Prediction of financial information manipulation by using support vector machine and probabilistic neural network

Öğüt, Hulisi; Aktaş, Ramazan; Alp, Ali; Doğanay, M. Mete

doi:10.1016/j.eswa.2008.06.055

Cited by 26 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This approach is by far the most common way to develop PNN models (e.g., Modaresi and Araghinejad, 2014;Muniz et al, 2010;Öğüt et al, 2009) because it corresponds to the very basic implementation of PNN (Specht, 1989(Specht, , 1990. The smoothing parameter is equalled for each input variables (i.e., 1 = 2 = ⋯ = ); thus, the influence of each pattern on each coordinate coincides ( Fig.…”

Section: Homoscedastic Pnnmentioning

confidence: 99%

“…As with PNNs, SVMs only require the optimisation of very few parameters (Fukuda and De Baets, 2016;Huang and Wang, 2006). Previous comparisons between PNNs and SVMs typically judged SVMs as the preferable option (e.g., Modaresi and Araghinejad, 2014;Muniz et al, 2010;Öğüt et al, 2009). However, since their inception, PNNs have been the subject of scientific research to improve their performance (Ahmadlou and Adeli, 2010) and/or reduce the computational burden (Kusy and Zajdel, 2015;Miguez et al, 2010;Li and Ma, 2008;Berthold and Diamond, 1998).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Revisiting probabilistic neural networks: a comparative study with support vector machines and the microhabitat suitability for the Eastern Iberian chub (Squalius valentinus)

Muñoz‐Mas

Fukuda

Pórtoles³

et al. 2018

Ecological Informatics

View full text Add to dashboard Cite

Probabilistic Neural Networks (PNNs) and Support Vector Machines (SVMs) are flexible classification techniques suited to render trustworthy species distribution and habitat suitability models. Although several alternatives to improve PNNs' reliability and performance and/or to reduce computational costs exist, PNNs are currently not well recognised as SVMs because the SVMs were compared with standard PNNs. To rule out this idea, the microhabitat suitability for the Eastern Iberian chub (Squalius valentinus Doadrio & Carmona, 2006) was modelled with SVMs and four types of PNNs (homoscedastic, heteroscedastic, cluster and enhanced PNNs); all of them optimised with differential evolution. The fitness function and several performance criteria (correctly classified instances, true skill statistic, specificity and sensitivity) and partial dependence plots were used to assess respectively the performance and reliability of each habitat suitability model. Heteroscedastic and enhanced PNNs achieved the highest performance in every index but specificity. However, these two PNNs rendered ecologically unreliable partial dependence plots. Conversely, homoscedastic and cluster PNNs rendered ecologically reliable partial dependence plots. Thus, Eastern Iberian chub proved to be a eurytopic species, presenting the highest suitability in microhabitats with cover present, low flow velocity (approx. 0.3 m/s), intermediate depth (approx. 0.6 m) and fine gravel (64-256 mm). PNNs outperformed SVMs; thus, based on the results of the cluster PNN, which also showed high values of the performance criteria, we would advocate a combination of approaches (e.g., cluster & heteroscedastic or cluster & enhanced PNNs) to balance the trade-off between accuracy and reliability of habitat suitability models. 1 Introduction Humans have facilitated species extinctions, invasions, increased soil erosion, altered fire frequency and hydrology, and incited profound changes in primary productivity and other key biogeochemical and ecosystems processes (Ellis et al., 2010). Therefore, in the face of this global change, forecasting future ecosystem states, such as future species geographic distributions or land-use patterns, is currently a central priority in biogeographical and ecological sciences (Eberenz et al., 2016; Evans et al., 2016). As a consequence of this priority, scientists, conservationists and managers are repeatedly compelled to confront new problems requiring data analysis (LaDeau et al., 2016). Data analysis is largely classified into two broad categories: unsupervised and supervised (Olden et al., 2008). The former focus on revealing patterns and structures in data (e.g., finding groups of co-occurring species), such as the renowned Self-Organising Maps (SOM) (Kohonen, 1982) or the laureate t-Distributed Stochastic Neighbour Embedding (t-SNE) (Van Der Maaten and Hinton, 2008). Conversely, supervised approaches, such as decision trees (e.g., CART; Breiman et al., 1984) or the Generalised Additive Models (GAMs) (Hastie and Tibshirani, 1990),...

show abstract

Section: Homoscedastic Pnnmentioning

confidence: 99%

mentioning

confidence: 99%

Revisiting probabilistic neural networks: a comparative study with support vector machines and the microhabitat suitability for the Eastern Iberian chub (Squalius valentinus)

Muñoz‐Mas

Fukuda

Pórtoles³

et al. 2018

Ecological Informatics

View full text Add to dashboard Cite

show abstract

“…Ogut et al [12] used Turkish financial data to detect financial information manipulations using variables obtained from financial statements. The experiment was performed with a balanced dataset where 75 of 150 companies had committed financial statement fraud.…”

