2024/09/27 –, 4F Track4
In the Mercari Group’s Trust and Safety ML Team, we provide solutions to ensure the safety of the users. Examples of the solutions we provide include anti-money laundering countermeasures, credit card fraud detection, and many others. Some of these solutions are powered by machine learning models. In order to be as reactive as possible to emerging frauds, it is important to streamline the model improvement and deployment processes. In this talk, we will explain our platform and automation, and how each element helps us rapidly deploy new countermeasures. We will cover all MLOps steps: experimentation, training/deployment, evaluation, and metric monitoring. We hope our talk benefits those integrating DevOps into their ML solutions or building ML platforms, especially with GCP’s Vertex AI.
We chose this topic because there are numerous ways to design automations for deploying ML models in production, yet few resources explain how these steps integrate into a cohesive workflow. By sharing our experiences and solutions, we aim to empower other teams to implement similar strategies, helping developers navigate the challenges of building MLOps automations. Our goal is to fill this knowledge gap and provide a comprehensive view of the entire process, from model development to deployment, which might provide ideas for teams to improve their own development flow.
オーディエンスが持って帰れる具体的な知識やノウハウ –- Insights into how our Mercari Group Trust and Safety ML Team manages ML model training and deployment.
- Practices for each step of the MLOps cycle, including experimentation, training, deployment, evaluation, and metric monitoring.
- Key insights about how our automation streamlines each MLOps process.
- Know-how on utilizing tools and techniques to achieve this, with a focus on GCP's Vertex AI platform.
- Basic understanding of data science fundamentals (importance of metrics and monitoring) and ML model training/evaluation/deployment flow.
- Basic DevOps knowledge (CI/CD, etc.)
- Familiarity with cloud platforms (especially GCP).
Intermediate
発表の言語 –English
発表資料の言語 –English
Calvin is an ML engineer currently working at Mercari, where he focuses on creating and improving ML models and MLOps infrastructure to ensure the safety of Mercari users. Previously, he worked as an ML engineer at Rakuten, developing various projects such as inappropriate review detection and business impact analysis, along with the MLOps and DevOps infrastructure supporting these initiatives. He is passionate about AI, ML, MLOps, and web development. In his free time, he produces electronic music and plays jazz fusion sporadically with his bandmates.