2023-12-09, 10:55–11:25 (Asia/Taipei), NYCU
Data science products within private organizations usually start with high expectation and end up low usage. This talk is about what are the common pitfalls of these data science products and shares some perspective of building useful data science projects.
Data science products within private company usually starts with high expectation and ends up with low usage. This talk is about what are the common pitfalls of these data science products and shares some perspective of building useful data science projects. It is mostly about concept with little tool sharing. The topics include
* Before anything starts, domain knowledge and business perspective are most important.
* Be sure to align your vision with customers and project team
* Data quality
* Model verification & accuracy
* Data visualization - always making sense to your customer
* Monitor metric - always tight to business requirement
* Extend your product phase by phase - keep your product alive
Yes, previous knowledge expected
Language –Mandarin talk w. English slides
data science manager in semiconductor industry