compare outcomes of personalized versus population nudges in the same setting.
The method might extend to domains like health or savings policy where individual differences matter.
Ethical guidelines for highly targeted influence would likely need development alongside the technical tools.

Load-bearing premise

Enough personalized traits and psychological variables can be sampled to enable models with stronger predictive power than population-level nudges.

What would settle it

An experiment that samples extensive individual traits and psychological variables yet finds ML models produce no improvement in predictive accuracy for choices compared with population nudges.

read the original abstract

Behavioral economics changed the way we think about market participants and revolutionized policy-making by introducing the concept of choice architecture. However, even though effective on the level of a population, interventions from behavioral economics, nudges, are often characterized by weak generalisation as they struggle on the level of individuals. Recent developments in data science, artificial intelligence (AI) and machine learning (ML) have shown ability to alleviate some of the problems of weak generalisation by providing tools and methods that result in models with stronger predictive power. This paper aims to describe how ML and AI can work with behavioral economics to support and augment decision-making and inform policy decisions by designing personalized interventions, assuming that enough personalized traits and psychological variables can be sampled.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

A short conceptual note on personalizing nudges with ML that flags its own key assumption but adds no new analysis or results.

read the letter

This paper is a brief conceptual discussion on combining machine learning with behavioral economics to personalize nudges. The core idea is that ML can improve on the weak individual-level performance of standard choice architecture by using more data on personal traits. The authors do a good job of stating the enabling assumption clearly: that we can sample enough individualized psychological variables to build stronger models. They also correctly note that current nudges are population-based and often fail to generalize. Nothing in the paper is new in terms of methods or evidence. It references existing work in both fields but doesn't derive anything, test anything, or provide data. The text is essentially a high-level proposal for future work. The main limitation is that the argument stops at the assumption without exploring its practicality or potential problems like data collection costs or ethical concerns. Since no model or result is presented, there's nothing to evaluate beyond the framing. On the positive side, the paper avoids overclaiming and keeps the scope narrow to describing potential rather than asserting results. That keeps it from having internal contradictions or circular claims. Readers interested in broad ideas at the intersection of AI and public policy might find it a quick read for inspiration. But for anyone wanting empirical work or formal contributions, it won't deliver much. I don't see this as something to cite or discuss in detail with a group. It probably doesn't warrant peer review either, as it's too preliminary and lacks the substance that referees would need to assess.

Referee Report

0 major / 1 minor

Summary. The manuscript proposes that machine learning and AI can integrate with behavioral economics to design personalized choice architecture interventions. It notes that population-level nudges often exhibit weak generalization to individuals and argues that ML/AI methods can yield stronger predictive power, provided that sufficient individualized traits and psychological variables can be sampled to enable this personalization and thereby support decision-making and policy.

Significance. If the stated sampling assumption can be met and operational synergies between the fields realized, the proposal could meaningfully advance policy applications by shifting from aggregate nudges to individualized ones, with potential gains in domains such as savings, health, and environmental behavior. The manuscript itself, however, advances no formal model, empirical test, derivation, or reproducible method, so its contribution remains a conditional conceptual outline rather than a validated result.

minor comments (1)

The central enabling assumption is stated clearly in the abstract but receives no further elaboration on measurement, data requirements, or potential selection biases in any section of the manuscript.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their review. We address the main points from the report below.

read point-by-point responses

Referee: The manuscript itself, however, advances no formal model, empirical test, derivation, or reproducible method, so its contribution remains a conditional conceptual outline rather than a validated result.

Authors: We agree that the manuscript presents a conceptual outline rather than new empirical tests, formal models, or reproducible methods. Its stated aim, as reflected in the abstract, is to describe potential ways in which ML and AI can support behavioral economics in designing personalized interventions, conditional on the ability to sample sufficient individualized traits and psychological variables. This scope was chosen to highlight interdisciplinary opportunities without claiming validated results. revision: no
Referee: If the stated sampling assumption can be met and operational synergies between the fields realized, the proposal could meaningfully advance policy applications by shifting from aggregate nudges to individualized ones, with potential gains in domains such as savings, health, and environmental behavior.

Authors: The manuscript explicitly conditions its argument on the sampling assumption and discusses potential policy gains in savings, health, and environmental domains. We note that the referee's assessment aligns with the paper's framing of when and how stronger individual-level predictive power could be achieved via ML methods. revision: no

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The manuscript is a short conceptual proposal that describes potential synergies between machine learning and behavioral economics for designing personalized interventions. Its central claim is explicitly conditioned on the feasibility of sampling sufficient individualized traits and psychological variables, with no formal model, equations, fitted parameters, theorems, or empirical results presented. No derivation chain exists that could reduce outputs to inputs by construction, and the provided text contains no self-citations or ansatzes that would trigger any of the enumerated circularity patterns. The argument remains self-contained as a high-level discussion rather than a technical derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are identifiable from the abstract; the work is a high-level proposal rather than a formal model.

pith-pipeline@v0.9.0 · 5648 in / 1020 out tokens · 36928 ms · 2026-05-25T09:23:20.521091+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

114 extracted references · 114 canonical work pages · 3 internal anchors

[1]

