Artificial Intelligence (AI) and Machine Learning (ML) products are unique. They hold enormous power and are by definition constantly changing. Due to the level of sophistication involved, the development process for AI products is distinct from traditional products. In this presentation, Ria Sankar, a Group Product Manager at Microsoft, introduces the best practices for developing AI products with insight, integrity,
When Building AI Products:
- Plan: Start from a clear understanding of your user, your business, the problem you are solving and the metrics you are using to define success
- Define: Prepare your data with clear specifications, and reach a sophisticated understanding of the model you are using, and why you chose it
- Execute: Deploy your chosen model. Constantly measure as you, your team and your software learn and gather more data
Now let’s dive deeper into those three stages within the context of building AI products. As we go through, you’ll notice some similarities to the classic product development formula, as well as some unique considerations that will help you understand why building AI products is a distinctive challenge.
- Understand the customer – see the tasks your product performs in their life, this is sometimes known as “jobs to be done“.
- Understand the business consequences – will this feature help you gain or lose the trust of your users?
- Understand data – use comprehensive case studies to protect against bias.
- Understand metrics – distinguish between primary and secondary goals, products and features, standard vs derived metrics.
- Prepare your data – Good data is: correct, current, consistent and consolidated.
- Design with ethics – know the context in which your product will be used, and make the human users the heroes. The product should feel like it empowers people to live better, more productive lives. It shouldn’t make them feel threatened or replaced.
- Select your model – make this critical decision based on consideration both of your business, and of the environment and context in which your product will be used. How is value measured? Will it be supplied online, or through a one-off batch?
- Model deployment – When deploying your model, Ria advises to be conscious of scale, check outliers and bias, visualize the output
- Ongoing learning – Your software will continually be learning and improving itself. There are many examples of this, one that Ria explores in the video is the Uber Michelangelo platform
Recap: CRISP-DM Model
The Cross-industry standard process for data mining (CRISP-DM) provides a useful structure for recapping the presentation:
- Scope your problem
- Build the business case for ML/AI
- Select your ML model
- Balance model performance and accuracy
- Ensure model relevance to changing business needs
- Human-powered vs. Machine powered AI