Comparing the modeling performance of regression and neural networks as data quality varies: A business value approach

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 and analysis. There are two main results: (1) Linear regression outperformed neural nets in terms of forecasting accuracy, but the opposite was true when the authors 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.