Richard Neustadt and Ernest May, Thinking in time: the uses of history for decision-makers (Free Press Col- lier Macmillan, New York London, 1986)

work page 1986
[2]

Sales Teams Arent Great at Forecasting. Heres How to Fix That,

Bob Suh, “Sales Teams Arent Great at Forecasting. Heres How to Fix That,” Harvard Business Review (2019), accessed 2019-05-19

work page 2019
[3]

Too much theory leads economists to bad predictions,

Peter A Coclanis, “Too much theory leads economists to bad predictions,” Wired (2019), accessed 2019-05-20

work page 2019
[4]

Karl Popper, The poverty of historicism (Ark, London, 1986)

work page 1986
[5]

David Halpern, Inside the nudge unit : how small changes can make a big diﬀerence (WH Allen, London, 2016)

work page 2016
[6]

Homo economicus evolves,

Steven D Levitt and John A List, “Homo economicus evolves,” Science 319, 909–910 (2008)

work page 2008
[7]

Norton, 2015)

Richard Thaler, Misbehaving: The Making of Behavioral Economics, Business/Economics (W.W. Norton, 2015)

work page 2015
[8]

A behavioral model of rational choice,

Herbert A Simon, “A behavioral model of rational choice,” The Quarterly Journal of Economics 69, 99– 118 (1955)

work page 1955
[9]

Judgment under uncertainty: Heuristics and biases,

Amos Tversky and Daniel Kahneman, “Judgment under uncertainty: Heuristics and biases,” Science 185, 1124– 1131 (1974)

work page 1974
[10]

Daniel Kahneman, Thinking, fast and slow (Farrar, Straus and Giroux, 2011)

work page 2011
[11]

Nick Wilkinson and Matthias Klaes, An introduction to behavioral economics (Palgrave Macmillan, Houndmills, Basingstoke New York, NY, 2012)

work page 2012
[12]

David Just, Introduction to behavioral economics : noneconomic factors that shape economic decisions (Wi- ley, Hoboken, NJ, 2014)

work page 2014
[13]

Richard Thaler and Cass Sunstein, Nudge : improving decisions about health, wealth, and happiness (Yale Uni- versity Press, 2008)

work page 2008
[14]

Toward a positive theory of consumer choice,

Richard Thaler, “Toward a positive theory of consumer choice,” Journal of Economic Behavior & Organization 1, 39–60 (1980)

work page 1980
[15]

Cass Sunstein, Human Agency and Behavioral Eco- nomics Nudging Fast and Slow (Palgrave Macmillan, Cham, Switzerland, 2017)

work page 2017
[16]

The rise of behavioral economics and its inﬂuence on organizations,

Francesca Gino, “The rise of behavioral economics and its inﬂuence on organizations,” Harvard Business Re- view (2017), accessed 2019-05-19

work page 2017
[17]

Behavioral economics and public policy: A pragmatic perspective,

Raj Chetty, “Behavioral economics and public policy: A pragmatic perspective,” American Economic Review 105, 1–33 (2015)

work page 2015
[18]

William Congdon, Jeﬀrey R Kling, and Sendhil Mul- lainathan, Policy and choice : public ﬁnance through the lens of behavioral economics (Brookings Institution Press, Washington, D.C, 2011)

work page 2011
[19]

Applying insights from behaviora l economics to policy design,

Brigitte C Madrian, “Applying insights from behaviora l economics to policy design,” Annual Review of Eco- nomics 6, 663–688 (2014)

work page 2014
[20]

Cass Sunstein, The ethics of inﬂuence : government in the age of behavioral science (Cambridge University Press, New York, NY, USA, 2016)

work page 2016
[21]

The last-mile problem: how data science and behavioral science can work together,

Jim Guszcza, “The last-mile problem: how data science and behavioral science can work together,” Deloitte Re- view (2015), accessed 2019-05-19

work page 2015
[22]

Using behavioral nudges to treat diabetes,

Thomas H Davenport, James Guszcza, and Greg Szwartz, “Using behavioral nudges to treat diabetes,” Harvard Business Review (2018), accessed 2019-05-19

work page 2018
[23]

Should governments invest more in nudging?

Shlomo Benartzi, John Beshears, Katherine L Milkman, Cass R Sunstein, Richard H Thaler, Maya Shankar, Will Tucker-Ray, William J Congdon, and Steven Galing, “Should governments invest more in nudging?” Psycho- logical science 28, 1041–1055 (2017). 7

work page 2017
[24]

Stuart Russell and Peter Norvig, Artiﬁcial intelligence: a modern approach (Pearson; 3 edition, 2016)

work page 2016
[25]

Economic reasoning and artiﬁcial intelligence,

David C Parkes and Michael P Wellman, “Economic reasoning and artiﬁcial intelligence,” Science 349, 267– 272 (2015)

work page 2015
[26]

Ian Goodfellow, Deep learning (The MIT Press, Cam- bridge, Massachusetts, 2016)

work page 2016
[27]

Trevor Hastie, Robert Tibshirani, and Jerome Fried- man, The elements of statistical learning : Data mining, inference, and prediction (Springer, New York, 2009)

work page 2009
[28]

Nils Nilsson, The quest for artiﬁcial intelligence : a his- tory of ideas and achievements (Cambridge University Press, Cambridge New York, 2010)

work page 2010
[29]

