Improving the Accuracy of COCOMO II Effort Estimation Based on Neural Network with Hyperbolic Tangent Activation Function

Sarah Abdulkarem Alshalif, Noraini Ibrahim, Waddah Waheeb


Constructive Cost Model II (COCOMO II) is one of the best-known software cost estimation model. The estimation of the effort in COCOMO II depends on several attributes that categorized by software size (SS), scale factors (SFs) and effort multipliers (EMs). However, provide accurate estimation is still unsatisfactory in software management. Neural Network (NN) is one of several approaches developed to improve the accuracy of COCOMO II. From the literature, they found that the learning using sigmoid function has always mismatched and ill behaved. Thus, this research proposes Hyperbolic Tangent activation function (Tanh) to use in the hidden layer of the NN. Two different architectures of NN with COCOMO (the basic COCOMO-NN and the modified COCOMO-NN) are used. Back-propagation learning algorithm is applied to adjust the COCOMO II effort estimation parameters. NASA93 dataset is used in the experiments. Magnitude of Relative Error (MRE) and Mean Magnitude of Relative Error (MMRE) are used as evaluation criteria. This research attempts to compare the performance of Tanh activation function with several activation functions, namely Uni-polar sigmoid, Bi-polar sigmoid, Gaussian and Softsign activation functions. The experiment results indicate that the Tanh with the modified COCOMO-NN architecture produce better result comparing to other activation functions.


Activation Functions; Constructive Cost Model II; Effort Estimation; Neural Network;

Full Text:



C. Jones, “Software cost estimation in 2002,” The Journal of Defense Software Engineering, vol. 15, pp. 4-8, Jun. 2002.

B. W. Boehm, Software engineering economics. Englewood Cliffs, NJ: Prentice-hall, 1981, pp. 9-29.

L. H. Putnam, “A general empirical solution to the macro software sizing and estimating problem,” IEEE Transactions on Software Engineering, vol. 4, no. 4, pp. 345-361, Jul. 1978.

B. W. Boehm, R. Madachy, and B. Steece, Software Cost Estimation with COCOMO II. Upper Saddle River, NJ: Prentice Hall, 2000, pp. 12-31.

A. Kaushik, A. Chauhan, D. Mittal, and S. Gupta, “COCOMO estimates using neural networks,” International Journal of Intelligent Systems and Applications, vol. 4, pp. 22-28, Aug. 2012.

O. Tailor, A. Kumar, and M. P. Rijwani, “A new high performance neural network model for software effort estimation,” International Journal of Innovative Science, Engineering & Technology, vol. 1, pp. 400-405, May 2014.

S. A. Alshalif, N. Ibrahim, T. Herawan, “Artificial neural network with hyperbolic tangent activation function to improve the accuracy of COCOMO II model,” in The Second International Conference on Soft Computing and Data Mining (SCDM), Springer, 2016, pp. 81-90.

C. Lopez-Martin, and A. Abran, “Neural networks for predicting the duration of new software projects,” Journal of Systems and Software, vol. 101, pp. 127-135, Mar. 2015.

C. S. Reddy, and K. Raju, “A concise neural network model for estimating software effort,” International Journal of Recent Trends in Engineering, vol. 1, pp. 188-193, May. 2009.

A. Kaushik, A. Chauhan, D. Mittal, and S. Gupta, “COCOMO estimates using neural networks,” International Journal of Intelligent Systems and Applications, vol. 4, pp. 22-28, Aug. 2012.

A. Kaushik, A. K. Soni, and R. Soni, “A simple neural network approach to software cost estimation,” Global Journal of Computer Science and Technology, vol. 13, pp. 23-30, Dec. 2013.

M. Madheswaran, and D. Sivakumar, “Enhancement of prediction accuracy in COCOMO model for software project using neural network,” in Fifth International Conference on Computing, Communications and Networking Technologies (ICCCNT), IEEE, 2014, pp. 1-5.

S. Mukherjee, and R. K. Malu, “Optimization of project effort estimate using neural network,” in 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies, 2014, pp. 406-410.

G. Kumar, and P. K. Bhatia, “Automation of software cost estimation using neural network technique,” International Journal of Computer Applications, vol. 98, pp. 11-17, Jan. 2014.

R. Sarno, and J. Sidabutar, “Comparison of different Neural Network architectures for software cost estimation,” in 2015 International Conference on Computer, Control, Informatics and its Applications (IC3INA), 2015, pp. 68-73.

R. Sarno., and J. Sidabutar, “Improving the accuracy of COCOMO's effort estimation based on neural networks and fuzzy logic model,” in International Conference on Information & Communication Technology and Systems (ICTS), 2015, pp. 197-202.

P. Rijwani, and S. Jain, “Enhanced software effort estimation using multi layered feed forward artificial neural network technique,” Procedia Computer Science, vol. 89, pp. 307-312, Dec. 2016.

B. Karlik, and A. V. Olgac, “Performance analysis of various activation functions in generalized MLP architectures of neural networks,” International Journal of Artificial Intelligence and Expert Systems, vol. 1, pp. 111-122, Feb. 2011.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN: 2180-1843

eISSN: 2289-8131