Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts
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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2021-06-01
|
| Series: | Journal of Social Computing |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.23919/JSC.2021.0009 |
| _version_ | 1797986194602065920 |
|---|---|
| author | Lu Hong PJ Lamberson Scott E Page |
| author_facet | Lu Hong PJ Lamberson Scott E Page |
| author_sort | Lu Hong |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T07:30:10Z |
| format | Article |
| id | doaj.art-ceb2fdec22914da387c22a24f5219619 |
| institution | Directory Open Access Journal |
| issn | 2688-5255 |
| language | English |
| last_indexed | 2024-04-11T07:30:10Z |
| publishDate | 2021-06-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Journal of Social Computing |
| spelling | doaj.art-ceb2fdec22914da387c22a24f52196192022-12-22T04:36:57ZengTsinghua University PressJournal of Social Computing2688-52552021-06-01228910210.23919/JSC.2021.0009Hybrid Predictive Ensembles: Synergies Between Human and Computational ForecastsLu Hong0PJ Lamberson1Scott E Page2<institution content-type="dept">Department of Finance</institution>, <institution>Loyola University Chicago</institution>, <city>Chicago</city>, <postal-code>IL 606002</postal-code>, <country>USA</country><institution content-type="dept">Department of Communication</institution>, <institution>University of California at Los Angeles (UCLA)</institution>, <city>Los Angeles</city>, <postal-code>CA 90095</postal-code>, <country>USA</country><institution content-type="dept">Ross Business School</institution>, <institution>University of Michigan</institution>, <city>Ann Arbor</city>, <postal-code>MI 48104</postal-code>, <country>USA</country>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.https://www.sciopen.com/article/10.23919/JSC.2021.0009collective intelligencepredictive modelshybrid groupsbig datathick data |
| spellingShingle | Lu Hong PJ Lamberson Scott E Page Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts Journal of Social Computing collective intelligence predictive models hybrid groups big data thick data |
| title | Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts |
| title_full | Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts |
| title_fullStr | Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts |
| title_full_unstemmed | Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts |
| title_short | Hybrid Predictive Ensembles: Synergies Between Human and Computational Forecasts |
| title_sort | hybrid predictive ensembles synergies between human and computational forecasts |
| topic | collective intelligence predictive models hybrid groups big data thick data |
| url | https://www.sciopen.com/article/10.23919/JSC.2021.0009 |
| work_keys_str_mv | AT luhong hybridpredictiveensemblessynergiesbetweenhumanandcomputationalforecasts AT pjlamberson hybridpredictiveensemblessynergiesbetweenhumanandcomputationalforecasts AT scottepage hybridpredictiveensemblessynergiesbetweenhumanandcomputationalforecasts |