A Comparison of Discriminant Analysis versus Artificial Neural Networks

By Youngohc Yoon, George Swales, T. Margavio. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Chih-Feng Liu
2. Chi-Yuan Yeh
3. Shie-Jue Lee
4. Paul Yoo
5. Y. Topcu
6. Tony Jan
7. B. Moon
8. Maria H. Kim

Citations in the corpus

• Neural networks for classification: a survey (2000, methodology): “Neural networks have also been compared with decision trees [28], [36], [66], [104], [155], discriminant analysis [36], [127], [146], [161], [193], CART [7], [40], -nearest-neighbor [82], [127], and linear programming method [127].”
• A Hybrid Neurogenetic Approach for Stock Forecasting (2007, methodology): “For example, ANNs showed better performance than statistical regression models [1] and discriminant analysis [2].”
• Machine Learning Techniques and Use of Event Information for Stock Market Prediction: A Survey and Evaluation (2005, background): “Yoon et al. [47] pointed out the superiority of NNs over classical discriminant analysis.”
• A new perspective on the competitiveness of nations (2008, result): “Artificial neural networks ANN techniques have been applied to a variety of problem types and, in many instances, provided superior results to conventional methods [30].”
• Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables (1999, methodology): “Recent comparisons in which ANNs performed favorably against conventional statistical approaches include Reibnegger et al. (1991), Patuwo et al. (1993), Yoon et al. (1993), Marzban and Stumpf (1996), Paruelo and Tomasel (1996), and Haas (1996), and Marzban et al. (1997).”
• Application of type-2 neuro-fuzzy modeling in stock price prediction (2012, methodology): “The given training data set is partitioned into clusters through input-similarity and output-similarity tests, and a type-2 TSK rule is derived from each cluster to form a fuzzy rule base.”
• Credit Scoring, Statistical Techniques and Evaluation Criteria: A Review of the Literature (2011, methodology): “Under the former validation technique, some studies have used a 50%-50% proportion between the two samples (Lenard et al, 1995; Yoon et al, 1993), whilst others have applied a 70%-30% or “2/3-1/3” proportion between different samples (Lee et al, 2002; Desai et al, 1996; Boritz & Kennedy, 1995;…”