AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Social Computing Article
PDF (1.7 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts

Department of Finance, Loyola University Chicago, Chicago, IL 606002, USA
Department of Communication, University of California at Los Angeles (UCLA), Los Angeles, CA 90095, USA
Ross Business School, University of Michigan, Ann Arbor, MI 48104, USA
Show Author Information

Abstract

An increasing proportion of decisions, design choices, and predictions are being made by hybrid groups consisting of humans and artificial intelligence (AI). In this paper, we provide analytic foundations that explain the potential benefits of hybrid groups on predictive tasks, the primary use of AI. Our analysis relies on interpretive and generative signal frameworks as well as a distinction between the big data used by AI and the thick, often narrative data used by humans. We derive several conditions on accuracy and correlation necessary for humans to remain in the loop. We conclude that human adaptability along with the potential for atypical cases that mislead AI will likely mean that humans always add value on predictive tasks.

Keywords

big datacollective intelligencepredictive modelshybrid groupsthick data

References

1
J. Grusin and S. Lindo, Intelligent Analysis: How to Defeat Uncertainty in High-Stakes Decisions. Brighton, UK: Intelligent Risk Management Publications, 2021.
2

J. Mongan and M. Kohli, Artificial intelligence and human life: Five lessons for radiology from the 737 MAX disasters, Radiology:Artificial Intelligence, vol. 2, no. 2, p. e190111, 2020.
Crossref Google Scholar
3
A. Pickering, The Mangle of Practice: Time, Agency, and Science. Chicago, IL, USA: University of Chicago Press, 1995.https://doi.org/10.7208/chicago/9780226668253.001.0001
Crossref
4
G. G. Creamer, Y. Ren, Y. Sakamoto, and J. V. Nickerson, Ensembles of crowds and computers: Experiments in forecasting, Research Paper No. 2015–54, School of Business, Stevens Institute of Technology, Hoboken, NJ, USA, 2015.https://doi.org/10.2139/ssrn.2673129
Crossref
5
H. Moravec, Mind Children: The Future of Robot and Human Intelligence. Cambridge, MA, USA: Harvard University Press, 1988.
6
B. Latour, Reassembling the Social: An Introduction to Actor-Network-Theory. Oxford, UK: Oxford University Press, 2005.
7
J. Surowiecki, The Wisdom of Crowds. New York, NY, USA: Anchor Books, 2005.
8
Y. Nagar and T. W. Malone, Making business predictions by combining human and machine intelligence in prediction markets, in Proc. Thirty Second Int. Conf. Information Systems, Shanghai, China, 2011.
9

J. Kleinberg, J. Ludwig, S. Mullainathan, and Z. Obermeyer, Prediction policy problems, The American Economic Review, vol. 105, no. 5, pp. 491–495, 2015.
Crossref Google Scholar
10
P. E. Meehl, Clinical Versus Statistical Prediction: A Theoretical Analysis and a Review of the Evidence. Minneapolis, MN, USA: University of Minnesota Press, 1954.https://doi.org/10.1037/11281-000
Crossref
11
T. Wang, Why big data needs thick data, Ethnography Matter.Medium.com, 2016.
12

A. Tacchella, S. Romano, M. Ferraldeschi, M. Salvetti, A. Zaccaria, A. Crisanti, and F. Grassi, Collaboration between a human group and artificial intelligence can improve prediction of multiple sclerosis course: A proof-of-principle study, F1000Research, vol. 6, p. 2172, 2017.
Crossref Google Scholar
13

D. Kahneman, A. M. Rosenfield, L. Gandhi, and T. Blaser, Noise: How to overcome the high, hidden cost of inconsistent decision making, Harvard Business Review, pp. 36–43, 2016.
Google Scholar
14

Z. Obermeyer, B. Powers, C. Vogeli, and S. Mullainathan, Dissecting racial bias in an algorithm used to manage the health of populations, Science, vol. 366, no. 6464, pp. 447–453, 2019.
Crossref Google Scholar
15

