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.     

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.     

Do interventions in foreign exchange markets modify investors' expectations? The experience of Japan between 1992 and 2004

The purpose of this paper is to analyze the impact of the Bank of Japan's official interventions on the JPY/USD parity during the period 1992–2004. The novelty of our approach is to combine two recent advances of the empirical literature on foreign exchange interventions: (i) drawing on over-the-counter option prices to characterize more precisely the distribution of market expectations; (ii) redefining interventions in terms of events as they tend to come in clusters. Moreover, in order to deal with the features of the data (small sample size, non-standard distribution), we use bootstrap tests.We show that interventions have a significant impact on the mean expectation (the forward rate). The results are more ambiguous for variance. Additionally, we find that the effect of interventions on skewness is significant, robust to different definitions of skewness, and consistent with the direction of interventions. On the contrary, our results clearly show that kurtosis is not affected by interventions. We finally show that: (i) coordination increases effectiveness of interventions; (ii) results are not altered when controlling for other economic and political news.     

How to measure mutual fund performance: economic versus statistical relevance

In the present paper a comprehensive assessment of existing mutual fund performance models is presented. Using a survivor‐bias free database of all US mutual funds, we explore the added value of introducing extra variables such as size, book‐to‐market, momentum and a bond index. In addition to that we evaluate the use of introducing time‐variation in betas and alpha. The search for the most suitable model to measure mutual fund performance will be addressed along two lines. First, we are interested in the statistical significance of adding more factors to the single factor model. Second, we focus on the economic importance of more elaborate model specifications. The added value of the present study lies both in the step‐wise process of identifying relevant factors, and the use of a rich US mutual fund database that was recently released by the Center for Research in Security Prices.     

Strategy Creation in the Periphery: Inductive Versus Deductive Strategy Making*

abstract   Although strategy process research has provided careful and in-depth descriptions and examinations of strategy, micro-level processes and activities have been less commonly evaluated, especially as regards strategy creation and development. This paper examines how managers create and develop strategy in practice. A dual longitudinal case methodology, including a single in-depth study combined with a multiple retrospective study is used, involving four multinational companies. The findings show a twofold character of strategy creation, including fundamental different strategy activities in the periphery and centre, reflecting their diverse location and social embeddedness. Strategy making in the periphery was inductive , including externally oriented and exploratory strategy activities like trial and error, informal noticing, experiments and the use of heuristics. In contrast, strategy making in the centre was more deductive involving an industry and exploitation focus, and activities like planning, analysis, formal intelligence and the use of standard routines.     

Playing the synthesizer with Canadian data: Adding polls to a structural forecasting model

Election forecasting has become a fixture of election campaigns in a number of democracies. Structural modeling, the major approach to forecasting election results, relies on ‘fundamental’ economic and political variables to predict the incumbent’s vote share usually a few months in advance. Some political scientists contend that adding vote intention polls to these models—i.e., synthesizing ‘fundamental’ variables and polling information—can lead to important accuracy gains. In this paper, we look at the efficiency of different model specifications in predicting the Canadian federal elections from 1953 to 2015. We find that vote intention polls only allow modest accuracy gains late in the campaign. With this backdrop in mind, we then use different model specifications to make ex ante forecasts of the 2019 federal election. Our findings have a number of important implications for the forecasting discipline in Canada as they address the benefits of combining polls and ‘fundamental’ variables to predict election results; the efficiency of varying lag structures; and the issue of translating votes into seats.     

Learning for Innovation and the Skill Premium

The rc="/content/j8y5ty4cwj9kupef/xxlarge8220.gif" alt="ldquo" align="MIDDLE" BORDER="0">computer revolutionrc="/content/j8y5ty4cwj9kupef/xxlarge8221.gif" alt="rdquo" align="MIDDLE" BORDER="0"> took very long to pay off in productivity growth in the computer-using sectors. The relative wage of skilled workers, however, has risen sharply from the early days of the rc="/content/j8y5ty4cwj9kupef/xxlarge8220.gif" alt="ldquo" align="MIDDLE" BORDER="0">computer revolutionrc="/content/j8y5ty4cwj9kupef/xxlarge8221.gif" alt="rdquo" align="MIDDLE" BORDER="0"> onward. As skilled workersrc="/content/j8y5ty4cwj9kupef/xxlarge8217.gif" alt="rsquo" align="BASELINE" BORDER="0"> wages reflect their productivity, the two observations together pose a puzzle.This paper provides a micro-based explanation for the long diffusion period of the rc="/content/j8y5ty4cwj9kupef/xxlarge8220.gif" alt="ldquo" align="MIDDLE" BORDER="0">computer revolutionrc="/content/j8y5ty4cwj9kupef/xxlarge8221.gif" alt="rdquo" align="MIDDLE" BORDER="0">. The general equilibrium model of growth zooms in on the research process and provides an explanation for sluggish growth with booming relative wages of the skilled. Technological progress in firms is driven by research aimed at improving the production technology (innovation) and by assimilation of ideas or principles present outside the firm (learning). A new General Purpose Technology (GPT) like the rc="/content/j8y5ty4cwj9kupef/xxlarge8220.gif" alt="ldquo" align="MIDDLE" BORDER="0">computer revolutionrc="/content/j8y5ty4cwj9kupef/xxlarge8221.gif" alt="rdquo" align="MIDDLE" BORDER="0"> generates an initial slowdown in economic growth and an increase in the skill premium.Acknowledgement I am indebted to Theo van de Klundert for suggestions and encouragement. Suggestions by Jan Boone, Bas Jacobs, Patrick Francois, Henri de Groot, Lex Meijdam, Niek Nahuis Sjak Smulders, Harald Uhlig and anonymous referees have contributed to the paper.     

Incomplete regulation, market competition and collusion

Regulators often do not regulate all firms competing in a given sector. Due to product substitutability, unregulated competitors have incentives to bribe regulated firms to have them overstate their costs and produce less, thereby softening competition. The best collusion-proof contract entails distortions both for inefficient and efficient regulated firms (distortion ‘at the top’). But a contract inducing active collusion may do better by allowing the regulator to ‘team up’ with the regulated firm to indirectly tax its competitor. The best such contract is characterized. It is such that the unregulated firm pays the regulated one to have it truthfully reveals its inefficiency. We finally compare those contracts.     

Problems and environment of small businesses in the Czech Republic

The impressive and spontaneous build-up of the private small and medium-sized enterprises (SMEs) in the Czech Republic in 1990–93 coincided with the similarly dramatic changes in the public administration and in the whole environment for decision-making. The resulting problems of SMEs in the Czech Republic seem to be common to all economies in transition. A lot of the problems are caused by the macroeconomic policy for which this sector is not the most important part of the national economy. The paper shows some conflicts between macroeconomic anti-inflationary (monetary and fiscal) policies, and interests of small businesses. The authors stress the importance of SMEs during the period of transition. Informal aspects of the functioning of small firms are discussed, especially their relation with banks and public administration. The paper offers some empirical evidence and available statistics on SMEs developments during 1990–94 focusing particularly on manufacturing.