Software Development Effort Estimation from Unstructured Software Project Description by Sequence Models
Summary :
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.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.4 pp.739-747
- Publication Date
- 2020/04/01
- Publicized
- 2020/01/14
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019IIP0014
- Type of Manuscript
- Special Section PAPER (Special Section on Intelligent Information and Communication Technology and its Applications to Creative Activity Support)
- Category
Authors
Tachanun KANGWANTRAKOOL
Sirindhorn International Institute of Technology
Kobkrit VIRIYAYUDHAKORN
Sirindhorn International Institute of Technology
Thanaruk THEERAMUNKONG
Sirindhorn International Institute of Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Tachanun KANGWANTRAKOOL, Kobkrit VIRIYAYUDHAKORN, Thanaruk THEERAMUNKONG, "Software Development Effort Estimation from Unstructured Software Project Description by Sequence Models" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 4, pp. 739-747, April 2020, doi: 10.1587/transinf.2019IIP0014.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019IIP0014/_p
Copy
@ARTICLE{e103-d_4_739,
author={Tachanun KANGWANTRAKOOL, Kobkrit VIRIYAYUDHAKORN, Thanaruk THEERAMUNKONG, },
journal={IEICE TRANSACTIONS on Information},
title={Software Development Effort Estimation from Unstructured Software Project Description by Sequence Models},
year={2020},
volume={E103-D},
number={4},
pages={739-747},
abstract={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.},
keywords={},
doi={10.1587/transinf.2019IIP0014},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Software Development Effort Estimation from Unstructured Software Project Description by Sequence Models
T2 - IEICE TRANSACTIONS on Information
SP - 739
EP - 747
AU - Tachanun KANGWANTRAKOOL
AU - Kobkrit VIRIYAYUDHAKORN
AU - Thanaruk THEERAMUNKONG
PY - 2020
DO - 10.1587/transinf.2019IIP0014
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2020
AB - 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.
ER -
English