A. Caliskan, J. J. Bryson, and A. Narayanan, Semantics derived automatically from language corpora contain human-like biases, Science, vol. 356, no. 6334, pp. 183–186, 2017.
Crossref Google Scholar
16
B. Uzzi, A simple tactic that could help reduce bias in AI, Harvard Business Review, November 4, 2020.
17
Y. Y. Ang, Integrating big data and thick data to transform public services delivery, Research report, IBM Center for the Business of Government, New York, NY, USA, 2019.
18
S. E. Page, The Model Thinker: What You Need to Know to Make Data Work For You. New York, NY, USA: Basic Books, 2018.
19
J. Ober, Democracy and Knowledge: Innovation and Learning in Classical Athens. Princeton, NJ, USA: Princeton University Press, 2008.https://doi.org/10.1515/9781400828807
Crossref
20
H. Landemore, Democratic Reason: Politics, Collective Intelligence, and the Rule of the Many. Princeton, NJ, USA: Princeton University Press, 2013.https://doi.org/10.23943/princeton/9780691155654.001.0001
Crossref
21

I. D. Couzin, Collective cognition in animal groups, Trends in Cognitive Sciences, vol. 13, no. 1, pp. 36–43, 2009.
Crossref Google Scholar
22

L. Breiman, Random forests, Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
Crossref Google Scholar
23

L. Hong and S. Page, Interpreted and generated signals, Journal of Economic Theory, vol. 144, no. 5, pp. 2174–2196, 2009.
Crossref Google Scholar
24
P. E. Tetlock, Expert Political Judgment: How Good Is It? How Can We Know? Princeton, NJ, USA: Princeton University Press, 2005.
25

B. Mellers, E. Stone, T. Murray, A. Minster, N. Rohrbaugh, M. Bishop, E. Chen, J. Baker, Y. Hou, M. Horowitz, et al., Identifying and cultivating superforecasters as a method of improving probabilistic predictions, Perspectives on Psychological Science, vol. 10, no. 3, pp. 267–281, 2015.
Crossref Google Scholar
26

A. E. Mannes, J. B. Soll, and R. P. Larrick, The wisdom of select crowds, Journal of Personality and Social Psychology, vol. 107, no. 2, pp. 276–299, 2014.
Crossref Google Scholar
27
N. Silver, The Signal and the Noise: Why So Many Predictions Fail—but Some Don’t. New York, NY, USA: Penguin Press, 2012.
28
R. J. Lempert, Robust Decision Making (RDM), in Decision Making under Deep Uncertainty: From Theory to Practice, V. A. W. J. Marchau, W. E. Walker, P. J. T. M. Bloemen, and S. W. Popper, eds. Springer, 2019, pp. 23–51.https://doi.org/10.1007/978-3-030-05252-2_2
Crossref
29
L. Valentino, Cultural logics: Toward theory and measurement, Poetics, doi: 10.1016/j.poetic.2021.101574.https://doi.org/10.1016/j.poetic.2021.101574
Crossref
30
T. Y. Schalter, Does the NFL combine have any predictive value to NFL success? Bleacher Report, https://bleacherreport.com/articles/1535606, 2013.
31

P. J. Lamberson and S. E. Page, Tipping points, Quarterly Journal of Political Science, vol. 7, no. 2, pp. 175–208, 2012.
Crossref Google Scholar
32
D. Kahneman, O. Sibony, and C. R. Sunstein, Noise: A Flaw in Human Judgment. New York, NY, USA: Little, Brown, and Company, 2021.
33

P. J. Lamberson and S. E. Page, Optimal forecasting groups, Management Science, vol. 58, no. 4, pp. 805–810, 2012.
Crossref Google Scholar
34

Y. Yuan, A. Alabdulkareem, and A. Pentland, An interpretable approach for social network formation among heterogeneous agents, Nature Communications, vol. 9, no. 1, p. 4704, 2018.
Crossref Google Scholar
Journal of Social Computing
Volume 2 Issue 2,
June 2021
Pages 89-102
DOI: 10.23919/JSC.2021.0009
Cite this article:
Hong L, Lamberson P, Page SE. Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts. Journal of Social Computing, 2021, 2(2): 89-102. https://doi.org/10.23919/JSC.2021.0009

1810

Views

116

Downloads

9

Crossref

9

Scopus

Altmetrics
Received: 24 June 2021
Accepted: 26 June 2021
Published: 23 August 2021
© The author(s) 2021

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return