(MIT Press, Cambridge, Mass, 1996)

Herbert Simon, The sciences of the artiﬁcial, 3rd ed. (MIT Press, Cambridge, Mass, 1996)

work page 1996
[30]

Economics in the age of big data,

Liran Einav and Jonathan Levin, “Economics in the age of big data,” Science 346, 1243089 (2014)

work page 2014
[31]

Foster Provost and Tom Fawcett, Data science for business : what you need to know about data mining and data-analytic thinking (O’Reilly, Sebastopol, Calif, 2013)

work page 2013
[32]

Machine learning: Trends, perspectives, and prospects,

M. I. Jordan and T. M. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science 349, 255– 260 (2015)

work page 2015
[33]

Deep learning,

Yann LeCun, Yoshua Bengio, and Geoﬀrey Hinton, “Deep learning,” Nature 521, 436 (2015)

work page 2015
[34]

Text as data: The promise and pitfalls of automatic content analysis methods for political texts,

Justin Grimmer and Brandon M Stewart, “Text as data: The promise and pitfalls of automatic content analysis methods for political texts,” Political analysis 21, 267– 297 (2013)

work page 2013
[35]

Deep Learning for Identifying Metastatic Breast Cancer

Dayong Wang, Aditya Khosla, Rishab Gargeya, Hu- mayun Irshad, and Andrew H. Beck, “Deep Learn- ing for Identifying Metastatic Breast Cancer,” arXiv e- prints , arXiv:1606.05718 (2016)

work page internal anchor Pith review Pith/arXiv arXiv 2016
[36]

Machine learning methods for demand estimation,

Patrick Bajari, Denis Nekipelov, Stephen P Ryan, and Miaoyu Yang, “Machine learning methods for demand estimation,” American Economic Review 105, 481–85 (2015)

work page 2015
[37]

Big data: New tricks for econometrics,

Hal R Varian, “Big data: New tricks for econometrics,” Journal of Economic Perspectives 28, 3 –28 (2014)

work page 2014
[38]

Welcome to the brave new world of per- suasion proﬁling,

Eli Pariser, “Welcome to the brave new world of per- suasion proﬁling,” Wired (2011), accessed 2019-05-03

work page 2011
[39]

The accuracy, fairness, and limits of predicting recidivism,

Julia Dressel and Hany Farid, “The accuracy, fairness, and limits of predicting recidivism,” Science Advances 4 (2018)

work page 2018
[40]

Predicting and preventing shootings among at- risk youth,

Dana Chandler, Steven D Levitt, and John A List, “Predicting and preventing shootings among at- risk youth,” American Economic Review 101, 288–92 (2011)

work page 2011
[41]

Predicting poverty and wealth from mobile phone metadata,

Joshua Blumenstock, Gabriel Cadamuro, and Robert On, “Predicting poverty and wealth from mobile phone metadata,” Science 350, 1073–1076 (2015)

work page 2015
[42]

Fighting poverty with data,

Joshua Blumenstock, “Fighting poverty with data,” Sci - ence 353, 753 – 754 (2016)

work page 2016
[43]

Combin- ing satellite imagery and machine learning to predict poverty,

Neal Jean, Marshall Burke, Michael Xie, W Matthew Davis, David B Lobell, and Stefano Ermon, “Combin- ing satellite imagery and machine learning to predict poverty,” Science 353, 790–794 (2016)

work page 2016
[44]

What can ma- chine learning do? Workforce implications,

Erik Brynjolfsson and Tom Mitchell, “What can ma- chine learning do? Workforce implications,” Science 358, 1530–1534 (2017)

work page 2017
[45]

The social dilemma of autonomous vehicles,

Jean-Fran¸ cois Bonnefon, Azim Shariﬀ, and Iyad Rah- wan, “The social dilemma of autonomous vehicles,” Sci- ence 352, 1573–1576 (2016)

work page 2016
[46]

Sean Gerrish, How smart machines think (The MIT Press, Cambridge, MA, 2018)

work page 2018
[47]

Credit scoring with a data mining approach based on support vector machines,

Cheng-Lung Huang, Mu-Chen Chen, and Chieh-Jen Wang, “Credit scoring with a data mining approach based on support vector machines,” Expert Systems with Applications 33, 847–856 (2007)

work page 2007
[48]

Ethical issues for autonomous trading agents,

Michael P Wellman and Uday Rajan, “Ethical issues for autonomous trading agents,” Minds and Machines 27, 609–624 (2017)

work page 2017
[49]

Deep direct reinforcement learning for ﬁ- nancial signal representation and trading,

Yue Deng, Feng Bao, Youyong Kong, Zhiquan Ren, and Qionghai Dai, “Deep direct reinforcement learning for ﬁ- nancial signal representation and trading,” IEEE Trans- actions on Neural Networks and Learning Systems 28, 653–664 (2016)

work page 2016
[50]

The rise of the artiﬁcially intelligent hed ge fund,

Cade Metz, “The rise of the artiﬁcially intelligent hed ge fund,” Wired (2016), accessed 2019-05-03

work page 2016
[51]

