The Unofficial Google Data Science Blog

APRIL 23, 2024

If $Y$ at that point is (statistically and practically) significantly better than our current operating point, and that point is deemed acceptable, we update the system parameters to this better value. In isolation, the $x_1$-system is optimal: changing $x_1$ and leaving the $x_2$ at 0 will decrease system performance.

Experimentation 52

Experimentation Optimization Uncertainty Metrics 52

Domino Data Lab

JANUARY 24, 2019

In 2018 we saw the “data science platform” market rapidly crystallize into three distinct product segments. This group of solutions targets code-first data scientists who use statistical programming languages and spend their days in computational notebooks (e.g., Reflections. Jupyter) or IDEs (e.g.,

Data Science 65

Data Science Marketing Data-driven Statistics 65

Business Over Broadway

MAY 22, 2019

For those of you who are interested, here is Gartner’s latest (2018) hype cycle on emerging technologies. According to Gartner, companies need to adopt these practices: build culture of collaboration and experimentation; start with a 3-way partnership among executives leading digital initiative, line of business and IT.

Machine Learning 40

Machine Learning Technology Digital Transformation Data Science 40

Occam's Razor

JULY 24, 2018

The ability to optimize landing pages. At the top-right, you’ll discover my obsession with Profit and Incrementality, which form the basis of competitive advantage in 2018 (and beyond). Ignore the metrics produced as an experimental exercise nine months ago. So, how do we ensure that each has an optimal analytical approach?

Analytics 93

Analytics Metrics Strategy Measurement 93

Domino Data Lab

MAY 8, 2019

2018-06-21). They also require advanced skills in statistics, experimental design, causal inference, and so on – more than most data science teams will have. Perhaps if machine learning were solely being used to optimize advertising or ecommerce, then Agile-ish notions could serve well enough. Riccardo Guidotti, et al.

Machine Learning 105

Machine Learning Data Science Modeling Visualization 105

Domino Data Lab

AUGUST 22, 2019

Although it’s not perfect, [Note: These are statistical approximations, of course!] You can home in on an optimal value by specifying, say, 32 dimensions and varying this value by powers of 2. If we were using CBOW, then a window size of 5 (for a total of 10 context words) could be near the optimal value. Example 11.6

Deep Learning 111

Deep Learning Modeling Metrics Testing 111