data mining techniques for software effort estimation
Abstract A prescient model is required to be exact and understandable so as to motivate trust in a business setting. The two angles have been surveyed in a product exertion estimation setting by past investigations. Be that as it may, no univocal end about which procedure is the most fit has been come to. This examination tends to this issue by covering the aftereffects of an enormous scope benchmarking study. Various sorts of systems are getting looked at, including procedures prompting tree/rule-based models like M5 and Truck, straight models, for example, different kinds of direct relapse, nonlinear models. Besides, the part of highlight subset choice by utilizing a conventional in reverse information choice wrapper is researched. The outcomes are exposed to thorough factual testing and demonstrate that common least squares relapse in blend with a logarithmic change performs best. Another key finding is that by choosing a subset of exceptionally prescient traits, for example, venture size, advancement, and condition related qualities, normally a huge increment in estimation exactness can be gotten.
 B. W. Boehm, "Software engineering economics," in Software pioneers: Springer, 2002, pp. 641-686.
 L. C. Briand, K. El Emam, D. Surmann, I. Wieczorek, and K. D. Maxwell, "An assessment and comparison of common software cost estimation modeling techniques," in Proceedings of the 1999 International Conference on Software Engineering (IEEE Cat. No. 99CB37002), 1999: IEEE, pp. 313-323.
 L. C. Briand, T. Langley, and I. Wieczorek, "A replicated assessment and comparison of common software cost modeling techniques," in Proceedings of the 22nd international conference on Software engineering, 2000, pp. 377-386.
 R. Sakia, "The Box‐Cox transformation technique: a review," Journal of the Royal Statistical Society: Series D (The Statistician), vol. 41, no. 2, pp. 169-178, 1992.