Building machine learning products or ML-assisted product features involve two distinct disciplines:
Model Development: Data Scientists — highly skilled in statistics, linear algebra, and calculus — train, evaluate, and select the best-performing statistical or neural network model.
Model Deployment: Developers — highly skilled in software design and engineering — build a robust software system, deploy it on the cloud, and scale it to serve a huge number of concurrent model inference requests.
Of course, that is a gross over-simplification. It takes several other vital expertise in building useful and successful ML-assisted products:
Data Engineering: Build data pipelines to collect data from disparate sources, curate and transform it, and turn it into homogenous, clean data that can be safely used for training models.
Product Design: Understand business needs, identify impactful objectives and relevant business matrices; define product features or user stories for those objectives, recognize the underlying problems that ML is better suitable to solve; design user experience to not only utilize ML model prediction seamlessly with rest of the product features but also collect user (re)action as implicit evaluation of the model results, and use it to improve the models.
Security Analysis: Ensure that the software system, data, and model are secure, and no Personally Identifiable Information (PII) is revealed by combining model results and other publicly available information or data.
AI Ethics: Ensure adherence to all applicable laws, and add measures to protect against any kind of bias (e.g. limit the scope of the model, add human oversight, etc.)
As more models are being deployed in production, the importance of MLOps has naturally grown. There is an increasing focus on the seamless design and functioning of ML models within the overall product. Model Development can’t be done in a silo given the consequences it may have on the product and business.
We need an ML lifecycle that is attuned to the realities of ML-assisted products and MLOps. It should facilitate visibility for all stakeholders, without causing too many changes in the existing workflows of data scientists and engineers.
In the rest of the article, I first give an overview of the typical Model Development and Software Development workflows, and then how to bring the two together for adapting to the needs of building ML-assisted products in the MLOps era.
Top comments (0)