Search results

1 – 10 of 31
Article
Publication date: 8 January 2020

Sonali Shankar, P. Vigneswara Ilavarasan, Sushil Punia and Surya Prakash Singh

Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This…

Abstract

Purpose

Better forecasting always leads to better management and planning of the operations. The container throughput data are complex and often have multiple seasonality. This makes it difficult to forecast accurately. The purpose of this paper is to forecast container throughput using deep learning methods and benchmark its performance over other traditional time-series methods.

Design/methodology/approach

In this study, long short-term memory (LSTM) networks are implemented to forecast container throughput. The container throughput data of the Port of Singapore are used for empirical analysis. The forecasting performance of the LSTM model is compared with seven different time-series forecasting methods, namely, autoregressive integrated moving average (ARIMA), simple exponential smoothing, Holt–Winter’s, error-trend-seasonality, trigonometric regressors (TBATS), neural network (NN) and ARIMA + NN. The relative error matrix is used to analyze the performance of the different models with respect to bias, accuracy and uncertainty.

Findings

The results showed that LSTM outperformed all other benchmark methods. From a statistical perspective, the Diebold–Mariano test is also conducted to further substantiate better forecasting performance of LSTM over other counterpart methods.

Originality/value

The proposed study is a contribution to the literature on the container throughput forecasting and adds value to the supply chain theory of forecasting. Second, this study explained the architecture of the deep-learning-based LSTM method and discussed in detail the steps to implement it.

Details

Industrial Management & Data Systems, vol. 120 no. 3
Type: Research Article
ISSN: 0263-5577

Keywords

Content available

Abstract

Details

Journal of Enterprise Information Management, vol. 30 no. 1
Type: Research Article
ISSN: 1741-0398

Article
Publication date: 20 October 2022

Vishal Gupta, Shweta Mittal, P. Vigneswara Ilavarasan and Pawan Budhwar

Building on the arguments of expectancy theory and social exchange theory, the present study provides insights into the process by which pay-for-performance (PFP) impacts…

Abstract

Purpose

Building on the arguments of expectancy theory and social exchange theory, the present study provides insights into the process by which pay-for-performance (PFP) impacts employee job performance.

Design/methodology/approach

Based on a sample size of 226 employees working in a technology company in India, the study examines the relationships between PFP, procedural justice, organizational citizenship behavior (OCB) and employee job performance. Data on perceptions of PFP and procedural justice were collected from the employees, data on OCB were collected from the supervisors and the data on employee job performance were collected from organizational appraisal records.

Findings

The study found support for the positive relationship between PFP and job performance and for the sequential mediation of the relationship between PFP and job performance via procedural justice and OCB. Further, procedural justice was found to mediate the relationship between PFP and OCB.

Research limitations/implications

The study was cross-sectional, so inferences about causality are limited.

Practical implications

The study tests the relationship between PFP and employee job performance in the Indian work context. The study shows that the existence of PFP is positively related to procedural justice which, in turn, is positively related to OCB. The study found support for the sequential mediation of PFP-job performance relationship via procedural justice and OCB.

Originality/value

The study provides an insight into the underlying process through which PFP is related to employee job performance. To the best of our knowledge, such a study is the first of its kind undertaken in an organizational context.

Details

Personnel Review, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 0048-3486

Keywords

Article
Publication date: 22 June 2021

Sonali Shankar, Sushil Punia and P. Vigneswara Ilavarasan

Container throughput forecasting plays a pivotal role in strategic, tactical and operational level decision-making. The determination and analysis of the influencing…

Abstract

Purpose

Container throughput forecasting plays a pivotal role in strategic, tactical and operational level decision-making. The determination and analysis of the influencing factors of container throughput are observed to enhance the predicting accuracy. Therefore, for effective port planning and management, this study employs a deep learning-based method to forecast the container throughput while considering the influence of economic, environmental and social factors on throughput forecasting.

Design/methodology/approach

A novel multivariate container throughput forecasting method is proposed using long short-term memory network (LSTM). The external factors influencing container throughput, delineated using triple bottom line, are considered as an input to the forecasting method. The principal component analysis (PCA) is employed to reduce the redundancy of the input variables. The container throughput data of the Port of Los Angeles (PLA) is considered for empirical analysis. The forecasting accuracy of the proposed method is measured via an error matrix. The accuracy of the results is further substantiated by the Diebold-Mariano statistical test.