Deep learning for ﬁnance: deep portfolios,

JB Heaton, NG Polson, and Jan Hendrik Witte, “Deep learning for ﬁnance: deep portfolios,” Applied Stochas- tic Models in Business and Industry 33, 3–12 (2017)

work page 2017
[52]

Machine learn- ing: an applied econometric approach,

Sendhil Mullainathan and Jann Spiess, “Machine learn- ing: an applied econometric approach,” Journal of Eco- nomic Perspectives 31, 87–106 (2017)

work page 2017
[53]

Is romantic desire predictable? Machine learning applied to initial romantic attraction,

Samantha Joel, Paul W Eastwick, and Eli J Finkel, “Is romantic desire predictable? Machine learning applied to initial romantic attraction,” Psychological science 28, 1478–1489 (2017)

work page 2017
[54]

Machine learn- ing phases of matter,

Juan Carrasquilla and Roger G Melko, “Machine learn- ing phases of matter,” Nature Physics 13, 431 (2017)

work page 2017
[55]

Machine learning for molecular and materials science,

Keith T Butler, Daniel W Davies, Hugh Cartwright, Olexandr Isayev, and Aron Walsh, “Machine learning for molecular and materials science,” Nature 559, 547 (2018)

work page 2018
[56]

Active learning in materi- als science with emphasis on adaptive sampling using uncertainties for targeted design,

Turab Lookman, Prasanna V Balachandran, Dezhen Xue, and Ruihao Yuan, “Active learning in materi- als science with emphasis on adaptive sampling using uncertainties for targeted design,” npj Computational Materials 5, 21 (2019)

work page 2019
[57]

Quantum machine learning,

Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patric k Rebentrost, Nathan Wiebe, and Seth Lloyd, “Quantum machine learning,” Nature 549, 195 (2017)

work page 2017
[58]

Ma- chine learning in materials informatics: recent applica- tions and prospects,

Rampi Ramprasad, Rohit Batra, Ghanshyam Pilania, Arun Mannodi-Kanakkithodi, and Chiho Kim, “Ma- chine learning in materials informatics: recent applica- tions and prospects,” npj Computational Materials 3, 54 (2017)

work page 2017
[59]

Structure prediction drives mate- rials discovery,

Artem R Oganov, Chris J Pickard, Qiang Zhu, and Richard J Needs, “Structure prediction drives mate- rials discovery,” Nature Reviews Materials 4, 331–348 (2019)

work page 2019
[60]

Planning chemical syntheses with deep neural networks and symbolic ai,

Marwin HS Segler, Mike Preuss, and Mark P Waller, “Planning chemical syntheses with deep neural networks and symbolic ai,” Nature 555, 604 (2018)

work page 2018
[61]

How AI technology can tame the sci- entiﬁc literature,

Andy Extance, “How AI technology can tame the sci- entiﬁc literature,” Nature 561, 273–274 (2018)

work page 2018
[62]

Noise: How to overcome the high, hidden cost of inconsistent decision making,

Daniel Kahneman, “Noise: How to overcome the high, hidden cost of inconsistent decision making,” Harvard Business Review , 36–43 (2016)

work page 2016
[63]

Ajay Agrawal, Joshua Gans, and Avi Goldfard, Predic- tion machines: the simple economics of artiﬁcial intel- ligence (Harvard Business Review Press, Boston, 2018)

work page 2018
[64]

Combining psychological models with ma- chine learning to better predict peoples decisions,

Avi Rosenfeld, Inon Zuckerman, Amos Azaria, and Sarit Kraus, “Combining psychological models with ma- chine learning to better predict peoples decisions,” Syn- these 189, 81–93 (2012). 8

work page 2012
[65]

Scaling nudges with machine learning,

Chris Risdon, “Scaling nudges with machine learning,” Behavioral Scientist (2017), accessed 2019-04-20

work page 2017
[66]

Predicting hu- man behavior: The next frontiers,

VS Subrahmanian and Srijan Kumar, “Predicting hu- man behavior: The next frontiers,” Science 355, 489– 489 (2017)

work page 2017
[67]

Retention futility: Targeting high-ris k customers might be ineﬀective,

Eva Ascarza, “Retention futility: Targeting high-ris k customers might be ineﬀective,” Journal of Marketing Research 55, 80–98 (2018)

work page 2018
[68]

Targeting with machine learning: An application to a tax rebate program in italy,

Monica Andini, Emanuele Ciani, Guido de Blasio, Alessio D’Ignazio, and Viola Salvestrini, “Targeting with machine learning: An application to a tax rebate program in italy,” Journal of Economic Behavior & Or- ganization 156, 86–102 (2018)

work page 2018
[69]

Predicting human decisions with behav- ioral theories and machine learning,

Ori Plonsky, Reut Apel, Eyal Ert, Moshe Tennen- holtz, David Bourgin, Joshua C Peterson, Daniel Re- ichman, Thomas L Griﬃths, Stuart J Russell, Evan C Carter, et al. , “Predicting human decisions with behav- ioral theories and machine learning,” arXiv e-prints , arXiv:1904.06866 (2019)

work page arXiv 1904
[70]

Warning: You are about to be nudged,

George Loewenstein, Cindy Bryce, David Hagmann, and Sachin Rajpal, “Warning: You are about to be nudged,” Behavioral Science & Policy 1, 35 – 42 (2015)

work page 2015
[71]

