A methodology for forecasting knowledge work projects. (English) Zbl 0973.90039

Summary: Forecasting project duration for knowledge workers is particularly difficult due to the complexity and variability of their work. This study examines prediction of software development completion times which has traditionally involved either software engineering techniques or purely judgmental forecasts by lead analysts or project managers. In practice, neither approach has achieved much success in forecasting software project duration. This paper proposes a neural network model to modeling software project overruns. Actual software project management data, obtained for a regional grocery chain, were used to develop and test the neural network model as well as a traditional regression model for forecasting project overruns. Comparisons between the forecasts and the actual project overruns revealed that the neural network model outperformed the regression model in terms of forecast accuracy, degree of forecast bias and model fit. The results suggest that neural network modelling can be used to integrate managerial judgments and actual operating data to accurately forecast software project completion times.


90B50 Management decision making, including multiple objectives
Full Text: DOI


[1] Davenport T, Jarvenpaa S, Beers M. Improving knowledge work processes. Sloan Management Review 1996: 53-65.
[2] Dutta, S.; Shekhar, S.; Wong, W.Y., Decision support in non-conservative domains: generalization with neural networks, Decision support systems, 11, 527-544, (1994)
[3] Marucheck, A.; Sulek, J., A process approach to measuring knowledge worker productivity, Operations management review, 9, 4, 1-15, (1993)
[4] Goodwin, P., Statistical correction of judgmental point forecasts and decisions, Omega, 24, 3, 551-558, (1994)
[5] Goodwin, P.; Wright, G., Heuristics, biases and improvement strategies in judgmental time series forecasting, Omega, 23, 6, 553-568, (1994)
[6] Blattenburg, R.; Hoch, S., Database models and managerial intuition: 50
[7] Einhorn, H.J., Expert judgment: some necessary conditions and examples, Journal of applied psychology, 59, 562-571, (1974)
[8] Klein, J.H., Cognitive processes and operational research: a human information processing perspective, Journal of the operational research society, 45, 8, 855-866, (1993)
[9] Brehmer A, Brehmer B. What have we learned from thirty years of policy capturing? In: Brehmer B, Joyce C. editors. Human judgment: the social theory view, Amsterdam: North Holland, 1988. p. 203-210.
[10] Lee, J.W.; Yates, J.F., How quantity judgment changes and the number of cues increases: an analytical framework and review, Psychological bulletin, 112, 363-367, (1992)
[11] Stork, D., Self-organization, pattern recognition, and adaptive resonance networks, Neural network computing, 1, 1, 26-42, (1989)
[12] Bunn, D.; Wright, G., Interaction of judgmental and statistical forecasting methods: issues and analysis, Management science, 37, 5, 501-518, (1991)
[13] Schocken, S.; Ariav, G., Neural networks for decision support: problems and opportunities, Decision support systems, 11, 393-414, (1994)
[14] Gorman, R.P.; Sejnowski, T.J., Analysis of hidden units in a layered network trained to classify sonar targets, Neural networks, 1, 1, 75-89, (1988)
[15] Silverman, R.H.; Noetzel, A.S., Image processing and pattern recognition in ultrasonograms by backpropagation, Neural networks, 3, 5, 593-603, (1990)
[16] Lodewyck, R.W.; Deng, P., Experimentation with a back-propagation neural network, Information & management, 24, 1-8, (1993)
[17] Quang Do A, Grudnitski G. A neural network approach to residential property appraisal. The Real Estate Appraiser, December 1992; 38-45.
[18] Kryzanowski L, Galler M, Wright DW. Using artificial networks to pick stocks. Financial Analysis Journal 1993; 21-7.
[19] Swales GS, Yoon Y. Applying artificial neural networks to investment analysis. Financial Analysis Journal 1992; 78-80.
[20] Salchenberger, L.M.; Cinar, E.M.; Lash, N.A., Neural networks: a new tool for predicting thrift failures, Decision sciences, 23, 899-916, (1992)
[21] Fletcher, D.; Gross, E., Forecasting with neural networks: an application using bankruptcy data, Information and management, 24, 159-167, (1993)
[22] Bansal, A.; Kauffman, R.J.; Weitz, R.R., Comparing the modeling performance of regression and neural networks as data quality varies: a business approach, Journal of management information systems, 10, 1, 11-32, (1993)
[23] Tam, K.Y.; Kiang, M.Y., Managerial applications of neural networks: the case of bank failure predictions, Management science, 38, 7, 926-947, (1992) · Zbl 0763.90062
[24] Lee, J.K.; Jhee, W.C., A two-stage neural network approach for ARMA model identification with ESACF, Decision support systems, 11, 461-479, (1994)
[25] Hill, T.; Remus, W., Neural network models for intelligent support of managerial decision making, Decision support systems, 11, 449-459, (1994)
[26] Tam, K.Y., Neural networks for decision support, Decision support systems, 11, 389-392, (1994)
[27] Wilson, R.L., A neural network approach to decision alternative prioritization, Decision support systems, 11, 431-447, (1994)
[28] Drucker P. The age of discontinuity. New York: Harper and Row, 1969. p. 290. · Zbl 0183.45401
[29] Armstrong, J.S., Long-range forecasting from crystal ball to computer, (1985), Wiley-Interscience New York
[30] Armstrong, J.S.; Colloy, F., Causal forces: structuring knowledge for time-series extrapolation, Journal of forecasting, 12, 103-115, (1993)
[31] Collopy, F.; Adya, M.; Armstrong, J.S., Principles for examining predictive validity: the case of information systems spending forecasts, Information systems research, 5, 2, 170-179, (1994)
[32] Armstrong, J.S.; Fildes, R., Correspondence on the selection of error measures for comparisons among forecasting methods, Journal of forecasting, 14, 67-71, (1995)
[33] Mathews, B.; Diamantopoulos, A., Towards a taxonomy of forecast error: a factor comparative investigation of forecast error dimensions, Journal of forecasting, 13, 409-416, (1994)
[34] Gray P. How to get gains from technology. Information Systems Management 1994; 88-91.
[35] Brainmaker, User’s guide and reference manual, 7th ed. California Scientific Software, Nevada City, CA 95959, August 1993. p. 161.
[36] Lawrence, JL. Introduction to neural networks, 2nd ed. Grass Valley, CA. California Scientific Software, 1991. p. 162.
[37] Stewart, T.R.; Lusk, C.M., Seven components of judgmental forecasting skill implications for research and the improvement of forecasts, Journal of forecasting, 13, 579-599, (1994)
[38] Lederer, A.L.; Prasad, J., Nine management guidelines for better cost estimating, Communications of the ACM, 25, 2, 51-59, (1992)
[39] Badiru, A., Towards the standardization of performance measures for project scheduling heuristic, IEEE transactions on engineering management, 35, 2, 82-89, (1988)
[40] Arsham, H., Managing project activity — duration uncertainties, Omega, 21, 111-122, (1993)
[41] Neter J, Wasserman W, Kutner MH. Applied linear statistical models. Homewood, IL: Richard D. Irwin, 1974.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.