A well-known core concept within artificial intelligence systems is that their predictions are only as good as their data. A classic example would be, an algorithm with a million data points will surely outperform the same algorithm with 10,000 data points.
According to Hoa Khanh Dam, a lead researcher from the University of Wollongong, the vision of the whole research is based upon our team’s collective experience working in and with the industry. The experiences involved from seeing real challenges in running agile software projects and serious lack of meaningful support for software teams and practitioners to witnessing the potential of AI in offering significant support for managing agile projects, not only in automating routine tasks, but also in learning and harvesting valuable insights from project data for making predictions and estimations, planning and recommending concrete actions.
Keeping that in view, researchers at the University of Wollongong, Kyushu University have developed a holistic framework that could be used to build a smart, agile project management assistant powered by artificial intelligence. The research paper has been accepted at the 41st International Conference on Software Engineering (ICSE) 2019.
Major Benefits of AI-Powered Agile Project Management
- Usage of AI tools will revolutionise project management which will be enhancing productivity by automating repetitive and high-volume tasks.
- AI tools will also be able to deliver analytics-driven risk predictions and estimations, complete basic administration tasks and give actionable recommendations too.
- AI tools will also ensure in transforming the practice of software project management to increase software quality.
- Using agile project management methods such as Scrum, software teams can rapidly deliver quality software using an iterative approach to guide and plan project processes is a good example of this.
- This combination of AI technologies could offer support at almost every step of an agile project’s lifecycle
- It will help product owners identify product backlog items that are the user stories and tasks.
- It will help in refining them that is decomposing an epic into several user stories, splitting user stories into small stories, and breaking a user story into several tasks.
- Also use of AI will help in detecting duplicates and dependencies.
- It will also help agile teams in sprint planning, for example by selecting items in the product backlog for the upcoming sprint, recommending optimal sprint plans, or predicting future risks and mitigations.
- Use of AI in this will only assist, not substitute, human teams. Individuals, interactions, and collaboration are still the key elements of project success as set out in the agile manifesto.
- Use of AI will also serve as a distinctive accelerator for agile teams and thereby help in increasing project success rates.
What The Research Proposes?
- This research explores the potential use of AI for agile project management, which has become increasingly popular over the past few years.
- The researchers proposed a new framework for the use of AI technologies, including deep learning, reinforcement learning, natural language processing, evolutionary search, and intelligent agents, within the context of agile project management.
- The researchers envision an AI-powered agile project assistant that can converse with users and support them in their work.
This AI system would feature –
- Analytics Engine – The analytics engine majorly provides decision support through descriptive, predictive and prescriptive analytics.
- Planning Engine – Planning Engine is where an AI planning problem in which the initial state is the state of the project and the product prior a sprint, a goal state is specified in the sprint’s goal.
- Optimisation Engine – This engine helps in a supportive role, the planning engine to compute and execute the optimal set of actions given a certain situation.
- Conversation Dialog Engine – This engine primarily helps and works with agile teams. It is a form of a software chatbot that acts as an interface between the users and the remaining part of the AI system.
The framework developed by the researchers addresses four main areas in agile project management that are particularly challenging, due to a lack of effective tools.
These include –
- Identifying backlog items.
- Refining backlog items and sprint planning.
- Monitoring of sprint progress and risk management.
A framework for #AI-powered agile project management https://t.co/gdDsvWiyle #fintech #insurtech #ArtificialIntelligence #MachineLearning #DeepLearning #robotics @Ini_fadelli @TechXplore_com @DimDrandakis @sallyeaves @jblefevre60 @alvinfoo @antgrasso pic.twitter.com/5HTFA9nY90
— Spiros Margaris (@SpirosMargaris) January 12, 2019
Outlook
According to Hoa Khanh Dam , the most important contribution here of the research team is setting out a big, ambitious roadmap for future research and development of an AI tool suite for agile project management. With already having developed several components of our framework, including sprint planning, story point estimation and delay risk estimation they have realised that the vision set out in the paper is a big project and for developing parts or the full framework collaboration of industry partners is a must.
Developing prototype tools for each of the components outlined in their framework is what Dam along with fellow colleagues are looking to focus upon. After these components are finalized, evaluating their system on a dataset of 150 open source projects is what further they have planned for.
The post How To Achieve Effective AI-Powered Agile Project Management appeared first on Analytics India Magazine.