Prediction-based decisions and fairness: A catalogue of choices, assumptions, and definitions

Shira Mitchell, Eric Potash, and Solon Barocas, “Prediction-based decisions and fairness: A catalogue of choices, assumptions, and deﬁnitions,” arXiv preprint , arXiv:1811.07867 (2018)

work page arXiv 2018
[72]

Beyond prediction: Using big data for policy problems,

Susan Athey, “Beyond prediction: Using big data for policy problems,” Science 355, 483–485 (2017)

work page 2017
[73]

Random forests,

Leo Breiman, “Random forests,” Machine learning 45, 5–32 (2001)

work page 2001
[74]

A recipe for rigor,

Kai Kupferschmidt, “A recipe for rigor,” Science 361, 1192–1193 (2018)

work page 2018
[75]

Artiﬁcial intelligence faces repro- ducibility crisis,

Matthew Hutson, “Artiﬁcial intelligence faces repro- ducibility crisis,” Science 359, 725–726 (2018)

work page 2018
[76]

Counterfactual fairness,

Matt J Kusner, Joshua Loftus, Chris Russell, and Ricardo Silva, “Counterfactual fairness,” Advances in Neural Information Processing Systems , 4066–4076 (2017)

work page 2017
[77]

Learning fair representations,

Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork, “Learning fair representations,” Pro- ceedings of International Conference on Machine Learn- ing , 325–333 (2013)

work page 2013
[78]

Algorithmic fairness,

Jon Kleinberg, Jens Ludwig, Sendhil Mullainathan, and Ashesh Rambachan, “Algorithmic fairness,” AEA Pa- pers and Proceedings 108, 22–27 (2018)

work page 2018
[79]

Did the Model Understand the Question?

Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan, and Kedar Dhamdhere, “Did the model understand the question?” arXiv e-print , arXiv:1805.05492 (2018)

work page internal anchor Pith review Pith/arXiv arXiv 2018
[80]

Optimized pre-processing for discrimination pre- vention,

Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, and Kush R Varsh- ney, “Optimized pre-processing for discrimination pre- vention,” in Advances in Neural Information Process- ing Systems 30 , edited by I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Curran Associates, Inc., 2017) ...

work page 2017

Showing first 80 references.

[1] [1]

Richard Neustadt and Ernest May, Thinking in time: the uses of history for decision-makers (Free Press Col- lier Macmillan, New York London, 1986)

work page 1986

[2] [2]

Sales Teams Arent Great at Forecasting. Heres How to Fix That,

Bob Suh, “Sales Teams Arent Great at Forecasting. Heres How to Fix That,” Harvard Business Review (2019), accessed 2019-05-19

work page 2019

[3] [3]

Too much theory leads economists to bad predictions,

Peter A Coclanis, “Too much theory leads economists to bad predictions,” Wired (2019), accessed 2019-05-20

work page 2019

[4] [4]

Karl Popper, The poverty of historicism (Ark, London, 1986)

work page 1986

[5] [5]

David Halpern, Inside the nudge unit : how small changes can make a big diﬀerence (WH Allen, London, 2016)

work page 2016

[6] [6]

Homo economicus evolves,

Steven D Levitt and John A List, “Homo economicus evolves,” Science 319, 909–910 (2008)

work page 2008

[7] [7]

Norton, 2015)

Richard Thaler, Misbehaving: The Making of Behavioral Economics, Business/Economics (W.W. Norton, 2015)

work page 2015

[8] [8]

A behavioral model of rational choice,

Herbert A Simon, “A behavioral model of rational choice,” The Quarterly Journal of Economics 69, 99– 118 (1955)

work page 1955

[9] [9]

Judgment under uncertainty: Heuristics and biases,

Amos Tversky and Daniel Kahneman, “Judgment under uncertainty: Heuristics and biases,” Science 185, 1124– 1131 (1974)

work page 1974

[10] [10]

Daniel Kahneman, Thinking, fast and slow (Farrar, Straus and Giroux, 2011)

work page 2011

[11] [11]

Nick Wilkinson and Matthias Klaes, An introduction to behavioral economics (Palgrave Macmillan, Houndmills, Basingstoke New York, NY, 2012)

work page 2012

[12] [12]

David Just, Introduction to behavioral economics : noneconomic factors that shape economic decisions (Wi- ley, Hoboken, NJ, 2014)

work page 2014

[13] [13]

Richard Thaler and Cass Sunstein, Nudge : improving decisions about health, wealth, and happiness (Yale Uni- versity Press, 2008)

work page 2008

[14] [14]

Toward a positive theory of consumer choice,

Richard Thaler, “Toward a positive theory of consumer choice,” Journal of Economic Behavior & Organization 1, 39–60 (1980)

work page 1980

[15] [15]

Cass Sunstein, Human Agency and Behavioral Eco- nomics Nudging Fast and Slow (Palgrave Macmillan, Cham, Switzerland, 2017)

work page 2017

[16] [16]

The rise of behavioral economics and its inﬂuence on organizations,

Francesca Gino, “The rise of behavioral economics and its inﬂuence on organizations,” Harvard Business Re- view (2017), accessed 2019-05-19

work page 2017

[17] [17]