Findings

The result of the proposed method is benchmarked with vector autoregression (VAR), autoregressive integrated moving average (ARIMAX) and LSTM. It is observed that the proposed method outperforms other counterpart methods. Though PCA was not an integral part of the forecasting process, it facilitated the prediction by means of “less data, more accuracy.”

Originality/value

A novel deep learning-based forecasting method is proposed to predict container throughput using a hybridized autoregressive integrated moving average with external factors model and long short-term memory network (ARIMAX-LSTM).

Details

Industrial Management & Data Systems, vol. 121 no. 10
Type: Research Article
ISSN: 0263-5577

Keywords

Article
Publication date: 22 March 2021

Nimish Joseph, Arpan Kumar Kar and P. Vigneswara Ilavarasan

Social media platforms play a key role in information propagation and there is a need to study the same. This study aims to explore the impact of the number of close…

Abstract

Purpose

Social media platforms play a key role in information propagation and there is a need to study the same. This study aims to explore the impact of the number of close communities (represented by cliques), the size of these close communities and its impact on information virality.

Design/methodology/approach

This study identified 6,786 users from over 11 million tweets for analysis using sentiment mining and network science methods. Inferential analysis has also been established by introducing multiple regression analysis and path analysis.

Findings

Sentiments of content did not have a significant impact on the information virality. However, there exists a stagewise development relationship between communities of close friends, user reputation and information propagation through virality.

Research limitations/implications

This paper contributes to the theory by introducing a stagewise progression model for influencers to manage and develop their social networks.

Originality/value

There is a gap in the existing literature on the role of the number and size of cliques on information propagation and virality. This study attempts to address this gap.

Details

Information Discovery and Delivery, vol. 49 no. 2
Type: Research Article
ISSN: 2398-6247

Keywords

Article
Publication date: 8 November 2019

Pulkit Tiwari, P. Vigneswara Ilavarasan and Sushil Punia

The purpose of this paper is to provide a systematic literature review on the technological aspects of smart cities and to give insights about current trends, sources of…

Abstract

Purpose

The purpose of this paper is to provide a systematic literature review on the technological aspects of smart cities and to give insights about current trends, sources of research, contributing authors and countries. It is required to understand technical concepts like information technology, big data analytics, Internet of Things and blockchain needed to implement smart city models successfully.

Design/methodology/approach

The data were collected from the Scopus database, and analysis techniques like bibliometric analysis, network analysis and content analysis were used to obtain research trends, publications growth, top contributing authors and nations in the domain of smart cities. Also, these analytical techniques identified various fields within the literature on smart cities and supported to design a conceptual framework for Industry 4.0 adoption in a smart city.

Findings

The bibliometric analysis shows that research publications have increased significantly over the last couple of years. It has found that developing countries like China is leading the research on smart cities. The network analytics and article classification identified six domains within the literature on smart cities. A conceptual framework for the smart city has proposed for the successful implementation of Industry 4.0 technologies.

Originality/value

This paper explores the role of Industry 4.0 technologies in smart cities. The bibliometric data on publications from the year 2013 to 2018 were used and investigated by using advanced analytical techniques. The paper reviewS key technical concepts for the successful execution of a smart city model. It also gives an idea about various technical considerations required for the implementation of the smart city model through a conceptual framework.

Details

Benchmarking: An International Journal, vol. 28 no. 5
Type: Research Article
ISSN: 1463-5771

Keywords

Article
Publication date: 5 February 2020

Harjit Singh, Purva Grover, Arpan Kumar Kar and P. Vigneswara Ilavarasan

The purpose of this paper is to summarize the literature of electronic government frameworks and models to identify various constructs and their relationship to measure…

1032

Abstract

Purpose

The purpose of this paper is to summarize the literature of electronic government frameworks and models to identify various constructs and their relationship to measure the performance of e-government projects.

Design/methodology/approach

In total, 77 publications were identified from Scopus database after using exclusion and inclusion criteria. A total of 136 constructs were mapped across five categories. Further using network science, communities of usage of these constructs across different studies were identified.

