• Ashwni Kumar
• Dr.D.L.Gupta

In the software engineering the most difficult problem is the software effort estimation. Today’s industry is facing the most common problem of developing error free software at low cost with less time. So to develop good quality of software it is very essential to know how to estimate the cost of the software. For good result of estimation and prediction it is very essential to take consideration of any previous projects. It is not very easy task to determine which techniques gives better result in software effort estimation. This paper focus on performance of M5 Rule, Decision Table, Conjection Rule, Zero Rule classifier is experimented for software effort estimation. The performance measures criteria are based on RMSE and MAE values. The result shows that the M 5 Rule technique gives best performance in software effort estimation model.

Software Effort Estimation, Machine Learning Techniques, COCOMO 2 dataset, comparative Analysis

"A Comparison of Machine Learning Techniques for Software Effort Estimation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.123-126, June 2019, Available :http://www.jetir.org/papers/JETIR1907O20.pdf

"A Comparison of Machine Learning Techniques for Software Effort Estimation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp123-126, June 2019, Available at : http://www.jetir.org/papers/JETIR1907O20.pdf