Search results

1 – 10 of 106
To view the access options for this content please click here
Article
Publication date: 11 February 2021

Krithiga R. and Ilavarasan E.

The purpose of this paper is to enhance the performance of spammer identification problem in online social networks. Hyperparameter tuning has been performed by…

Abstract

Purpose

The purpose of this paper is to enhance the performance of spammer identification problem in online social networks. Hyperparameter tuning has been performed by researchers in the past to enhance the performance of classifiers. The AdaBoost algorithm belongs to a class of ensemble classifiers and is widely applied in binary classification problems. A single algorithm may not yield accurate results. However, an ensemble of classifiers built from multiple models has been successfully applied to solve many classification tasks. The search space to find an optimal set of parametric values is vast and so enumerating all possible combinations is not feasible. Hence, a hybrid modified whale optimization algorithm for spam profile detection (MWOA-SPD) model is proposed to find optimal values for these parameters.

Design/methodology/approach

In this work, the hyperparameters of AdaBoost are fine-tuned to find its application to identify spammers in social networks. AdaBoost algorithm linearly combines several weak classifiers to produce a stronger one. The proposed MWOA-SPD model hybridizes the whale optimization algorithm and salp swarm algorithm.

Findings

The technique is applied to a manually constructed Twitter data set. It is compared with the existing optimization and hyperparameter tuning methods. The results indicate that the proposed method outperforms the existing techniques in terms of accuracy and computational efficiency.

Originality/value

The proposed method reduces the server load by excluding complex features retaining only the lightweight features. It aids in identifying the spammers at an earlier stage thereby offering users a propitious environment.

Details

International Journal of Pervasive Computing and Communications, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1742-7371

Keywords

To view the access options for this content please click here
Article
Publication date: 7 August 2017

Eun-Suk Yang, Jong Dae Kim, Chan-Young Park, Hye-Jeong Song and Yu-Seop Kim

In this paper, the problem of a nonlinear model – specifically the hidden unit conditional random fields (HUCRFs) model, which has binary stochastic hidden units between…

Abstract

Purpose

In this paper, the problem of a nonlinear model – specifically the hidden unit conditional random fields (HUCRFs) model, which has binary stochastic hidden units between the data and the labels – exhibiting unstable performance depending on the hyperparameter under consideration.

Design/methodology/approach

There are three main optimization search methods for hyperparameter tuning: manual search, grid search and random search. This study shows that HUCRFs’ unstable performance depends on the hyperparameter values used and its performance is based on tuning that draws on grid and random searches. All experiments conducted used the n-gram features – specifically, unigram, bigram, and trigram.

Findings

Naturally, selecting a list of hyperparameter values based on a researchers’ experience to find a set in which the best performance is exhibited is better than finding it from a probability distribution. Realistically, however, it is impossible to calculate using the parameters in all combinations. The present research indicates that the random search method has a better performance compared with the grid search method while requiring shorter computation time and a reduced cost.

Originality/value

In this paper, the issues affecting the performance of HUCRF, a nonlinear model with performance that varies depending on the hyperparameters, but performs better than CRF, has been examined.

Details

Engineering Computations, vol. 34 no. 6
Type: Research Article
ISSN: 0264-4401

Keywords

To view the access options for this content please click here
Article
Publication date: 26 May 2020

Murat Özemre and Ozgur Kabadurmus

The purpose of this paper is to present a novel framework for strategic decision making using Big Data Analytics (BDA) methodology.

Abstract

Purpose

The purpose of this paper is to present a novel framework for strategic decision making using Big Data Analytics (BDA) methodology.

Design/methodology/approach

In this study, two different machine learning algorithms, Random Forest (RF) and Artificial Neural Networks (ANN) are employed to forecast export volumes using an extensive amount of open trade data. The forecasted values are included in the Boston Consulting Group (BCG) Matrix to conduct strategic market analysis.

Findings

The proposed methodology is validated using a hypothetical case study of a Chinese company exporting refrigerators and freezers. The results show that the proposed methodology makes accurate trade forecasts and helps to conduct strategic market analysis effectively. Also, the RF performs better than the ANN in terms of forecast accuracy.

Research limitations/implications

This study presents only one case study to test the proposed methodology. In future studies, the validity of the proposed method can be further generalized in different product groups and countries.

Practical implications

In today’s highly competitive business environment, an effective strategic market analysis requires importers or exporters to make better predictions and strategic decisions. Using the proposed BDA based methodology, companies can effectively identify new business opportunities and adjust their strategic decisions accordingly.

Originality/value

This is the first study to present a holistic methodology for strategic market analysis using BDA. The proposed methodology accurately forecasts international trade volumes and facilitates the strategic decision-making process by providing future insights into global markets.

