Project Effort: Empirical Case Studies in

clangedbivalveΤεχνίτη Νοημοσύνη και Ρομποτική

19 Οκτ 2013 (πριν από 3 χρόνια και 8 μήνες)

69 εμφανίσεις

Using Machine Learning to Predict
Project Effort: Empirical Case Studies in
Data
-
starved Domains

Gary D. Boetticher

Department of Software Engineering

University of Houston
-

Clear Lake

What Customers Want

What Requirements Tell Us

Standish Group
[Standish94]



Exceeded planned budget by 90%



Schedule by 222%



More than 50% of the projects had less than
50% requirements

Underlying Problems


85% are at CMM 1 or 2
[CMU CMM95, Curtis93]



Scarcity of data

Consequences



Early life
-
cycle estimates use a factor of 4
[Boehm81, Heemstra92]

Related Research: Economic Models

Why are Machine Learning
algorithms not used more often for
estimating early in the life cycle?

Related Research
-

2

Goal


Apply Machine Learning (Neural Network)



early in the software lifecycle


against Empirical Data

Neural Network

Data


B2B Electronic Commerce Data


Delphi
-
based


104 Vectors


Fleet Management Software


Delphi
-
based


433 Vectors

Experiment 1:
Product
-
Based
Fleet to B2B

Experiment 1:
Product

Results

Experiment 2:
Project
-
Based Results
Fleet to B2B

Experiment 3:
Product
-
Based
B2B to Fleet

Extrapolation issue



Largest SLOCs divided by each other


4398 / 2796 = 1.57


Experiment 3:
Product

Results

Experiment 4:
Project
-
Based Results
B2B to Fleet

Results

Conclusions


Bottom
-
up approach produced very good
results on a project
-
basis


Results comparable between NN and stat.


Scaling helped


Estimation Approach is suitable for
Prototype/Iterative Development

Future Directions


Explore an extrapolation function


Apply other ML algorithms


Collect additional metrics


Integrate with COCOMO II


Conduct more experiments (additional data)