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.     

Firm age and performance

Amid increasing interest in firm age and its effects on firm performance, this special issue offers an exhaustive review of the literature and a novel collection of evidence on the effects of firm age on performance, including a special focus of interest on innovation performance, financial performance, exports, survival and growth. This editorial positions the theme in the extant literature, and provides key definitions and challenges ahead in the field of evolutionary economics. It introduces the collection of articles composing the special issue. The papers offer a diversity of country contexts, as well as analytical approaches and methods. They include an exhaustive review of the literature on age and firms’ performance, and present original empirical studies focusing on the effects of age on firms’ economic outcomes on the one hand, and on innovation outcomes on the other hand. While most of the papers use econometric analysis, the level of analysis ranges from firm to individual.     

Killing off cohorts: Forecasting mortality of non-extinct cohorts with the penalized composite link model

Mortality forecasting has crucial implications for insurance and pension policies. A large amount of literature has proposed models to forecast mortality using cross-sectional (period) data instead of longitudinal (cohort) data. As a consequence, decisions are generally based on period life tables and summary measures such as period life expectancy, which reflect hypothetical mortality rather than the mortality actually experienced by a cohort. This study introduces a novel method to forecast cohort mortality and the cohort life expectancy of non-extinct cohorts. The intent is to complete the mortality profile of cohorts born up to 1960. The proposed method is based on the penalized composite link model for ungrouping data. The performance of the method is investigated using cohort mortality data retrieved from the Human Mortality Database for England & Wales, Sweden, and Switzerland for male and female populations.     

Environmental quality indicators: Background,principles and examples from Norway

The need for a simple and general overview of the development in the state of the environment has led to work on environmental indicators in several countries and international organizations. Except for the basic common requirement of providing an overview, the works vary a great deal with regard to final aim, target groups, classification and, hence, choice of indicators. This paper gives an overview of the work carried out in the Central Bureau of Statistics of Norway within this field, with emphasis on the basic principles behind the choice of indicators. A hierarchical system of indicator sets is proposed, and examples of indicators are presented. Also, a brief overview of work carried out elsewhere is included.     

On commodification: volunteer experiences in festivals†

This paper is about the creation of non-commodified volunteer experiences, for tourists and local volunteers participating in festivals. How is the tourist experience created when most of the traditional tourism demands are not fulfilled? And what are the experiences and how do they relate to different ‘regimes of value’? The experience context includes tourists who work together with locals voluntarily in a festival, where the volunteers pay for their own travel, food, overnight stay, and work for free. To gain more knowledge on the volunteers is important because local cultural life becomes more festivalized, most festivals are reliant on the involvement of volunteers, and the festivals gain an important role in an economy where even small places are engaged in branding [Löfgren, O. 2003. The new economy: A cultural history. Global Networks, 3, 239–254]. This paper uses a qualitative approach. Interviews were conducted (n?=?23) and participants were observed during four festivals in Finnmark, Norway. Nothing in the experiences was facilitated, and the experience creation occurred in the work tasks together with volunteer colleagues. It was like a holiday experience, without a stream of commodified moments. It was a value creation that could be seen as authentic and real, created in the interaction between the local and visiting volunteers.     

Non-cooperative exploitation of multi-cohort fisheries—The role of gear selectivity in the North-East Arctic cod fishery

North-East Arctic cod is shared by Russia and Norway. Taking its multi-cohort structure into account, how would optimal management look like? How would non-cooperative exploitation limit the obtainable profits? To which extent could the strategic situation explain today’s over-harvesting? Simulation of a detailed bio-economic model reveals that the mesh size should be significantly increased, resulting not only in a doubling of economic gains, but also in a biologically healthier age-structure of the stock. The Nash equilibrium is close to the current regime. Even when effort is fixed to its optimal level, the non-cooperative choice of gear selectivity leads to a large dissipation of rents.     

Economics at DG Competition 2006–2007

This paper discusses a number of significant developments in the enforcement activities of the Directorate General for Competition at the European Commission, during 2006–2007. It covers a selection of investigations as well as policy initiatives that have triggered a debate in terms of the underlying economics.     

Richer and cleaner—At others’ expense?

In rich economies emissions of many pollutants tend to grow at a slower rate than GDP. This could be a result of shifting comparative advantages. If so, net imports of dirty products to these economies will increase and rather than reduced, emissions will be relocated to other countries. In this paper we investigate if decoupling in a rich, open economy coincides with such pollution leakages abroad. Based on historical observations and model projections, we find little evidence to support this hypothesis. Historically, decoupling coincides with falling pollution leakages. Projections over a period of decades indicate a weakening of the decoupling, but that leakages will increase.     

Auditing and the Purification of Blame

Although public sector special audit and performance audit are frequently involved in blame, very few studies (save for Radcliffe 1997) provide detailed empirical accounts on how auditing participates in blame allocation. This study sets out to study one case of blame allocation by describing and characterizing the origins of failure and antecedents leading to the need for blame allocation, the institutional entities and arrangements that participate in the blame game, and how these entities, including the supreme audit institution, are mobilized in the processes of blame allocation. Applying a case methodology with Actor–Network Theory principles, the study extends Hood's (2002, 2007) research on blame and blame avoidance strategies by showing how a blame‐frame evaluates and allocates blame. The contribution of the paper is in four parts: first, it reveals the mechanisms that cause scapegoating of particular people and the role of auditors as experts in such mechanisms; second, it assists to develop an understanding of some factors at the core of the “accountability paradox” noted by Roberts (2009); third, it contributes to explanations as to why failing public sector reforms survive controversy and scandal since a scapegoating process can “reboot” reforms by erasing the reform's problems; and fourth, it demonstrates that an understanding of blame can be a useful addition to Actor–Network Theory.     

The stock market and investment in the small and open Norwegian economy

The relationship between the stock market and investment is analyzed by utilizing a multivariate vector autoregressive model, which also includes fundamentals represented by production and the bank interest rate. Two important results appear on the basis of data from the small, open economy of Norway. The financial market has no lead effect on real activity, as neither the stock market nor the credit market can predict future investment or production. On the contrary, current stock returns correlate negatively with lagged growth in investment, and positively with current growth in production. In addition, changes in the bank interest rate have a positive effect on future stock returns, production leads investment positively, and both production and the bank interest rate become exogenous variables in our model. First version received: November 1997/Final version received: October 2000