Search results
1 – 3 of 3Martin Jullum, Anders Løland, Ragnar Bang Huseby, Geir Ånonsen and Johannes Lorentzen
The purpose of this paper is to develop, describe and validate a machine learning model for prioritising which financial transactions should be manually investigated for potential…
Abstract
Purpose
The purpose of this paper is to develop, describe and validate a machine learning model for prioritising which financial transactions should be manually investigated for potential money laundering. The model is applied to a large data set from Norway’s largest bank, DNB.
Design/methodology/approach
A supervised machine learning model is trained by using three types of historic data: “normal” legal transactions; those flagged as suspicious by the bank’s internal alert system; and potential money laundering cases reported to the authorities. The model is trained to predict the probability that a new transaction should be reported, using information such as background information about the sender/receiver, their earlier behaviour and their transaction history.
Findings
The paper demonstrates that the common approach of not using non-reported alerts (i.e. transactions that are investigated but not reported) in the training of the model can lead to sub-optimal results. The same applies to the use of normal (un-investigated) transactions. Our developed method outperforms the bank’s current approach in terms of a fair measure of performance.
Originality/value
This research study is one of very few published anti-money laundering (AML) models for suspicious transactions that have been applied to a realistically sized data set. The paper also presents a new performance measure specifically tailored to compare the proposed method to the bank’s existing AML system.
Details
Keywords
Erika K. Gubrium, Bettina Leibetseder, Danielle Dierckx and Peter Raeymaeckers
The purpose of this paper is to compare the impact of two social investment strategies (labour activation and governance coordination) targeted to social assistance clients within…
Abstract
Purpose
The purpose of this paper is to compare the impact of two social investment strategies (labour activation and governance coordination) targeted to social assistance clients within three different welfare-system coordination cases, with focus on social and economic inclusion.
Design/methodology/approach
The authors focus on the impact of reform at micro (individually experienced impact), meso (impact across settings) and macro (socio-structural impact) levels.
Findings
While social investment reform has given some clients new opportunities, in no study case were clients fully able to use the incentive-driven strategies. Reforms have led to a “Matthew effect”: the better resourced reap the largest benefit from new services on offer while the less resourced have their marginal socioeconomic position reinforced. Clients may internalise their relative activation success. Intimate connections between macro- and micro-impacts may have heightened the sense of social and economic exclusion, stigma and shame experienced by those who are most vulnerable.
Social implications
Social investment reform (labour activation) may not be a model that reduces social and economic exclusion and it may, instead, reify socioeconomic marginalisation, enhancing sense of stigma and shame and reducing self-efficacy.
Originality/value
Scholars have assessed social investment according to its economic performance, but there has been a lack of research considering impact of reform on socioeconomic inclusion.
Details
Keywords
This paper aims to offer an analysis of the conflicting values behind Norway's much celebrated inclusive working life (IWL) programme, which aims to reduce sickness absenteeism…
Abstract
Purpose
This paper aims to offer an analysis of the conflicting values behind Norway's much celebrated inclusive working life (IWL) programme, which aims to reduce sickness absenteeism, to increase the average age of retirement, and to hire functionally challenged persons. This article, moreover, presents sorely needed qualitative data from a preliminary study on IWL that shows how state‐owned enterprises have struggled to cope with the conflicting goals.
Design/methodology/approach
This is a qualitative study based on interviews with regional managers and representatives of the unions who had to adapt to IWL, and the results suggest possible explanations behind the disappointing numbers found by other quantitative studies on IWL.
Findings
Because of the decision to implement IWL, regional managers are caught in the middle of two different ideologies, namely, neo‐liberalism or new public management (NPM) and the welfare‐state ideology, and they find themselves making choices according to the former. This study on state enterprises at the local level has found that managers and union representatives appeared to support the intentions behind the programme, but they clearly prioritized productivity and efficiency over inclusiveness.
Research limitations/implications
As the results are from a preliminary qualitative study of IWL that only included state enterprises, there is a need for further research that also includes the private enterprises.
Practical implications
This study finds that IWL is ineffective because it cannot harmonize the NPM and the welfare‐state ideologies.
Originality/value
This article helps to remedy the lack of qualitative documentation on the progress of IWL. These results also question the prevailing optimism over the potential of IWL by pointing to the ideological tensions between welfare and efficiency.
Details