Comparing the Modeling Performance of Regression and Neural Networks as Data Quality Varies: A Business Value Approach.

Author List: Bansal, Arun; Kauffman, Robert J.; Weitz, Rob R.;
Journal of Management Information Systems, 1993, Volume 10, Issue 1, Page 11/1/1932.
Under circumstances where data quality may vary (due to inaccuracies or lack of timeliness, for example), knowledge about the potential performance of alternate predictive models can help a decision maker to design a business-value-maximizing information system. This paper examines a real-world example from the field of finance to illustrate a comparison of alternative modeling tools. Two modeling alternatives are used in this example: regression analysis and neural network analysis. There are two main results: (1) Linear regression outperformed neural nets in terms of forecasting accuracy, but the opposite was true when we considered the business value of the forecast. (2) Neural net-based forecasts tended to be more robust than linear regression forecasts as data accuracy degraded. Managerial implications for financial risk management of mortgage-backed security portfolios are drawn from the results.
Keywords: business value of information technology; data quality; decision support systems; forecasting; information economics; mortgage-backed securities; neural networks; prepayment forecasting; risk management forecasting systems
Algorithm:

List of Topics

#215 0.268 data classification statistical regression mining models neural methods using analysis techniques performance predictive networks accuracy method variables prediction problem measure
#8 0.129 decision making decisions decision-making makers use quality improve performance managers process better results time managerial task significantly help indicate maker
#226 0.121 models linear heterogeneity path nonlinear forecasting unobserved alternative modeling methods different dependence paths efficient distribution probabilities demonstrate observed heterogeneous probability
#143 0.101 value business benefits technology based economic creation related intangible cocreation assessing financial improved key economics assess question created create understanding
#0 0.084 information types different type sources analysis develop used behavior specific conditions consider improve using alternative understanding data available main target
#240 0.065 systems information management development presented function article discussed model personnel general organization described presents finally computer-based role examined functional components
#37 0.064 intelligence business discovery framework text knowledge new existing visualization based analyzing mining genetic algorithms related techniques large proposed novel artificial