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.     

Enhancing Stock Market Return with New Product Preannouncements: The Role of Information Quality and Innovativeness

To advance development and application of signaling theory in the new product preannouncement literature while seeking to resolve ambiguity regarding the influence of innovativeness on stock market return, the role of information quality is examined. Specifically, this study investigates the effect of innovativeness across low and high levels of information quality. The results, ascertained using event study methodology on a sample of 243 new product preannouncements collected over a nine‐year period, indicate that higher information quality increases the strength of the positive relationship between innovativeness and stock market return. The findings offer managers insight into what role information quality plays in new product preannouncements that can help their firms generate higher stock market return.     

A Tutorial on Palm Distributions for Spatial Point Processes

This tutorial provides an introduction to Palm distributions for spatial point processes. Initially, in the context of finite point processes, we give an explicit definition of Palm distributions in terms of their density functions. Then we review Palm distributions in the general case. Finally, we discuss some examples of Palm distributions for specific models and some applications.     

Aufdeckung von Versicherungsbetrug bei Kfz-Schäden mit Hilfe des Benford-Tests

The German Insurance Association estimates a yearly amount of damage of € 1.5?bn to German motor vehicle insurance companies because of systematic fraud by insurance holders. It is supposed that about 10% of submitted claim applications contain manipulated data, therefore insurance companies are forced to complete a detailed and cost intensive case-by-case review of each single application. An alternative method to detect fraud in empiric data is the method of digital analysis based on Benford’s law. The Benford method uses a mathematical law of specific logarithmic distribution attributes of first digits. According to this approach, the data of a Benford set confirm with the expected digit distribution, if the data is not manipulated, whereas fraudulent interventions lead to a deviation from Benford’s law. Hence, until now there has not been any investigation whether the Benford method can also be applied on insurance data. The present article analyses a dataset consisting of more than 120,000 damage claim applications to answer this question as well as to identify the impact of specific characteristics on the probability of fraud contained in claim applications, such as the repair of the vehicle in a franchised or an independent workshop, the vehicle brand or the examination by insurance companies experts. Indeed it could be shown that Benford’s Law is only applicable on second digits of insurance data, but delivers very strong results here: All results of the considered characteristics could be verified by plausible arguments. For this reason insurance companies can benefit from making use of the Benford method to identify those claim applications with a high probability of fraud, which should then be reviewed in more detail so that resources can be allocated in a much more cost efficient way.     

Adverse Selection,Investor Experience and Security Choice in Venture Capital Finance: Evidence from Germany

This article analyses 336 German venture capital transactions from 1990 to 2005 and seeks to determine why selected financial securities differ across deals. We find that a broad array of financial instruments is used, covering straight equity, mezzanine and debt‐like securities. Based on the chosen financial securities’ upside potential and downside protection characteristics, we provide an explanation for the differing use of these securities. Our results show that investors’ deal experience, adverse selection risks and economic prospects in the public equity market influence the selection of financial securities.     

Procurement of logistics services and sustainable development in Europe: Fields of activity and empirical results

This paper strives to answer the general question; how far purchasers of logistics services take into account aspects of sustainable development. Modeled on the German Sustainable Development Strategy, which is based on the EU Sustainable Development plan, five fields of activity are defined: the reduction of transport intensity and emission, the reduction of land use, the choice of carrier under consideration of sustainable aspects, the permanent improvement of working conditions, and the enhancement of qualified employment. Then, propositions for purchasing companies of logistics services are developed, which contribute to safeguard ecological as well as social sustainability. In order to conduct an explorative study, a questionnaire was sent to 750 purchase and logistics managers. It was found that purchasing companies place high value on ecological and social aspects. But the perceived importance is not associated with purchasing companies' own contributions to logistics service providers' sustainable activities. Additionally, it was seen that purchasing companies exert only a minor influence on logistics service providers regarding ecologically and socially sustainable actions. A fundamental precondition for a sustainably oriented procurement of logistics services can be seen in the purchasing companies' awareness of the need for integrating sustainable aspects in economic decisions.     

The perceived fairness of performance evaluation: The role of uncertainty

This paper investigates the relationship between performance evaluation procedures and managerial perceptions of procedural justice. We examine two metric and two process characteristics. Metric characteristics are the diversity of metrics used by superiors and their reliance on outcome vs. effort metrics. Regarding process characteristics, we analyse the amount of subordinate's voice in the performance evaluation process, and the extent of formalization of the process. Using uncertainty management theory, we argue that justice effects of performance evaluation procedures may not be direct but are instead conditional on the amount of task uncertainty managers face in the their job context as well as on managers’ tolerance for ambiguity. Using a sample of 178 managers from the banking industry, we find that all four performance evaluation characteristics are related to justice perceptions, yet their effect depends on the level of task uncertainty and tolerance for ambiguity. These findings explain some inconsistencies in extant studies on fairness of performance evaluation procedures.     

Purchasing Competence: A Stakeholder‐Based Framework for Chief Purchasing Officers

A specific research stream within the purchasing and supply management literature focuses on the development of purchasing competence frameworks. We apply stakeholder theory and multiple methods of data collection to develop and confirm a hierarchy‐specific purchasing competence management framework for Chief Purchasing Officers and validate it using confirmatory factor analysis on empirical data from 124 multinational companies. The results reveal a significant relationship between Chief Purchasing Officers purchasing management competence and different purchasing performance measures confirming the appropriateness of stakeholder theory for such a competence framework.