AI Model Life Cycle
Every AI project lifecycle encompasses three main stages: project scoping, design
or build phase, and deployment in production. Let's go over each of them and the
key steps and factors to consider when implementing them.
Scoping (Requirements analysis):
The project’s goals and objectives are described in the scope statement, which
serves as a definition of the project. A description of the constraints, assumptions,
deliverables, acceptance criteria and the scope of the product should be included
according to the project standard.
The planning and motivational parts of your project come first during this stage. It
is important to start strong if you want your artificial intelligence project to be
successful. This means if the data you collect is no good, you won't be able to build
an effective AI algorithm, and your whole project will collapse. Selecting the AI or
machine learning use cases and being able to evaluate the return on investment
(ROI) is critical to the success of any data project.
Design/Building the Model:
Once the relevant projects have been selected and properly scoped, the next step of
the machine learning lifecycle is the Design or Build phase, which can take from a
few days to multiple months, depending on the nature of the project. The Design
phase is essentially an iterative process comprising all the steps relevant to
building the AI or machine learning model: data acquisition, exploration,
preparation, cleaning, feature engineering, testing and running a set of models to
try to predict behaviours or discover insights in the data.
Enabling all the different people involved in the AI project to have the appropriate
access to data, tools, and processes in order to collaborate across different stages of
the model building is critical to its success.
During this phase, you need to evaluate the various AI development platforms,
e.g.:
➢ Open languages — Python is the most popular, with R and Scala also in the
mix.
➢ Open frameworks — Scikit-learn, XGBoost, TensorFlow, etc.
➢ Approaches and techniques — Classic ML techniques from regression all
the way to state-of-theart GANs and RL
➢ Productivity-enhancing capabilities — Visual modelling, AutoAI to help
with feature engineering, algorithm selection and hyperparameter
optimization
➢ Development tools — DataRobot, H2O, Watson Studio, Azure ML Studio,
Sagemaker, Anaconda, etc.
Different AI development platforms offer extensive documentation to help the
development teams. Choice of the AI platform, you need to visit the appropriate
webpages for this documentation, which are as follows:
• Microsoft Azure AI Platform;
• Google Cloud AI Platform;
• IBM Watson Developer platform;
• BigML
• Infosys Nia resources.
Testing:
While the fundamental testing concepts are fully applicable in AI development
projects, there are additional considerations too. These are as follows:
➢ The volume of test data can be large, which presents complexities.
➢ Human biases in selecting test data can adversely impact the testing phase,
therefore, data validation is important.
➢ Your testing team should test the AI and ML algorithms keeping model
validation, successful learnability, and algorithm effectiveness in mind.
➢ Regulatory compliance testing and security testing are important since the
system might deal with sensitive data, moreover, the large volume of data
makes performance testing crucial.
➢ You are implementing an AI solution that will need to use data from your
other systems, therefore, systems integration testing assumes importance.
➢ Test data should include all relevant subsets of training data, i.e., the data
you will use for training the AI system.
➢ Your team must create test suites that help you validate your ML models.
