Should asset managers pay for economic research? A machine learning evaluation

Rybiński, Krzysztof

doi:10.1016/j.jfds.2020.08.001

Cited by 2 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 2021 ) suggest that the Quanteda R package is one of the most efficient software packages to process sentiment in financial texts. This approach is also commonly used in the economics and finance literature (e.g., Dybowski and Kempa 2020 , Rybinski 2020 , Ferrara et al. 2021 , etc.)…”

Section: Notesmentioning

confidence: 99%

“…Benoit et al (2018) and Arratia et al (2021) suggest that the Quanteda R package is one of the most efficient software packages to process sentiment in financial texts. This approach is also commonly used in the economics and finance literature (e.g., Dybowski and Kempa 2020, Rybinski 2020, Ferrara et al 2021 The Quanteda R package identifies the sentiment by using the Lexicoder Sentiment Dictionary (Young and Soroka 2012). Lexicoder Sentiment Dictionary is a bag-of-word dictionary designed for automatic sentiment coding that is widely used in news coverage, legislative debates and public policy.…”

Section: Notesmentioning

confidence: 99%

See 1 more Smart Citation

COVID‐19 Disclosures and Market Uncertainty: Evidence from 10‐Q Filings

Hao

Pham

2022

Australian Accounting Review

View full text Add to dashboard Cite

We examine whether the quarterly filing COVID‐19 disclosures reduce uncertainty for investors and analysts. We find a negative relationship between COVID‐19 disclosure and return volatility, suggesting COVID‐19 disclosure reduces investor uncertainty. This reduction effect concentrates mainly during the short window following 10‐Q releases and phases out over time. We then detect that industry‐wide COVID‐19 disclosure dispersion is positively associated with return volatility, suggesting high variation of industry‐wide COVID‐19 disclosures reduces information comparability across firms, resulting in increased investor uncertainty. Moreover, we find that COVID‐19 disclosures are positively associated with analysts’ downward earnings forecast revisions and negatively associated with analyst forecast dispersion after 10‐Q releases, suggesting the disclosures reduce information risk even for sophisticated market participants. Further analyses show that COVID‐19 disclosures are negatively associated with future financial and operational performances (i.e., sales, operating cash flow, operating income and ROA). Lastly, we find that the low readability of COVID‐19 disclosure attenuates the negative relation between COVID‐19 disclosure and market volatility. Collectively, our findings suggest that 10‐Q COVID‐19 disclosures contain value‐relevant information that temporarily assists market participants in evaluating the changes in firms’ values in the time of a crisis.

show abstract

Section: Notesmentioning

confidence: 99%

Section: Notesmentioning

confidence: 99%

COVID‐19 Disclosures and Market Uncertainty: Evidence from 10‐Q Filings

Hao

Pham

2022

Australian Accounting Review

View full text Add to dashboard Cite

show abstract

“…AI technologies enable the mining of hidden, innovative patterns and notable information from massive datasets with no need for prior knowledge of the data. Models such as ANNs, BNNs, DL, and SVRs have been employed for predicting the relationship between financial variables (Chen et al, [2021]; Cogoljević et al, [2018]; Wang et al, [2020]; Li et al, [2019]; Rybinski, [2020]; Wu et al, [2020]; Aggarwal et al, [2021]; Rawat et al, [2021]; and Nasir et al, [2021]).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Similarly, Goralski and Tan (2020) analyzed the effects of AI on sustainable development with a special emphasis on the progress of the UN's Sustainable Development Goals, combining the views of business strategy and public policy. In recent times, AI models have been utilized to predict the relationship between financial variables (Safi et al, [2022]; Chen et al, [2021]; Cogoljević et al, [2018]; Wang et al, [2020]; Rybinski [2020]; Wu et al, [2020]) and the spread of COVID-19 (Safi and Sanusi [2021]; Vaishya et al, [2020]; Pham et al,[2020]). These AI techniques enable the identification of hidden, innovative trends and remarkable information in massive datasets with no need for prior understanding of the data.…”

Section: Introductionmentioning

confidence: 99%

Can Oil Price Predict Exchange Rate? Empirical Evidence from Deep Learning

Safi

Aliyu

Ibrahim

et al. 2022

IJEEP

View full text Add to dashboard Cite

This paper critically analyses the predictability of exchange rates using oil prices. Extant literature that investigates the significance of oil prices in forecasting exchange rates remains largely inconclusive due to limitations arising from methodological issues. As such, this study uses deep learning approaches such as Multi-Layer Perceptron (MLP), Convolution Neural Network (CNN), and Long Short-Term Memory (LSTM) to predict exchange rates. In addition, the Empirical Mode Decomposition (EMD) of time series dataset was utilized to ascertain its effect on the quality of prediction. To examine the efficacy of using oil prices in forecasting exchange rates, bivariate models were also built. Of the three bivariate models developed, the EMD-CNN model has the best predictive performance. Results obtained show that oil price information has a strong influence on forecasting exchange rates.

show abstract

Should asset managers pay for economic research? A machine learning evaluation

Cited by 2 publications

References 18 publications

COVID‐19 Disclosures and Market Uncertainty: Evidence from 10‐Q Filings

COVID‐19 Disclosures and Market Uncertainty: Evidence from 10‐Q Filings

Can Oil Price Predict Exchange Rate? Empirical Evidence from Deep Learning

Contact Info

Product

Resources

About