Neural network ensemble strategies for financial decision applications
By David West, Scott A. Dellana, Jingxia Qian. Computers & Operations Research, 2005
354 citations recorded by the source corpus.
Subfields: Accounting, Artificial Intelligence, Management Science and Operations Research
View Paper: https://www.semanticscholar.org/paper/3e4dd93704c9be1d344a539e072afa54b16007ed
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Accounting
In Artificial Intelligence
In Management Science and Operations Research
Citations in the corpus
- A privacy-preserving algorithm for distributed training of neural network ensembles (2012, methodology): “Since neural network ensemble can improve the generalization ability of the learning model significantly, it has been widely used in machine learning and applied successfully to many other areas such as medical diagnosis [13, 14] and financial analysis [11, 12].”
- Using neural network ensembles for bankruptcy prediction and credit scoring (2008, background): “In West, Dellana, and Qian (2005) ‘‘multiple experts’’ (i.e. ensembles) of predictors have demonstrated the potential to reduce the generalization error of a single model from 5% to 70%.”
- A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems (2010, background): “In another type of studies, researchers compared single ANN classifier with multiple ANN classifier such as work done by [57] that compared ensemble NNs versus single NN for credit risk classification and concluded that ensemble NNs perform better than single NN.”
- Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey (2010, methodology): “Hu (2008) uses the k-fuzzy measure and applies GA to train an MLP.”
- Predicting financial distress and corporate failure: A review from the state-of-the-art definitions, modeling, sampling, and featuring approaches (2014, methodology): “Bagging and Boosting (including Ada- Boost) ensembles based on NN were widely applied in FDP researches such West et al. [126], Alfaro et al. [2], and Kim and Kang [56].”
- Artificial neural networks in business: Two decades of research (2016, methodology): “[401] focused on financial decision applications.”
- Credit Scoring, Statistical Techniques and Evaluation Criteria: A Review of the Literature (2011, background): “…al, 2006), classification problems (Ben-David & Frank, 2009; Laha, 2007; Trinkle & 2004; Glen, 2001); financial distress (Hu, 2008; Mukkamala, et al., 2008; Hu & Ansell, 2007; Van Gestel et al, 2006) and financial decisions and financial returns (Yu et al, 2009; West et al, 2005; Xia et al, 2000).”
- Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research (2015, background): “effectiveness of different classification algorithms in credit scoring (e.g., Finlay, 2011; Paleologo et al., 2010; West et al., 2005).”
- Financial Statement Fraud Detection: An Analysis of Statistical and Machine Learning Algorithms (2011, positive): “Such machine learning studies have found that classification algorithms like SVM (Fries et al. 1998; Fan and Palaniswami 2000; Shin et al. 2005), C4.5 (Phua et al. 2004), and bagging (West et al. 2005) perform relatively well.”
- Auditor Risk Assessment: Insights from the Academic Literature (2006, background): “2004), and recent work suggests that using multiple bankruptcy prediction methods together may produce the best results (West et al. 2005).”
- Credit Scoring Models Using Soft Computing Methods: A Survey (2010, background): “ANNs have been extensively used in many disciplines to model complex real-world problems.”