Details

Journal of Enterprise Information Management, vol. 33 no. 6
Type: Research Article
ISSN: 1741-0398

Keywords

To view the access options for this content please click here
Article
Publication date: 19 February 2021

Zulkifli Halim, Shuhaida Mohamed Shuhidan and Zuraidah Mohd Sanusi

In the previous study of financial distress prediction, deep learning techniques performed better than traditional techniques over time-series data. This study…

Abstract

Purpose

In the previous study of financial distress prediction, deep learning techniques performed better than traditional techniques over time-series data. This study investigates the performance of deep learning models: recurrent neural network, long short-term memory and gated recurrent unit for the financial distress prediction among the Malaysian public listed corporation over the time-series data. This study also compares the performance of logistic regression, support vector machine, neural network, decision tree and the deep learning models on single-year data.

Design/methodology/approach

The data used are the financial data of public listed companies that been classified as PN17 status (distress) and non-PN17 (not distress) in Malaysia. This study was conducted using machine learning library of Python programming language.

Findings

The findings indicate that all deep learning models used for this study achieved 90% accuracy and above with long short-term memory (LSTM) and gated recurrent unit (GRU) getting 93% accuracy. In addition, deep learning models consistently have good performance compared to the other models over single-year data. The results show LSTM and GRU getting 90% and recurrent neural network (RNN) 88% accuracy. The results also show that LSTM and GRU get better precision and recall compared to RNN. The findings of this study show that the deep learning approach will lead to better performance in financial distress prediction studies. To be added, time-series data should be highlighted in any financial distress prediction studies since it has a big impact on credit risk assessment.

Research limitations/implications

The first limitation of this study is the hyperparameter tuning only applied for deep learning models. Secondly, the time-series data are only used for deep learning models since the other models optimally fit on single-year data.

Practical implications

This study proposes recommendations that deep learning is a new approach that will lead to better performance in financial distress prediction studies. Besides that, time-series data should be highlighted in any financial distress prediction studies since the data have a big impact on the assessment of credit risk.

Originality/value

To the best of authors' knowledge, this article is the first study that uses the gated recurrent unit in financial distress prediction studies based on time-series data for Malaysian public listed companies. The findings of this study can help financial institutions/investors to find a better and accurate approach for credit risk assessment.

Details

Business Process Management Journal, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1463-7154

Keywords

To view the access options for this content please click here
Article
Publication date: 25 July 2019

Xia Li, Ruibin Bai, Peer-Olaf Siebers and Christian Wagner

Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of…

Abstract

Purpose

Many transport and logistics companies nowadays use raw vehicle GPS data for travel time prediction. However, they face difficult challenges in terms of the costs of information storage, as well as the quality of the prediction. This paper aims to systematically investigate various meta-data (features) that require significantly less storage space but provide sufficient information for high-quality travel time predictions.

Design/methodology/approach

The paper systematically studied the combinatorial effects of features and different model fitting strategies with two popular decision tree ensemble methods for travel time prediction, namely, random forests and gradient boosting regression trees. First, the investigation was conducted using pseudo travel time data that were generated using a pseudo travel time sampling algorithm, which allows generating travel time data using different noise processes so that the prediction performance under different travel conditions and noise characteristics can be studied systematically. The results and findings were then further compared and evaluated through a real-life case.

Findings

The paper provides empirical insights and guidelines about how raw GPS data can be reduced into a small-sized feature vector for the purposes of vehicle travel time prediction. It suggests that, add travel time observations from the previous departure time intervals are beneficial to the prediction, particularly when there is no other types of real-time information (e.g. traffic flow, speed) are available. It was also found that modular model fitting does not improve the quality of the prediction in all experimental settings used in this paper.

Research limitations/implications

The findings are primarily based on empirical studies on limited real-life data instances, and the results may lack generalisabilities. Therefore, the researchers are encouraged to test them further in more real-life data instances.

Practical implications

The paper includes implications and guidelines for the development of efficient GPS data storage and high-quality travel time prediction under different types of travel conditions.

Originality/value

This paper systematically studies the combinatorial feature effects for tree-ensemble-based travel time prediction approaches.

Details

VINE Journal of Information and Knowledge Management Systems, vol. 49 no. 3
Type: Research Article
ISSN: 2059-5891

Keywords

To view the access options for this content please click here
Article
Publication date: 8 February 2020

Ying Cui, Fu Chen and Ali Shiri

This study aims to investigate the feasibility of developing general predictive models for using the learning management system (LMS) data to predict student performances…

Abstract

Purpose

This study aims to investigate the feasibility of developing general predictive models for using the learning management system (LMS) data to predict student performances in various courses. The authors focused on examining three practical but important questions: are there a common set of student activity variables that predict student performance in different courses? Which machine-learning classifiers tend to perform consistently well across different courses? Can the authors develop a general model for use in multiple courses to predict student performance based on LMS data?

