Machine learning for financial transaction classification across companies using character-level word embeddings of text fields

An important initial step in accounting is mapping financial transfers to the corresponding accounts. We devised machine-learning-based systems that automate this process. They use word embeddings with character-level features to process transaction texts. When considering 473 companies independently, our approach achieved an average top-1 accuracy of 80.50%, outperforming baselines that exclude the transaction texts or rely on a lexical bag-of-words text representation. We extended the approach to generalizes across companies and even across different corporate sectors. After standardization of the account structures and careful feature engineering, a single classifier trained on 44 companies from 28 sectors achieved a test accuracy of more than 80%. When trained on 43 companies and tested on the remaining one, the system achieved an average performance of 64.62%. This rate increased to nearly 70% when considering only the largest sector.     

The Effect of Media Coverage on the Pricing of Seasoned Equity Offerings

This paper examines the role of media coverage and investor attention on the outcomes of seasoned equity offerings (SEOs). I use an archive of Thomson Reuters news articles to proxy for firm visibility and investor attention. I find that the volumes of news articles prior to the offerings are positively associated with the offer price discounts of SEOs. Furthermore, the volumes of news articles are negatively associated with the cumulative abnormal returns three days around the SEOs. I conclude that the costs of equity increase with media coverage prior to SEOs. Overall, the evidence is consistent with the hypothesis that media coverage affects investors' information processing in SEOs. Copyright © 2018 ASAC. Published by John Wiley & Sons, Ltd.     

A conceptual model and research agenda for bidding,planning and delivering Major sport events that lever human rights

In this conceptual article, the authors propose a framework for how progressive human rights outcomes may be obtained in the context of bidding, planning and implementing major sport events (MSEs) through the implementation of four pathways, including good governance, the democratic participation of stakeholders, the formalisation of human rights agendas and the deployment of sensitive urban development. The authors argue that there is a need for adherence to internationally recognised standards, such as the Universal Declaration of Human Rights and the United Nations Guiding Principles on Business and Human Rights if rhetorical statements from MSE awarding bodies and host organisers are to be accountable to a wider set of actors. If researchers and practitioners want to address some of the critical issues related to human rights and MSEs, it is imperative that key actors working in the rights sphere are involved in shaping the research agenda and monitoring its implementation. Academics need to take a proactive approach aimed at achieving both theoretically grounded and practically relevant solutions, with engagement occurring over an extended period of time. This approach, avowedly political and concerned with genuine action, is a key way in which MSE stakeholders can be held to account for their actions in regard to human rights.     

Application of Standardization Methods for Environmental Improvement as an Element of Quality of Life Through the Development of a Company’s Business Potential

Various aspects of sustainable development and quality of life are considered, including the impact of standardization. Particular attention is paid to the study of the role played by standardization in improving environmental protection. In this connection the significance of standardization is shown as a factor of improving the technological potential of an enterprise and the quality of life. Various approaches to methods for assessing the effective impact of standardization on the quality of life are analyzed.     

Flood Risk and Salience: New Evidence from the Sunshine State

A growing literature finds evidence that flood risk salience varies over time, spiking directly following a flood and then falling off individuals' cognitive radar in the following years. In this article, we provide new evidence of salience exploiting a hurricane cluster impacting Florida that was preceded and followed by periods of unusual calm. Utilizing residential property sales across the state from 2002 through 2012, our main estimate finds a salience impact of ?8%, on average. The salience effect persists when we base estimation only on spatial variation in prices to limit confounding from other simultaneous changes due to shifting hedonic equilibria over time. These effects range from housing prices decreases of 5.4–12.3% depending on the year of sale. Understanding flood risk salience has important implications for flood insurance and disaster policy, the benefits transfer literature, and, more broadly, our understanding of natural disaster resilience. JEL Classification: Q51, Q54, R21     

Testing the Empirical Relevance of the ‘Saving for a Rainy Day’ Hypothesis in US Metro Areas

The joint implication of the consumption Euler equation and cointegration between income and consumption is that savings predict future income declines, the ‘saving for a rainy day’ hypothesis. The empirical relevance of this hypothesis plays a key role in discussions of fiscal policy multipliers, and it holds under the null that the permanent income hypothesis is true. We find little support for this hypothesis using time series data for the 100 largest US Metropolitan Statistical Areas for the period 1980q1–2015q4. Our approach is to test for cointegration and weak exogeneity between income and consumption, and by exploring the direction of Granger causality between the two time series. We find that income more often predicts consumption and saving than the converse. We also give evidence that house price changes played a role in US income and consumption dynamics, before, during and after the Great Recession.     

