Search results

1 – 2 of 2
Article
Publication date: 11 July 2023

Kusum Lata and Naval Garg

This study aims to develop a model to predict non-violent work behaviour (NVWB) among employees using machine learning techniques.

Abstract

Purpose

This study aims to develop a model to predict non-violent work behaviour (NVWB) among employees using machine learning techniques.

Design/methodology/approach

Four machine learning techniques (Naïve Bayes, decision tree, logistic regression and ensemble learning) were used to develop a prediction model for NVWB of employees. Also, 10-fold cross-validation method was used to validate the NVWB prediction models. The confusion matrix is used to derive various performance matrices to express the predictive capability of NVWB models quantitatively.

Findings

The model developed using random forest technique was identified as best NVWB prediction model, as it resulted in highest true positive rate and true negative rate, thereby resulting in the highest geometric mean, balance and area under receiver operator characteristics curve.

Originality/value

To the best of the authors’ knowledge, this is one of the pioneer studies that used machine learning techniques to develop a predictive model of NVBW.

Details

International Journal of Conflict Management, vol. 34 no. 5
Type: Research Article
ISSN: 1044-4068

Keywords

Article
Publication date: 15 May 2023

Asanga Abeyagoonasekera

This paper aims to examine the present Sri Lankan political-economic crisis and its connection to corruption. The paper will discuss the autocratic rule, elite domination of state…

Abstract

Purpose

This paper aims to examine the present Sri Lankan political-economic crisis and its connection to corruption. The paper will discuss the autocratic rule, elite domination of state extractive systems, which have been moulded and configured by Sri Lanka’s political environment over decades. Elite capture has become a significant factor. Sri Lanka’s authoritarian model exercised by Gotabaya Rajapaksa reduced competitive mode and shifted towards a monopolistic corruption structure, centralising on the first family and military rule where powerful elites supported the model. The paper attempts to find the connection between dysfunctional political model and economic crimes committed through several case studies.

Design/methodology/approach

The paper discusses five case studies using qualitative analysis using secondary data. The insider trading case study is discussed with quantitative data. Several political and social analyses were carried out with primary data captured from field research by the author.

Findings

Sri Lankan economic crisis was triggered because of high-level corruption. The autocratic model introduced by the political authority failed to fight corruption. Transnational mechanisms will fail if there is no credibility and commitment in their own respective nations such as in the USA. External factors such as China in Sri Lanka did have an impact for elite capture.

Research limitations/implications

This study is limited only to five case studies. Transnational mechanism and recommendations require a lengthy study. Only one external factor was assessed because of its significance; there could be other external factors for elite capture.

Practical implications

This study has limited access to capture primary data because of sensitivity during a heavy autocratic regime. Because of state and self-censorship, secondary data had to be tested.

Social implications

Economic crisis in Sri Lanka is an example to many developing nations fighting corruption. The autocratic family rule supported by external forces crippled the state anti-corruption processes. Economic crime is a key driver for poverty and economic crisis.

Originality/value

This is a unique paper that examines Sri Lanka’s present economic crisis and its political model and economic crime. The paper will discuss transnational mechanisms for anti-corruption and attempt to apply to the Sri Lankan crisis.

Access

Year

Last 12 months (2)

Content type

1 – 2 of 2