Findings

Dominant constructs used across studies were ease of use, usefulness, user satisfaction, infrastructure, website maturity, security, user trust, transparency, empowerment, operational efficiency, service quality and information quality. This review offers directions for future research in terms of potential for constructs, which have been explored lesser in the existing literature.

Research limitations/implications

The study provides direction for the usage of theoretical lenses, constructs and association among usage for the evaluation of e-government projects, which have been used less in existing literature, and thus, has higher needs for greater exploration. Search scope is limited to Scopus database, which is one of the largest citation database.

Practical implications

It gives information to the policymakers about the importance of the dominant constructs such as user satisfaction, usefulness, ease of use, efficiency and quality, which have been used across the spectrum of studies of e-government performance assessment frameworks and models. Practitioners need to accommodate the relevance of these factors while designing processes and key performance indicators.

Originality/value

This study analyzes the e-government assessment frameworks and gives direction to theory building for future studies.

Details

Transforming Government: People, Process and Policy, vol. 14 no. 1
Type: Research Article
ISSN: 1750-6166

Keywords

Article
Publication date: 12 February 2021

Pooja Sarin, Arpan Kumar Kar and Vigneswara P. Ilavarasan

The Web 3.0 has been hugely enabled by smartphones and new generation mobile applications. With the growing adoption of smartphones, the use of mobile applications has…

Abstract

Purpose

The Web 3.0 has been hugely enabled by smartphones and new generation mobile applications. With the growing adoption of smartphones, the use of mobile applications has grown exponentially and so has the development of mobile applications. This study is an attempt to understand the issues and challenges faced in the mobile applications domain using discussions made on Twitter based on mining of user generated content.

Design/methodology/approach

The study uses 89,908 unique tweets to understand the nature of the discussions. These tweets are analyzed using descriptive, content and network analysis. Further using transaction cost economics, the findings are reviewed to develop practice insights about the ecosystem.

Findings

Findings indicate that the discussions are mostly skewed toward a positive polarity and positive user experiences. The tweeters are predominantly application developers who are interacting more with marketers and less with individual users.

Research limitations/implications

Most of these applications are for individual use (B2C) and not for enterprise usage. There are very few individual users who contribute to these discussions. The predominant users are application reviewers or bloggers of review websites who use the recently developed applications and discuss their thoughts on the same.

Practical implications

The results may be useful in varied domains which are planning to expand their reach to a larger audience using mobile applications and for marketers who primarily focus on promotional content.

Social implications

The domain of mobile applications on social media is still restricted to promotions and digital marketing and may solely be used for the purpose of link building by application developers. As such, the discussions could provide inputs towards mobile phone manufacturers and ecosystem providers on what are the real issues these communities are facing while developing these applications.

Originality/value

The study uses mixed research methodology for mining experiences in the domain of mobile application developers using social media analytics and transaction cost economics. The discussion on the findings provides inputs for policy-making and possible intervention areas.

Details

Journal of Advances in Management Research, vol. 18 no. 4
Type: Research Article
ISSN: 0972-7981

Keywords

Article
Publication date: 1 June 2004

P. Vigneswara Ilavarasan

Despite extensive investigation of the Indian software industry, knowledge about small software firms is inadequate. This knowledge is important as many developing…

Abstract

Despite extensive investigation of the Indian software industry, knowledge about small software firms is inadequate. This knowledge is important as many developing countries are contemplating the software industry as a means of national growth along the lines that India has taken. This paper provides a descriptive analysis of small software firms in India. It shows that small software firms that are located in software clusters; quality certified; low product oriented; and slightly larger tend to be more productive than others. Small software firms are defined as firms that have fewer software employees than the national median size. The paper used firm level data available in the Indian IT Software and Services Directory 2003, whose members contribute 95% of the industry revenue.

Details

Journal of Systems and Information Technology, vol. 8 no. 1/2
Type: Research Article
ISSN: 1328-7265

Keywords

Content available

Abstract

Details

On the Horizon, vol. 14 no. 3
Type: Research Article
ISSN: 1074-8121

Keywords

1 – 10 of 31