Human and AI Ensembles: When Can They Work?

Choudhary, Vivek; Marchetti, Arianna; Shrestha, Yash Raj; Puranam, Phanish

doi:10.2139/ssrn.3902402

Cited by 5 publications

(1 citation statement)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te other relevant aspect that motivates our humanmachine ensemble algorithm is that any ensemble algorithm benefts from the diversity of its experts, either humans or machines. Te aggregation of very diferent experts helps to manage the tradeof bias-diversity avoiding a bias in a certain direction when all the experts are very similar [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Human and Machine Learning Algorithms to Forecast the European Stock Market

et al. 2023

View full text Add to dashboard Cite

This paper explores the power of news sentiment to predict financial returns, particularly the returns of a set of European stocks. Building on past decision support work going back to the Delphi method, this paper describes a text analysis expert weighting algorithm that aggregates the responses of both humans and algorithms by dynamically selecting the best answer according to previous performance. The proposed system is tested through an experiment in which ensembles of experts, crowds, and machines analyzed Thomson Reuters news stories and predicted the returns of the relevant stocks mentioned right after the stories appeared. In most cases, the expert weighting algorithm was better than or as good as the best algorithm or human. The algorithm’s capacity to dynamically select the best answers from humans and machines results in an evolving collective intelligence: the final decision is an aggregation of the best automated individual answers, some of which come from machines and some from humans. Additionally, this paper shows that the groups of humans, algorithms, and expert weighting algorithms have associated with them, particularly, news topics that these groups are good at making predictions from.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid Human and Machine Learning Algorithms to Forecast the European Stock Market

et al. 2023

View full text Add to dashboard Cite

show abstract

Designing human resource management systems in the age of AI

Tinguely,

Lee,

2023

J Org Design

View full text Add to dashboard Cite

The increasing adoption of artificial intelligence (AI) is reshaping the practices of human resource management (HRM). We propose a typology of HR–AI collaboration systems across the dimensions of task characteristics (routine vs. non-routine; low vs. high cognitive complexity) and social acceptability of such systems among organizational members. We discuss how organizations should design HR–AI collaboration systems in light of issues of AI explainability, high stakes contexts, and threat to employees’ professional identities. We point out important design considerations that may affect employees' perceptions of organizational fairness and emphasize HR professionals' role in the design process. We conclude by discussing how our Point of View article contributes to literatures on organization design and human–AI collaboration and suggesting potential avenues for future research.

show abstract

The rationality of explanation or human capacity? Understanding the impact of explainable artificial intelligence on human-AI trust and decision performance

Wang,

Ding

2024

Information Processing & Management

View full text Add to dashboard Cite

Human and AI Ensembles: When Can They Work?

Cited by 5 publications

References 79 publications

Hybrid Human and Machine Learning Algorithms to Forecast the European Stock Market

Hybrid Human and Machine Learning Algorithms to Forecast the European Stock Market

Designing human resource management systems in the age of AI

The rationality of explanation or human capacity? Understanding the impact of explainable artificial intelligence on human-AI trust and decision performance

Contact Info

Product

Resources

About