Comparing the 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 adecision maker to design a business value-maximizing information system. This paper examines a real-worldexample from the field of finance to illustrate a comparison of alternative modeling tools. Twomodeling alternatives are used in this example: regression analysis and neural network analysis. Thereare 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-basedforecasts tended to be more robust than linear regression forecasts as data accuracy degraded.Managerial implications for financial risk management of MBS portfolios are drawn from the results