The Unofficial Google Data Science Blog

JULY 18, 2023

E ven after we account for disagreement, human ratings may not measure exactly what we want to measure. Overview Human-labeled data is ubiquitous in business and science, and platforms for obtaining data from people have become increasingly common. And for thousands of years, measurement was as simple as this.

Measurement 52

Measurement Metrics Uncertainty Slice and Dice 52

Occam's Razor

SEPTEMBER 15, 2014

But why blame others, in this post let's focus on one important reason whose responsibility can be squarely put on your shoulders and mine: Measurement. Create a distinct mobile website and mobile app measurement strategies. Mobile content consumption, behavior along key metrics (time, bounces etc.)

Metrics 141

Metrics Reporting Analytics Marketing 141

CIO Business Intelligence

MAY 16, 2023

higher [in 2022] than in 2017.” The inherent capabilities of AI–to process vast amounts of data and use learned intelligence to make decisions with extraordinary speed–enable opportunities uncovered through digital listening. McKinsey & Company’s 2022 Global Survey on AI says , “AI adoption globally is 2.5x

Advertising 79

Advertising Recreation/Entertainment Experimentation Enterprise 79

Domino Data Lab

MAY 8, 2019

The lens of reductionism and an overemphasis on engineering becomes an Achilles heel for data science work. Instead, consider a “full stack” tracing from the point of data collection all the way out through inference. Finale Doshi-Velez, Been Kim (2017-02-28) ; see also the Domino blog article about TCAV. 2018-06-21).

Machine Learning 105

Machine Learning Data Science Modeling Visualization 105

Domino Data Lab

MAY 20, 2021

Working with highly imbalanced data can be problematic in several aspects: Distorted performance metrics — In a highly imbalanced dataset, say a binary dataset with a class ratio of 98:2, an algorithm that always predicts the majority class and completely ignores the minority class will still be 98% correct. return synthetic.

Machine Learning 136

Machine Learning Metrics Data mining Knowledge Discovery 136

Domino Data Lab

AUGUST 1, 2021

Because of its architecture, intrinsically explainable ANNs can be optimised not just on its prediction performance, but also on its explainability metric. but it generally relies on measuring the entropy in the change of predictions given a perturbation of a feature. regression, multi-class classification etc.), See Wei et al.

Modeling 139

Modeling Deep Learning Machine Learning Knowledge Discovery 139

Alation

AUGUST 26, 2021

Data intelligence first emerged to support search & discovery, largely in service of analyst productivity. For years, analysts in enterprises had struggled to find the data they needed to build reports. This problem was only exacerbated by explosive growth in data collection and volume. HBR Review May/June 2017.

Metadata 64

Metadata Data Governance Dashboards Software 64