Can neural networks be easily interpreted in software cost estimation?

Software development effort estimation with the aid of neural networks has generally been viewed with skepticism by a majority of the software cost estimation community. Although, neural networks have shown their strengths in solving complex problems, their shortcoming of being 'black boxes' models has prevented them from being accepted as a common practice for cost estimation. In this paper, we study the interpretation of cost estimation models based on a backpropagation three layer perceptron network. Our proposed idea comprises mainly of the use of a method that maps this neural network to a fuzzy rule based system. Consequently, if the obtained fuzzy rules are easily interpreted, the neural network will also be easy to interpret. Our case study is based on the COCOMO'81 dataset.

[1]  Douglas Fisher,et al.  Machine Learning Approaches to Estimating Software Development Effort , 1995, IEEE Trans. Software Eng..

[2]  Alain Abran,et al.  A fuzzy logic based set of measures for software project similarity: validation and possible improvements , 2001, Proceedings Seventh International Software Metrics Symposium.

[3]  Barry W. Boehm,et al.  Software Engineering Economics , 1993, IEEE Transactions on Software Engineering.

[4]  Taghi M. Khoshgoftaar,et al.  Estimating software project effort by analogy based on linguistic values , 2002, Proceedings Eighth IEEE Symposium on Software Metrics.

[5]  Magne Jørgensen,et al.  Experience With the Accuracy of Software Maintenance Task Effort Prediction Models , 1995, IEEE Trans. Software Eng..

[6]  A. R. Venkatachalam.  Software cost estimation using artificial neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[7]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[8]  Chuen-Tsai Sun,et al.  Functional equivalence between radial basis function networks and fuzzy inference systems , 1993, IEEE Trans. Neural Networks.

[9]  Alain Abran,et al.  COCOMO cost model using fuzzy logic , 2000 .

[10]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[11]  Barry W. Boehm,et al.  Cost models for future software life cycle processes: COCOMO 2.0 , 1995, Ann. Softw. Eng..

[12]  Ignacio Requena,et al.  Are artificial neural networks black boxes? , 1997, IEEE Trans. Neural Networks.

[13]  Gavin R. Finnie,et al.  Estimating software development effort with connectionist models , 1997, Inf. Softw. Technol..

[14]  Sunita Devnani-Chulani,et al.  Incorporating Bayesian Analysis to Improve the Accuracy of COCOMO II and Its Quality Model Extension , 1998 .

[15]  Alain Abran,et al.  Fuzzy Analogy: A New Approach for Software Cost Estimation , 2001 .

[16]  Alain Abran,et al.  Towards a fuzzy logic based measures for software projects similarity , 2000 .

[17]  Alan F. Murray,et al.  International Joint Conference on Neural Networks , 1993 .

[18]  Alain Abran,et al.  Evaluating software project similarity by using linguistic quantifier guided aggregations , 2001, Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569).