Behavioral economics and public policy: A pragmatic perspective,

Raj Chetty, “Behavioral economics and public policy: A pragmatic perspective,” American Economic Review 105, 1–33 (2015)

work page 2015

[18] [18]

William Congdon, Jeﬀrey R Kling, and Sendhil Mul- lainathan, Policy and choice : public ﬁnance through the lens of behavioral economics (Brookings Institution Press, Washington, D.C, 2011)

work page 2011

[19] [19]

Applying insights from behaviora l economics to policy design,

Brigitte C Madrian, “Applying insights from behaviora l economics to policy design,” Annual Review of Eco- nomics 6, 663–688 (2014)

work page 2014

[20] [20]

Cass Sunstein, The ethics of inﬂuence : government in the age of behavioral science (Cambridge University Press, New York, NY, USA, 2016)

work page 2016

[21] [21]

The last-mile problem: how data science and behavioral science can work together,

Jim Guszcza, “The last-mile problem: how data science and behavioral science can work together,” Deloitte Re- view (2015), accessed 2019-05-19

work page 2015

[22] [22]

Using behavioral nudges to treat diabetes,

Thomas H Davenport, James Guszcza, and Greg Szwartz, “Using behavioral nudges to treat diabetes,” Harvard Business Review (2018), accessed 2019-05-19

work page 2018

[23] [23]

Should governments invest more in nudging?

Shlomo Benartzi, John Beshears, Katherine L Milkman, Cass R Sunstein, Richard H Thaler, Maya Shankar, Will Tucker-Ray, William J Congdon, and Steven Galing, “Should governments invest more in nudging?” Psycho- logical science 28, 1041–1055 (2017). 7

work page 2017

[24] [24]

Stuart Russell and Peter Norvig, Artiﬁcial intelligence: a modern approach (Pearson; 3 edition, 2016)

work page 2016

[25] [25]

Economic reasoning and artiﬁcial intelligence,

David C Parkes and Michael P Wellman, “Economic reasoning and artiﬁcial intelligence,” Science 349, 267– 272 (2015)

work page 2015

[26] [26]

Ian Goodfellow, Deep learning (The MIT Press, Cam- bridge, Massachusetts, 2016)

work page 2016

[27] [27]

Trevor Hastie, Robert Tibshirani, and Jerome Fried- man, The elements of statistical learning : Data mining, inference, and prediction (Springer, New York, 2009)

work page 2009

[28] [28]

Nils Nilsson, The quest for artiﬁcial intelligence : a his- tory of ideas and achievements (Cambridge University Press, Cambridge New York, 2010)

work page 2010

[29] [29]

(MIT Press, Cambridge, Mass, 1996)

Herbert Simon, The sciences of the artiﬁcial, 3rd ed. (MIT Press, Cambridge, Mass, 1996)

work page 1996

[30] [30]

Economics in the age of big data,

Liran Einav and Jonathan Levin, “Economics in the age of big data,” Science 346, 1243089 (2014)

work page 2014

[31] [31]

Foster Provost and Tom Fawcett, Data science for business : what you need to know about data mining and data-analytic thinking (O’Reilly, Sebastopol, Calif, 2013)

work page 2013

[32] [32]

Machine learning: Trends, perspectives, and prospects,

M. I. Jordan and T. M. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science 349, 255– 260 (2015)

work page 2015

[33] [33]

Deep learning,

Yann LeCun, Yoshua Bengio, and Geoﬀrey Hinton, “Deep learning,” Nature 521, 436 (2015)

work page 2015

[34] [34]

Text as data: The promise and pitfalls of automatic content analysis methods for political texts,

Justin Grimmer and Brandon M Stewart, “Text as data: The promise and pitfalls of automatic content analysis methods for political texts,” Political analysis 21, 267– 297 (2013)

work page 2013

[35] [35]

Deep Learning for Identifying Metastatic Breast Cancer

Dayong Wang, Aditya Khosla, Rishab Gargeya, Hu- mayun Irshad, and Andrew H. Beck, “Deep Learn- ing for Identifying Metastatic Breast Cancer,” arXiv e- prints , arXiv:1606.05718 (2016)

work page internal anchor Pith review Pith/arXiv arXiv 2016

[36] [36]

Machine learning methods for demand estimation,

Patrick Bajari, Denis Nekipelov, Stephen P Ryan, and Miaoyu Yang, “Machine learning methods for demand estimation,” American Economic Review 105, 481–85 (2015)

work page 2015

[37] [37]

Big data: New tricks for econometrics,

Hal R Varian, “Big data: New tricks for econometrics,” Journal of Economic Perspectives 28, 3 –28 (2014)

work page 2014

[38] [38]

Welcome to the brave new world of per- suasion proﬁling,

Eli Pariser, “Welcome to the brave new world of per- suasion proﬁling,” Wired (2011), accessed 2019-05-03

work page 2011

[39] [39]

The accuracy, fairness, and limits of predicting recidivism,

Julia Dressel and Hany Farid, “The accuracy, fairness, and limits of predicting recidivism,” Science Advances 4 (2018)

work page 2018

[40] [40]

