The Unofficial Google Data Science Blog

APRIL 17, 2017

Quantification of forecast uncertainty via simulation-based prediction intervals. We conclude with an example of our forecasting routine applied to publicly available Turkish Electricity data. Such a model risks conflating important aspects, notably the growth trend, with other less critical aspects.

Forecasting 83

Forecasting Modeling Statistics Uncertainty 83

The Unofficial Google Data Science Blog

DECEMBER 4, 2019

by THOMAS OLAVSON Thomas leads a team at Google called "Operations Data Science" that helps Google scale its infrastructure capacity optimally. This classification is based on the purpose, horizon, update frequency and uncertainty of the forecast. Our team does a lot of forecasting.

Forecasting 113

Forecasting Data Science Statistics Uncertainty 113

Insight

FEBRUARY 19, 2020

Using variability in machine learning predictions as a proxy for risk can help studio executives and producers decide whether or not to green light a film project Photo by Kyle Smith on Unsplash Originally posted on Toward Data Science. and even set their risk tolerance. Input page for ReelRisk.

Risk 67

Risk ROI Modeling Metrics 67

Domino Data Lab

JUNE 2, 2019

Co-chair Paco Nathan provides highlights of Rev 2 , a data science leaders summit. We held Rev 2 May 23-24 in NYC, as the place where “data science leaders and their teams come to learn from each other.” If you lead a data science team/org, DM me and I’ll send you an invite to data-head.slack.com ”.

Data-driven 110

Data-driven Data Science Machine Learning Modeling 110

The Unofficial Google Data Science Blog

JULY 22, 2020

One reason to do ramp-up is to mitigate the risk of never before seen arms. A ramp-up strategy may mitigate the risk of upsetting the site’s loyal users who perhaps have strong preferences for the current statistics that are shown. For example, imagine a fantasy football site is considering displaying advanced player statistics.

Experimentation 95

Experimentation Statistics Testing Strategy 95

The Unofficial Google Data Science Blog

AUGUST 27, 2019

The measurement may be biased if our samples are generated from a procedure that samples without replacement, such as reservoir sampling , especially if some items have disproportionate weight, i.e., $p(v_i) cdot n$ is large. High Risk 10% 5% 33.3% Whether or not we borrow strength from other scores also impacts the estimation.

Metrics 98

Metrics Statistics Uncertainty Optimization 98

Peter James Thomas

AUGUST 12, 2018

This piece was prompted by both Olaf’s question and a recent article by my friend Neil Raden on his Silicon Angle blog, Performance management: Can you really manage what you measure? Data may be perfectly valid, but still not represent reality. It is hard to account for such tweaking in measurement systems.

Metrics 49

Metrics Statistics Data Quality Measurement 49

Domino Data Lab

JUNE 23, 2019

These measurement-obsessed companies have an advantage when it comes to AI. Google, Facebook, other leaders, they really have set up a culture of extreme measurement where every part of their product experience is instrumented to optimize clicks and drive user engagement. They have the foundations of data infrastructure.

Management 110

Management Machine Learning Experimentation Metrics 110

The Unofficial Google Data Science Blog

MAY 31, 2016

It is important that we can measure the effect of these offline conversions as well. Panel studies make it possible to measure user behavior along with the exposure to ads and other online elements. Wouldn't it be great if we didn't require individual data to estimate an aggregate effect? days or weeks).

Advertising 42

Advertising Testing Sales Statistics 42