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.     

A note on forecasting the prices of gold and silver: Asymmetric loss and forecast rationality

Given that the prices of gold and silver have witnessed large and substantial swings in recent years, policymakers and investors need readily available and reliable forecasts of the prices of these two precious metals. Survey data of forecasts of the prices of gold and silver provide a particularly rich data environment for policymakers and investors to study developments in the markets for gold and silver. Our research helps to develop a deeper understanding of the properties of survey data of the prices of gold and silver. We study the shape of forecasters’ loss function and the rationality of their forecasts. Assuming an asymmetric loss function weakens evidence against forecast rationality, but results depend on the empirical model being studied.     

What Drives Fraud in a Credence Goods Market? – Evidence from a Field Study

This paper investigates the impact of competition on an expert firm's incentive to defraud its customers in a credence goods market. Controlling for the competence of car repair shops, their financial situation, and reputational concerns, we use and complement the data set from a nationwide field study conducted by the German Automobile Association that regularly checks the reliability of garages in Germany. We find that more intense competition lowers a firm's incentive to defraud its customers.     

Short-haul city travel is truly environmentally sustainable

With rising interest in and concern about climate change and environmental sustainability, and the significance of the tourism industry worldwide, the impact of tourism-related activities and behaviors on the environment has become a key area of research. In particular, transport related to tourism has come under scrutiny for its contribution to the ecological footprint of tourism of a destination, mostly accounted for by the dominance of air travel. This study contributes to research in this area by identifying the types of travel situations in which tourists make environmentally friendly choices about travel modes and, consequently, which types of tourism destinations should seek to develop and promote in order to minimize the environmental impact of the tourist sector on both an individual destination and global scale.     

Innovation and performance in the hotel industry

The growing competition in the hotel industry is one of the main challenges of this segment, which increasingly depends on the ability to innovate. Thus, this article aims to analyze the impact of innovation on the performance of employees and hotel organizations. This is an exploratory study, with a quantitative approach using a structured computer-administered questionnaire to 73 managers of hotel chains, located in Brazil, which correspond to 792 hotels. Data analysis used multiple linear regression method with SPSS software to find out the relationship between the factors of innovation (communication, processes, leadership, and strategy) and the performance of employees and hotel organizations. Results show that the factors of communication, leadership, and strategy directly influence the performance of the employees. However, only the leadership factor directly affects the performance of hotel organizations.     

Awareness as a foundation for developing effective spatial data infrastructures

The development of an effective spatial data infrastructure (SDI) often occurs in a fragmented organizational environment requiring a high level of inter-organizational collaboration. Different organizations from various jurisdictions need to work together closely when agreeing on how they will jointly register, store, use and share data and how they will make their data available to the wider society. However, this collaboration is generally regarded as very difficult. For example people often resist data sharing across organizational boundaries due to loss of control, power and independency. Organizational issues are thus considered one of the fundamental constraints to inter-organizational sharing of spatial data.