Section: Related Workmentioning

confidence: 99%

Applying Cost-Sensitive Classification for Financial Fraud Detection under High Class-Imbalance

Moepya

Akhoury

Nelwamondo

2014

2014 IEEE International Conference on Data Mining Workshop

View full text Add to dashboard Cite

In recent years, data mining techniques have been used to identify companies who issue fraudulent financial statements. However, most of the research conducted thus far use datasets that are balanced. This does not always represent reality, especially in fraud applications. In this paper, we demonstrate the effectiveness of cost-sensitive classifiers to detect financial statement fraud using South African market data. The study also shows how different levels of cost affect overall accuracy, sensitivity, specificity, recall and precision using PCA and Factor Analysis. Weighted Support Vector Machines (SVM) were shown superior to the cost-sensitive Naive Bayes (NB) and K-Nearest Neighbors classifiers.

show abstract

“…Hal ini sejalan dengan penelitian yang telah dilakukan oleh (Soto Valero, 2016) yang mendapatkan hasil penggunaan metode SVM lebih baik dari pada SLC . Begitu pula dengan penelitian (Öğüt, Aktaş, Alp, & Doğanay, 2009) yang menunjukkan bahwa SVM juga lebih baik dalam mengenali manipulasi keuangan dibandingkan dengan Neural Network (Öğüt, Aktaş, Alp, & Doğanay, 2009 …”

Section: A Hasil Perankingan Fiturunclassified

Perbandingan Simple Logistic Classifier dengan Support Vector Machine dalam Memprediksi Kemenangan Atlet

Rainarli

Romadhan

2017

JISEBI

View full text Add to dashboard Cite

Abstrak-Prediksi kemenangan atlet adalah hal yang harus dilakukan oleh pelatih ketika memutuskan pemain yang akan diturunkan dalam suatu pertandingan. Banyaknya faktor-faktor yang mempengaruhi kemenangan atlet membuat keputusan tersebut tidak mudah untuk ditentukan. Dalam penelitian ini akan dilakukan perbandingan dari penggunaan metode Simple Logistic Classifier (SLC) dengan Support Vector Machine (SVM) dalam memprediksi kemenangan atlet berdasarkan data kesehatan dan data latihan fisik. Data yang digunakan diambil dari 28 cabang olahraga perorangan. Rata-rata akurasi SLC dan SVM masingmasing diperoleh sebesar 80% dan 88%, sedangkan rata-rata kecepatan pemrosesan metode SLC dan SVM adalah 1,6 detik dan 0,2 detik. Hal ini menunjukkan bahwa penggunaan metode SVM lebih unggul daripada SLC, baik dari segi kecepatan maupun dari nilai akurasi yang dihasilkan. Selain pengujian akurasi, dilakukan pula pengujian terhadap 24 fitur yang digunakan dalam proses klasifikasi. Hasilnya diketahui bahwa pengurangan fitur melalui tahap seleksi mengakibatkan penurunan nilai akurasi. Berdasarkan hal tersebut disimpulkan bahwa semua fitur yang digunakan dalam penelitian ini adalah fitur yang berpengaruh dalam penentuan prediksi kemenangan atlet. Kata Kunci-Prediksi, Simple Logistic Classifier, Sports Data Mining, Support Vector MachineAbstract-A coach must be able to select which athlete has a good prospect of winning a game. There are a lot of aspects which influence the athlete in winning a game, so it's not easy by coach to decide it.This research would compare Simple Logistic Classifier (SLC) and Support Vector Machine (SVM) usage applied to predict winning game of athlete based on health and physical condition record. The data get from 28 sports. The accuracy of SLC and SVM are 80% and 88% meanwhile processing times of SLC and SVM method are 1.6 seconds dan 0.2 seconds.The result shows the SVM usage superior to the SLC both of speed process and the value of accuracy. There were also testing of 24 features used in the classifications process. Based on the test, features selection process can cause decreasing the accuracy value. This result concludes that all features used in this research influence the determination of a victory athletes prediction.

show abstract

Prediction of financial information manipulation by using support vector machine and probabilistic neural network

Cited by 26 publications

References 20 publications

Revisiting probabilistic neural networks: a comparative study with support vector machines and the microhabitat suitability for the Eastern Iberian chub (Squalius valentinus)

Revisiting probabilistic neural networks: a comparative study with support vector machines and the microhabitat suitability for the Eastern Iberian chub (Squalius valentinus)

Applying Cost-Sensitive Classification for Financial Fraud Detection under High Class-Imbalance

Perbandingan Simple Logistic Classifier dengan Support Vector Machine dalam Memprediksi Kemenangan Atlet

Contact Info

Product

Resources

About