Machine Learning in Economics and Finance

Gogas, Periklis; Papadimitriou, Theophilos

doi:10.1007/s10614-021-10094-w

Cited by 72 publications

(35 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The concept is widely accepted in financial studies, e.g., mergers and acquisitions (Katsafados et al, 2021), and cryptocurrency and Twitter (Huynh, 2021). Therefore, the concept implies a potential direction for economics and finance studies (Gogas & Papadimitriou, 2021). Differing from the Thomson Reuters News Analytics (TRNA) system and the Thomson Reuters MarketPsych Index (TRMI), our study started with raw data extracted from specific Elon Musk tweets.…”

Section: Datamentioning

confidence: 99%

When Elon Musk Changes his Tone, Does Bitcoin Adjust Its Tune?

Huynh

2022

Comput Econ

View full text Add to dashboard Cite

We present a textual analysis that explains how Elon Musk’s sentiments in his Twitter content correlates with price and volatility in the Bitcoin market using the dynamic conditional correlation-generalized autoregressive conditional heteroscedasticity model, allowing less sensitive to window size than traditional models. After examining 10,850 tweets containing 157,378 words posted from December 2017 to May 2021 and rigorously controlling other determinants, we found that the tone of the world’s wealthiest person can drive the Bitcoin market, having a Granger causal relation with returns. In addition, Musk is likely to use positive words in his tweets, and reversal effects exist in the relationship between Bitcoin prices and the optimism presented by Tesla’s CEO. However, we did not find evidence to support linkage between Musk’s sentiments and Bitcoin volatility. Our results are also robust when using a different cryptocurrency, i.e., Ether this paper extends the existing literature about the mechanisms of social media content generated by influential accounts on the Bitcoin market.

show abstract

Section: Datamentioning

confidence: 99%

When Elon Musk Changes his Tone, Does Bitcoin Adjust Its Tune?

Huynh

2022

Comput Econ

View full text Add to dashboard Cite

show abstract

“…CryptoCoinCharts [2] shows 10,125 crypto coins as of April 2021, mostly attributed to factors like BTC open source which allow the continual creation of new cryptocurrencies. Various studies have been conducted to look at cryptos’ risk and return behavior using innovative techniques such as machine learning (ML) (Gogas and Papadimitriou, 2021, for a good overview). A hot topic remains the use of ML to forecast both the price and direction of financial assets, with the use of ML in financial forecasting benefiting from its ability to capture larger data sets and offers solutions to as follows: Economic problems involving many variables (Erel et al , 2021); Complex interactions among variables resulting in high dimensionality in data (Easley et al , 2021); and Cases where prediction is more economically important than statistical inference (Li et al , 2020).…”

Section: Introductionmentioning

confidence: 99%

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Gurrib

Kamalov

2021

SEF

View full text Add to dashboard Cite

Purpose Cryptocurrencies such as Bitcoin (BTC) attracted a lot of attention in recent months due to their unprecedented price fluctuations. This paper aims to propose a new method for predicting the direction of BTC price using linear discriminant analysis (LDA) together with sentiment analysis. Design/methodology/approach Concretely, the authors train an LDA-based classifier that uses the current BTC price information and BTC news announcements headlines to forecast the next-day direction of BTC prices. The authors compare the results with a Support Vector Machine (SVM) model and random guess approach. The use of BTC price information and news announcements related to crypto enables us to value the importance of these different sources and types of information. Findings Relative to the LDA results, the SVM model was more accurate in predicting BTC next day’s price movement. All models yielded better forecasts of an increase in tomorrow’s BTC price compared to forecasting a decrease in the crypto price. The inclusion of news sentiment resulted in the highest forecast accuracy of 0.585 on the test data, which is superior to a random guess. The LDA (SVM) model with asset specific (news sentiment and asset specific) input features ranked first within their respective model classifiers, suggesting both BTC news sentiment and asset specific are prized factors in predicting tomorrow’s price direction. Originality/value To the best of the authors’ knowledge, this is the first study to analyze the potential effect of crypto-related sentiment and BTC specific news on BTC’s price using LDA and sentiment analysis.

show abstract

“…Agent-based computational economics and a complexity economics framework sees the economy in terms of process and seeks to capture the feedback between micro and macro structures by modeling markets made up of diverse non-human agents who can simulate phenomena to allow strategies to evolve in order to study networks, change transmission, systemic risks, norm revolution, and policy gaming (see Arthur, 2021 , p. 136–142, Van de Gevel and Noussair, 2012 ; Gogas and Papadimitriou, 2021 , p. 64–73). But, Mariotti ( 2021 , p. 561–2) refers to the challenges posed by algorithmic collusions (where AI autonomously learns to adopt collusive pricing rules) and points out the problems ahead for prospects of the economies of AI in terms of market manipulations via personalized dynamic pricing, granular forms of indirect price discrimination, and digital doubles of individuals.…”

Section: Economics and Ai Reconsideredmentioning

confidence: 99%

3Es for AI: Economics, Explanation, Epistemology

Kaul

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

This article locates its roots/routes in multiple disciplinary formations and it seeks to advance critical thinking about an aspect of our contemporary socio-technical challenges by bracketing three knowledge formations—artificial intelligence (AI), economics, and epistemology—that have not often been considered together. In doing so, it responds to the growing calls for the necessity of further transdisciplinary engagements that have emanated from work in AI and also from other disciplines. The structure of the argument here is as follows. First, I begin by demonstrating how and why explanation is a problem in AI (“XAI problem”) and what directions are being taken by recent research that draws upon social sciences to address this, noting how there is a conspicuous lack of reference in this literature to economics. Second, I identify and analyze a problem of explanation that has long plagued economics too as a discipline. I show how only a few economists have ever attempted to grapple with this problem and provide their perspectives. Third, I provide an original genealogy of explanation in economics, demonstrating the changing nature of what was meant by an explanation. These systematic changes in consensual understanding of what occurs when something is said to have been “explained”, have reflected the methodological compromises that were rendered necessary to serve different epistemological tensions over time. Lastly, I identify the various relevant historical and conceptual overlaps between economics and AI. I conclude by suggesting that we must pay greater attention to the epistemologies underpinning socio-technical knowledges about the human. The problem of explanation in AI, like the problem of explanation in economics, is perhaps not only, or really, a problem of satisfactory explanation provision alone, but interwoven with questions of competing epistemological and ethical choices and related to the ways in which we choose sociotechnical arrangements and offer consent to be governed by them.

show abstract

Machine Learning in Economics and Finance

Cited by 72 publications

References 20 publications

When Elon Musk Changes his Tone, Does Bitcoin Adjust Its Tune?

When Elon Musk Changes his Tone, Does Bitcoin Adjust Its Tune?

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

3Es for AI: Economics, Explanation, Epistemology

Contact Info

Product

Resources

About