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.     

Testing the Empirical Relevance of the ‘Saving for a Rainy Day’ Hypothesis in US Metro Areas

The joint implication of the consumption Euler equation and cointegration between income and consumption is that savings predict future income declines, the ‘saving for a rainy day’ hypothesis. The empirical relevance of this hypothesis plays a key role in discussions of fiscal policy multipliers, and it holds under the null that the permanent income hypothesis is true. We find little support for this hypothesis using time series data for the 100 largest US Metropolitan Statistical Areas for the period 1980q1–2015q4. Our approach is to test for cointegration and weak exogeneity between income and consumption, and by exploring the direction of Granger causality between the two time series. We find that income more often predicts consumption and saving than the converse. We also give evidence that house price changes played a role in US income and consumption dynamics, before, during and after the Great Recession.     

Capability and need: A framework for understanding why states create sovereign wealth funds

Over the past half‐century, roughly one‐quarter of states in the international system have created sovereign wealth funds (SWFs). As a case of sovereign states investing public wealth mostly in private markets across borders, it is not altogether clear why SWFs have proliferated to this extent. What explains their spread in recent decades? In this paper, I build on a multidisciplinary literature that conceives of SWFs as a type of insurance against external risk and argue that middle economic powers that are highly exposed in global trade and capital markets are the states most likely to establish these institutions. Such states possess both the capability to create an SWF of a size sufficient to insure against risk and the need for the insurance function of a SWF by virtue of their relatively vulnerable position in the global economy. To evaluate my argument, I rely on a data set consisting of all states in the international system from 1950 to 2012 including the 48 SWFs created during that period. I find that middle economic powers with high degrees of trade and capital openness are the states most likely to create SWFs.     

Revisiting the expatriate failure concept: A qualitative study of Scandinavian expatriates in Hong Kong

This article advances the understanding of expatriate failure, which remains a contested social phenomenon in international work life as well as scholarly research. The study challenges the definition of expatriate failure and its inherent biases, i.e., the epistemological primacy of the firm level and the failure/success binary. We argue that this qualitative study of 51 Scandinavian expatriates in Hong Kong can contribute to advancing theory on the expatriate failure concept by asking individual expatriates what constitutes failure to them. By applying social constructionist and social anthropological ideas to the expatriate failure concept debate, we develop the internationality thesis which demonstrates a discrepancy between the expatriates’ perceptions of successful international assignments and the actual nature of their lived lives; many expatriates desire to enrich their lives through experiencing an international/intercultural and adventurous lifestyle, but, in fact, living lives with limited intercultural exposure and interaction. We conclude by proposing a reconceptualisation of expatriate failure in terms of offering both a new definition and approach to researching expatriate failure in which time/duration, context, and geographical location need to be taken into account. We believe the new approach can overcome some of the empirical unsoundness of mainstream definitions.     

Using the Pack‐and‐a‐Half Rule to Eliminate Backroom Inventories in Retail Operations

In the retail industry, backroom inventories are typically associated with higher labor costs and greater operational complexity. Thus, retailers look for ways to eliminate backroom inventories. A heuristic used for this purpose is the pack‐and‐a‐half rule which suggests that the shelf space allocated for a product should be at least 50% larger than the case pack quantity in which the product is delivered. Despite its popularity among retailers, the pack‐and‐a‐half rule has been ignored in the academic literature. We introduce the pack‐and‐a‐half rule, assess its impact on a retailer's profits, identify cost, demand, and product characteristics driving this impact, and propose a modification. Based on an analysis of data obtained from a retailer on 1,986 SKUs in 20 categories, we find that the pack‐and‐a‐half rule decreases a retailer's profits, on average, by 10% when applied uniformly across all SKUs. Further, this decrease is significantly affected by product depth, product width, demand elasticity, case pack quantity, and inventory carrying cost. Finally, we develop a set of modifications based on these variables where the pack‐and‐a‐half rule is applied selectively and in a stepwise fashion. These modifications limit the decrease in a retailer's profits to a range between 6% and 7%.     

Machine Learning and Expert Judgement: Analyzing Emerging Topics in Accounting and Finance Research in the Asia–Pacific

In this paper, we focus on the question to what extent machine learning (ML) tools can be used to support systematic literature reviews. We apply a ML approach for topic detection to analyze emerging topics in the literature—our context is accounting and finance research in the Asia–Pacific region. To evaluate the robustness of the approach, we compare findings from the automated ML approach with the results from a manual analysis of the literature. The automated approach uses a keyword algorithm detection mechanism whereby the manual analysis uses common techniques for qualitative data analysis, that is, triangulation between researchers (expert judgement). From our paper, we conclude that both methods have strengths and weaknesses. The automated analysis works well for large corpora of text and provides a very standardized and non-biased way of analyzing the literature. However, the human researcher is potentially better equipped to evaluate current issues and future trends in the literature. Overall, the best results might be achieved when a variety of tools are used together.     

The Impact of Employment on Parental Coresidence

We examine the extent to which parents use housing and shared living arrangements as a form of risk‐sharing for their adult children, using detailed data on children and parents in the Health and Retirement Study for 1998–2012. On average, a young man moving from full‐time to nonemployment raises the likelihood of coresiding with a parent by 1.5 percentage points; moving from full‐time employment to being part‐time employed raises the likelihood of coresiding with a parent by 2 percentage points. The implied elasticity of parental coresidence with respect to the son's income is ‐1.1; for daughters, the elasticity is ‐0.5.     

Sparse Signals in the Cross‐Section of Returns

This paper applies the Least Absolute Shrinkage and Selection Operator (LASSO) to make rolling one‐minute‐ahead return forecasts using the entire cross‐section of lagged returns as candidate predictors. The LASSO increases both out‐of‐sample fit and forecast‐implied Sharpe ratios. This out‐of‐sample success comes from identifying predictors that are unexpected, short‐lived, and sparse. Although the LASSO uses a statistical rule rather than economic intuition to identify predictors, the predictors it identifies are nevertheless associated with economically meaningful events: the LASSO tends to identify as predictors stocks with news about fundamentals.     

EDITORIAL: TAX REFORM AND SIMPLIFICATION

Major tax reform to simplify the UK tax system is possible. Merging income taxes, social security taxes and corporation tax into only a single flat-rate of tax on all incomes would be a radical start. Avoiding taxes on income and expenditure which are 'too high' requires major reductions in government spending, mainly on the welfare state. Given the political will, over a period of years we really can hugely improve the UK tax system.