Design/methodology/approach

Three mandatory undergraduate courses with large class sizes were selected from three different faculties at a large Western Canadian University, namely, faculties of science, engineering and education. Course-specific models for these three courses were built and compared using data from two semesters, one for model building and the other for generalizability testing.

Findings

The investigation has led the authors to conclude that it is not desirable to develop a general model in predicting course failure across variable courses. However, for the science course, the predictive model, which was built on data from one semester, was able to identify about 70% of students who failed the course and 70% of students who passed the course in another semester with only LMS data extracted from the first four weeks.

Originality/value

The results of this study are promising as they show the usability of LMS for early prediction of student course failure, which has the potential to provide students with timely feedback and support in higher education institutions.

Details

Information and Learning Sciences, vol. 121 no. 3/4
Type: Research Article
ISSN: 2398-5348

Keywords

To view the access options for this content please click here

Abstract

Details

Machine Learning and Artificial Intelligence in Marketing and Sales
Type: Book
ISBN: 978-1-80043-881-1

To view the access options for this content please click here

Abstract

Details

Essays in Honor of Cheng Hsiao
Type: Book
ISBN: 978-1-78973-958-9

To view the access options for this content please click here
Article
Publication date: 28 June 2021

Meseret Getnet Meharie, Wubshet Jekale Mengesha, Zachary Abiero Gariy and Raphael N.N. Mutuku

The purpose of this study to apply stacking ensemble machine learning algorithm for predicting the cost of highway construction projects.

Abstract

Purpose

The purpose of this study to apply stacking ensemble machine learning algorithm for predicting the cost of highway construction projects.

Design/methodology/approach

The proposed stacking ensemble model was developed by combining three distinct base predictive models automatically and optimally: linear regression, support vector machine and artificial neural network models using gradient boosting algorithm as meta-regressor.

Findings

The findings reveal that the proposed model predicted the final project cost with a very small prediction error value. This implies that the difference between predicted and actual cost was quite small. A comparison of the results of the models revealed that in all performance metrics, the stacking ensemble model outperforms the sole ones. The stacking ensemble cost model produces 86.8, 87.8 and 5.6 percent more accurate results than linear regression, vector machine support, and neural network models, respectively, based on the root mean square error values.

Research limitations/implications

The study shows how stacking ensemble machine learning algorithm applies to predict the cost of construction projects. The estimators or practitioners can use the new model as an effectual and reliable tool for predicting the cost of Ethiopian highway construction projects at the preliminary stage.

Originality/value

The study provides insight into the machine learning algorithm application in forecasting the cost of future highway construction projects in Ethiopia.

Details

Engineering, Construction and Architectural Management, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 0969-9988

Keywords

To view the access options for this content please click here
Article
Publication date: 3 April 2020

Abdelhalim Saadi and Hacene Belhadef

The purpose of this paper is to present a system based on deep neural networks to extract particular entities from natural language text, knowing that a massive amount of…

Abstract

Purpose

The purpose of this paper is to present a system based on deep neural networks to extract particular entities from natural language text, knowing that a massive amount of textual information is electronically available at present. Notably, a large amount of electronic text data indicates great difficulty in finding or extracting relevant information from them.

Design/methodology/approach

This study presents an original system to extract Arabic-named entities by combining a deep neural network-based part-of-speech tagger and a neural network-based named entity extractor. Firstly, the system extracts the grammatical classes of the words with high precision depending on the context of the word. This module plays the role of the disambiguation process. Then, a second module is used to extract the named entities.

Findings

Using deep neural networks in natural language processing, requires tuning many hyperparameters, which is a time-consuming process. To deal with this problem, applying statistical methods like the Taguchi method is much requested. In this study, the system is successfully applied to the Arabic-named entities recognition, where accuracy of 96.81 per cent was reported, which is better than the state-of-the-art results.

Research limitations/implications

The system is designed and trained for the Arabic language, but the architecture can be used for other languages.

Practical implications

Information extraction systems are developed for different applications, such as analysing newspaper articles and databases for commercial, political and social objectives. Information extraction systems also can be built over an information retrieval (IR) system. The IR system eliminates irrelevant documents and paragraphs.

Originality/value

The proposed system can be regarded as the first attempt to use double deep neural networks to increase the accuracy. It also can be built over an IR system. The IR system eliminates irrelevant documents and paragraphs. This process reduces the mass number of documents from which the authors wish to extract the relevant information using an information extraction system.

Details

Smart and Sustainable Built Environment, vol. 9 no. 4
Type: Research Article
ISSN: 2046-6099

Keywords

1 – 10 of 106