Predicting and preventing shootings among at- risk youth,

Dana Chandler, Steven D Levitt, and John A List, “Predicting and preventing shootings among at- risk youth,” American Economic Review 101, 288–92 (2011)

work page 2011

[41] [41]

Predicting poverty and wealth from mobile phone metadata,

Joshua Blumenstock, Gabriel Cadamuro, and Robert On, “Predicting poverty and wealth from mobile phone metadata,” Science 350, 1073–1076 (2015)

work page 2015

[42] [42]

Fighting poverty with data,

Joshua Blumenstock, “Fighting poverty with data,” Sci - ence 353, 753 – 754 (2016)

work page 2016

[43] [43]

Combin- ing satellite imagery and machine learning to predict poverty,

Neal Jean, Marshall Burke, Michael Xie, W Matthew Davis, David B Lobell, and Stefano Ermon, “Combin- ing satellite imagery and machine learning to predict poverty,” Science 353, 790–794 (2016)

work page 2016

[44] [44]

What can ma- chine learning do? Workforce implications,

Erik Brynjolfsson and Tom Mitchell, “What can ma- chine learning do? Workforce implications,” Science 358, 1530–1534 (2017)

work page 2017

[45] [45]

The social dilemma of autonomous vehicles,

Jean-Fran¸ cois Bonnefon, Azim Shariﬀ, and Iyad Rah- wan, “The social dilemma of autonomous vehicles,” Sci- ence 352, 1573–1576 (2016)

work page 2016

[46] [46]

Sean Gerrish, How smart machines think (The MIT Press, Cambridge, MA, 2018)

work page 2018

[47] [47]

Credit scoring with a data mining approach based on support vector machines,

Cheng-Lung Huang, Mu-Chen Chen, and Chieh-Jen Wang, “Credit scoring with a data mining approach based on support vector machines,” Expert Systems with Applications 33, 847–856 (2007)

work page 2007

[48] [48]

Ethical issues for autonomous trading agents,

Michael P Wellman and Uday Rajan, “Ethical issues for autonomous trading agents,” Minds and Machines 27, 609–624 (2017)

work page 2017

[49] [49]

Deep direct reinforcement learning for ﬁ- nancial signal representation and trading,

Yue Deng, Feng Bao, Youyong Kong, Zhiquan Ren, and Qionghai Dai, “Deep direct reinforcement learning for ﬁ- nancial signal representation and trading,” IEEE Trans- actions on Neural Networks and Learning Systems 28, 653–664 (2016)

work page 2016

[50] [50]

The rise of the artiﬁcially intelligent hed ge fund,

Cade Metz, “The rise of the artiﬁcially intelligent hed ge fund,” Wired (2016), accessed 2019-05-03

work page 2016

[51] [51]

Deep learning for ﬁnance: deep portfolios,

JB Heaton, NG Polson, and Jan Hendrik Witte, “Deep learning for ﬁnance: deep portfolios,” Applied Stochas- tic Models in Business and Industry 33, 3–12 (2017)

work page 2017

[52] [52]

Machine learn- ing: an applied econometric approach,

Sendhil Mullainathan and Jann Spiess, “Machine learn- ing: an applied econometric approach,” Journal of Eco- nomic Perspectives 31, 87–106 (2017)

work page 2017

[53] [53]

Is romantic desire predictable? Machine learning applied to initial romantic attraction,

Samantha Joel, Paul W Eastwick, and Eli J Finkel, “Is romantic desire predictable? Machine learning applied to initial romantic attraction,” Psychological science 28, 1478–1489 (2017)

work page 2017

[54] [54]

Machine learn- ing phases of matter,

Juan Carrasquilla and Roger G Melko, “Machine learn- ing phases of matter,” Nature Physics 13, 431 (2017)

work page 2017

[55] [55]

Machine learning for molecular and materials science,

Keith T Butler, Daniel W Davies, Hugh Cartwright, Olexandr Isayev, and Aron Walsh, “Machine learning for molecular and materials science,” Nature 559, 547 (2018)

work page 2018

[56] [56]

Active learning in materi- als science with emphasis on adaptive sampling using uncertainties for targeted design,

Turab Lookman, Prasanna V Balachandran, Dezhen Xue, and Ruihao Yuan, “Active learning in materi- als science with emphasis on adaptive sampling using uncertainties for targeted design,” npj Computational Materials 5, 21 (2019)

work page 2019

[57] [57]

Quantum machine learning,

Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patric k Rebentrost, Nathan Wiebe, and Seth Lloyd, “Quantum machine learning,” Nature 549, 195 (2017)

work page 2017

[58] [58]

Ma- chine learning in materials informatics: recent applica- tions and prospects,

Rampi Ramprasad, Rohit Batra, Ghanshyam Pilania, Arun Mannodi-Kanakkithodi, and Chiho Kim, “Ma- chine learning in materials informatics: recent applica- tions and prospects,” npj Computational Materials 3, 54 (2017)

work page 2017

[59] [59]

Structure prediction drives mate- rials discovery,

Artem R Oganov, Chris J Pickard, Qiang Zhu, and Richard J Needs, “Structure prediction drives mate- rials discovery,” Nature Reviews Materials 4, 331–348 (2019)

work page 2019

[60] [60]