Media-Based Sentiment Indices as an Alternative Measure of Consumer Confidence

In this paper, we consider the feasibility of constructing online sentiment indices, using large amounts of media data, as an alternative to the conventional survey method used to create the consumer confidence index in South Africa. A clustering framework is adopted to provide an indication of possible candidate sentiment indices constructed from a combination of different text sources and dictionaries that best mimic the traditional survey-based consumer confidence index from the South African Bureau for Economic Research (BER). The results conclude that it is possible to create an index using sentiment analysis using online editorial data that does resemble the BER’s consumer confidence index. The different media-based sentiment indices (MSI) show a significant level of correlation and co-movement with the BER’s CCI. Impulse responses and cross-correlation functions indicate that the MSI could potentially lead the survey-based method up to two quarters. Furthermore, Granger-causality tests show that the media-based indices are good predictors of future consumer confidence index values. The results provide motivation for further study on the use of sentiment-based techniques and online media data sources to track consumer confidence within an emerging market such as South Africa.     

Stock market volatility forecasting: Do we need high-frequency data?

The general consensus in the volatility forecasting literature is that high-frequency volatility models outperform low-frequency volatility models. However, such a conclusion is reached when low-frequency volatility models are estimated from daily returns. Instead, we study this question considering daily, low-frequency volatility estimators based on open, high, low, and close daily prices. Our data sample consists of 18 stock market indices. We find that high-frequency volatility models tend to outperform low-frequency volatility models only for short-term forecasts. As the forecast horizon increases (up to one month), the difference in forecast accuracy becomes statistically indistinguishable for most market indices. To evaluate the practical implications of our results, we study a simple asset allocation problem. The results reveal that asset allocation based on high-frequency volatility model forecasts does not outperform asset allocation based on low-frequency volatility model forecasts.     

Auditors,Specialists, and Professional Jurisdiction in Audits of Fair Values

Auditors frequently use valuation specialists to help them evaluate fair values, but researchers and regulators know little about how auditors use these specialists. Based on interviews with 28 auditors and 14 valuation specialists, I develop a theoretical framework informed by expert systems and professional competition theories. The interviews suggest that institutional pressures in the fair value environment unevenly impact auditors and specialists, causing tension between auditors' needs for ontological security and jurisdictional claims. This tension leads to one-sided competition between auditors and specialists and incomplete acceptance of specialists' work. Auditors' competitive behaviors coupled with this incomplete acceptance result in a tendency to make specialists' work conform to auditors' views. Collectively, these findings suggest that auditors use specialists as an institutional mechanism to create comfort, but not insight. This study links expert systems and professional competition theories, and it provides critical insight into some assumptions underlying tenets of each theory. It also informs researchers, regulators, and practitioners interested in understanding and addressing problems related to the use of specialists.     

How much are electric vehicles driven?

The prospect for electric vehicles as a climate change solution hinges on their ability to reduce gasoline consumption. But this depends on how many miles electric vehicles are driven and on how many miles would have otherwise been driven in gasoline-powered vehicles. Using newly-available U.S. nationally representative data, this paper finds that electric vehicles are driven considerably fewer miles per year on average than gasoline-powered vehicles. The difference is highly statistically significant and holds for both all-electric and plug-in hybrid vehicles, for both single- and multiple-vehicle households, and both inside and outside California. The paper discusses potential explanations and policy implications. Overall, the evidence suggests that today’s electric vehicles imply smaller environmental benefits than previously believed.