Abstract | ||
---|---|---|
Accurate estimation of development effort is highly crucial for software project planning since it affects project delivery time and project costs. In this work, Machine Learning based software effort estimation methods are compared and their error rates are documented. Decision Tree, Naive Bayes and Multiple Regression models were inspected and they were trained and tested using data obtained from a local software house. |
Year | Venue | Keywords |
---|---|---|
2018 | Signal Processing and Communications Applications Conference | software effort estimation,machine learning,decision tree,regression |
Field | DocType | ISSN |
Decision tree,Naive Bayes classifier,Computer science,Integrated project delivery,Software,Project planning,Artificial intelligence,Machine learning | Conference | 2165-0608 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vehbi Yurdakurban | 1 | 0 | 0.34 |
Nadia Erdoğan | 2 | 69 | 11.49 |