Planning chemical syntheses with deep neural networks and symbolic ai,

Marwin HS Segler, Mike Preuss, and Mark P Waller, “Planning chemical syntheses with deep neural networks and symbolic ai,” Nature 555, 604 (2018)

work page 2018

[61] [61]

How AI technology can tame the sci- entiﬁc literature,

Andy Extance, “How AI technology can tame the sci- entiﬁc literature,” Nature 561, 273–274 (2018)

work page 2018

[62] [62]

Noise: How to overcome the high, hidden cost of inconsistent decision making,

Daniel Kahneman, “Noise: How to overcome the high, hidden cost of inconsistent decision making,” Harvard Business Review , 36–43 (2016)

work page 2016

[63] [63]

Ajay Agrawal, Joshua Gans, and Avi Goldfard, Predic- tion machines: the simple economics of artiﬁcial intel- ligence (Harvard Business Review Press, Boston, 2018)

work page 2018

[64] [64]

Combining psychological models with ma- chine learning to better predict peoples decisions,

Avi Rosenfeld, Inon Zuckerman, Amos Azaria, and Sarit Kraus, “Combining psychological models with ma- chine learning to better predict peoples decisions,” Syn- these 189, 81–93 (2012). 8

work page 2012

[65] [65]

Scaling nudges with machine learning,

Chris Risdon, “Scaling nudges with machine learning,” Behavioral Scientist (2017), accessed 2019-04-20

work page 2017

[66] [66]

Predicting hu- man behavior: The next frontiers,

VS Subrahmanian and Srijan Kumar, “Predicting hu- man behavior: The next frontiers,” Science 355, 489– 489 (2017)

work page 2017

[67] [67]

Retention futility: Targeting high-ris k customers might be ineﬀective,

Eva Ascarza, “Retention futility: Targeting high-ris k customers might be ineﬀective,” Journal of Marketing Research 55, 80–98 (2018)

work page 2018

[68] [68]

Targeting with machine learning: An application to a tax rebate program in italy,

Monica Andini, Emanuele Ciani, Guido de Blasio, Alessio D’Ignazio, and Viola Salvestrini, “Targeting with machine learning: An application to a tax rebate program in italy,” Journal of Economic Behavior & Or- ganization 156, 86–102 (2018)

work page 2018

[69] [69]

Predicting human decisions with behav- ioral theories and machine learning,

Ori Plonsky, Reut Apel, Eyal Ert, Moshe Tennen- holtz, David Bourgin, Joshua C Peterson, Daniel Re- ichman, Thomas L Griﬃths, Stuart J Russell, Evan C Carter, et al. , “Predicting human decisions with behav- ioral theories and machine learning,” arXiv e-prints , arXiv:1904.06866 (2019)

work page arXiv 1904

[70] [70]

Warning: You are about to be nudged,

George Loewenstein, Cindy Bryce, David Hagmann, and Sachin Rajpal, “Warning: You are about to be nudged,” Behavioral Science & Policy 1, 35 – 42 (2015)

work page 2015

[71] [71]

Prediction-based decisions and fairness: A catalogue of choices, assumptions, and definitions

Shira Mitchell, Eric Potash, and Solon Barocas, “Prediction-based decisions and fairness: A catalogue of choices, assumptions, and deﬁnitions,” arXiv preprint , arXiv:1811.07867 (2018)

work page arXiv 2018

[72] [72]

Beyond prediction: Using big data for policy problems,

Susan Athey, “Beyond prediction: Using big data for policy problems,” Science 355, 483–485 (2017)

work page 2017

[73] [73]

Random forests,

Leo Breiman, “Random forests,” Machine learning 45, 5–32 (2001)

work page 2001

[74] [74]

A recipe for rigor,

Kai Kupferschmidt, “A recipe for rigor,” Science 361, 1192–1193 (2018)

work page 2018

[75] [75]

Artiﬁcial intelligence faces repro- ducibility crisis,

Matthew Hutson, “Artiﬁcial intelligence faces repro- ducibility crisis,” Science 359, 725–726 (2018)

work page 2018

[76] [76]

Counterfactual fairness,

Matt J Kusner, Joshua Loftus, Chris Russell, and Ricardo Silva, “Counterfactual fairness,” Advances in Neural Information Processing Systems , 4066–4076 (2017)

work page 2017

[77] [77]

Learning fair representations,

Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork, “Learning fair representations,” Pro- ceedings of International Conference on Machine Learn- ing , 325–333 (2013)

work page 2013

[78] [78]

Algorithmic fairness,

Jon Kleinberg, Jens Ludwig, Sendhil Mullainathan, and Ashesh Rambachan, “Algorithmic fairness,” AEA Pa- pers and Proceedings 108, 22–27 (2018)

work page 2018

[79] [79]

Did the Model Understand the Question?

Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan, and Kedar Dhamdhere, “Did the model understand the question?” arXiv e-print , arXiv:1805.05492 (2018)

work page internal anchor Pith review Pith/arXiv arXiv 2018

[80] [80]

Optimized pre-processing for discrimination pre- vention,

Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, and Kush R Varsh- ney, “Optimized pre-processing for discrimination pre- vention,” in Advances in Neural Information Process- ing Systems 30 , edited by I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Curran Associates, Inc., 2017) ...

work page 2017