Most existing methods of effort estimations in software development are manual, labor-intensive and subjective, resulting in overestimation with bidding fail, and underestimation with money loss. This paper investigates effectiveness of sequence models on estimating development effort, in the form of man-months, from software project data. Four architectures; (1) Average word-vector with Multi-layer Perceptron (MLP), (2) Average word-vector with Support Vector Regression (SVR), (3) Gated Recurrent Unit (GRU) sequence model, and (4) Long short-term memory (LSTM) sequence model are compared in terms of man-months difference. The approach is evaluated using two datasets; ISEM (1,573 English software project descriptions) and ISBSG (9,100 software projects data), where the former is a raw text and the latter is a structured data table explained the characteristic of a software project. The LSTM sequence model achieves the lowest and the second lowest mean absolute errors, which are 0.705 and 14.077 man-months for ISEM and ISBSG datasets respectively. The MLP model achieves the lowest mean absolute errors which is 14.069 for ISBSG datasets.

Analogy-based software effort estimation has gained a considerable amount of attention in current research and practice. Its excellent estimation accuracy relies on its solution adaptation stage, where an effort estimate is produced from similar past projects. This study proposes a solution adaptation technique named LSA-X that introduces an approach to exploit the potential of productivity factors, i.e., project variables with a high correlation with software productivity, in the solution adaptation stage. The LSA-X technique tailors the exploitation of the productivity factors with a procedure based on the Linear Size Adaptation (LSA) technique. The results, based on 19 datasets show that in circumstances where a dataset exhibits a high correlation coefficient between productivity and a related factor (r≥0.30), the proposed LSA-X technique statistically outperformed (95% confidence) the other 8 commonly used techniques compared in this study. In other circumstances, our results suggest using any linear adaptation technique based on software size to compensate for the limitations of the LSA-X technique.

In this paper we discuss the estimation of effort needed to update program codes according to given design specification changes. In the Object-Oriented incremental development (OOID), the requirement changes occur frequently and regularly. When a requirement change occurs, a design specification is changed accordingly. Then a program code is updated for given design specification change. In order to construct the development plan dynamically, a simple and fast estimation method of efforts for code updating is strongly required by both developers and managers. However, existing estimation methods cannot be applied to the OOID. We therefore try to propose a straightforward approach to estimate effort for code updating, which reflects the specific properties of the OOID. We list up following factors of the effort estimation for OOID: (1) updating activities consist of creation, deletion, and modification, (2) the target to be updated has four kinds of types (void type, basic type, library type, and custom type), (3) the degree of information hiding is classified into private, protected and public, and (4) the degree of inheritance affects updating efforts. We then propose a new formula E(P,σ) to calculate the efforts needed to update a program P according to a set of design specification changes σ. The formula E(P,σ) includes weighting parameters: Wupd, Wtype, Winf-h and Winht according to the characteristics (1), (2), (3) and (4), respectively. Finally, we conduct experimental evaluations by applying the formula E(P,σ) to actual project data in a certain company. The evaluation results statistically showed the validity of the proposed approach to some extent.