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.     

Combining data and text mining techniques for analysing financial reports

There is a vast amount of financial information on companies' financial performance available to investors in electronic form today. While automatic analysis of financial figures is common, it has been difficult to extract meaning from the textual parts of financial reports automatically. The textual part of an annual report contains richer information than the financial ratios. In this paper, we combine data and text mining methods for analysing quantitative and qualitative data from financial reports, in order to see if the textual part of the report contains some indications about future financial performance. The quantitative analysis has been performed using self‐organizing maps, and the qualitative analysis using prototype‐matching text clustering. The analysis is performed on the quarterly reports of three leading companies in the telecommunications sector. Copyright © 2004 John Wiley & Sons, Ltd.     

Consumer Self-Control Strategies: An Empirical Study of Their Structure and Determinants

People use self-control strategies to overcome time-inconsistent preferences. In the present study one aim was to test a two-factor model of consumer self-control strategies that divides them into desire-reducing and willpower strategies. Another aim was to explore what may determine the use of such strategies. Exploratory and confirmatory factor analyses gave support for the two-factor model of self-control. A positive attitude toward risk taking as well as the intention to reduce consumption in response to economic impairment predicted a decrease in the use of both strategies. Financial situation, age, and sex were found to influence the use of desire reduction and willpower in different directions. Income was not a predictor of the use of self-control strategies.     

Health and development∗

The linkage between development and health is clearly spelt out in the definition of primary health care by the World Health Organisation. There is a widespread and growing disillusionment with the traditional Western approach to health care which fails to meet the real demands of the Third World situation.

This paper looks briefly at conditions in the developing world and the strategy proposed by the W H O to attempt to meet the objective of health for all by the year 2000 and refers to the South African situation.     

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.     

Technology Sharing in Manufacturing Business Groups

Technology represents the primordial force for companies and organizations in securing long‐term competitiveness. In the intensive search to access new technology, organizations are more and more looking beyond the borders of the focal firm and becoming involved in various networks with suppliers, consultants, partners, and others. However, the distinction between the focal firm, on the one hand, and networks, on the other, is in this paper argued to be too extensive without intermediating nuances. Less focus is given to an in‐between perspective configured by business groups or concerns here defined as parent corporations with subsidiary companies. It is this perspective of business groups with characteristics between individual firms and open networks that is of interest in this paper. The focus is on manufacturing business groups in which the companies will typically have individual as well as common technologies. The research aim is to develop a framework to be used as an analytical tool for understanding and organizing technology sharing in manufacturing business groups. The research approach was to study technology sharing in a natural setting combining multiple in‐depth sources of evidence in a clinical research setting. A prestudy identified key dimensions in classifying cases leading to four clusters of typified cases. Data were gathered from meetings with 24 managers from various research and development (R&D) units who met regularly every other week during seven months, in‐depth interviews, internal documents and protocols, and workshops. Following the clinical field‐study approach, findings are theoretically validated in relation to literature. The analysis identifies and depicts four different types of technology‐sharing scenarios in manufacturing business groups. Each type has particular characteristics of its own. The four scenarios together provide a synthesized portfolio with different types of dimensions. A first dimension makes a distinction between sharing new technology development versus existing technology. Another distinguishes between technologies aimed at the whole business group and those aimed at specific segments. The two dimensions together comprise four different types of technology‐sharing alternatives. Each one of them can be used at the focal firm, and together, they are applicable from a business group perspective comprising technology‐sharing portfolios of manufacturing business groups.     

Editorial

Small Business Economics -     

Introduction to Institutions,Entrepreneurship and Firm Growth: From Sweden to the OECD

Small Business Economics -     

Contents of Volume 19

Volume Contents

Contents of Volume 19     

Practice makes perfect: Entrepreneurial-experience curves and venture performance

This study tackles the puzzle of why increasing entrepreneurial experience does not always lead to improved financial performance of new ventures. We propose an alternate framework demonstrating how experience translates into expertise by arguing that the positive experience–performance relationship only appears to expert entrepreneurs, while novice entrepreneurs may actually perform increasingly worse because of their inability to generalize their experiential knowledge accurately into new ventures. These negative performance implications can be alleviated if the level of contextual similarity between prior and current ventures is high. Using matched employee–employer data of an entire population of Swedish founder-managers between 1990 and 2007, we find a non-linear relationship between entrepreneurial experience and financial performance consistent with our framework. Moreover, the level of industry, geographic, and temporal similarities between prior and current ventures positively moderates this relationship. Our work provides both theoretical and practical implications for entrepreneurial experience—people can learn entrepreneurship and pursue it with greater success as long as they have multiple opportunities to gain experience, overcome barriers to learning, and build an entrepreneurial-experience curve.