Building Uber’s Fulfillment Platform for Planet-Scale using Google Cloud Spanner
You’re seeing information for Japan . To see local features and services for another location, select a different city. Show more Introduction The Fulfillment Platform is a foundational Uber domain that enables the rapid scaling of new verticals. The platform handles billions of database transactions each day, ranging from user actions (e.g., a driver starting a trip) and system actions (e.g., cre
Uber徹底研究 -MaaSを支えるデータサイエンス編-｜Tack
今回はUberが使用する高度な手法について紹介します。紹介するのは以下の5つですが、レコメンドに関しては次回に回します。今回からは少し専門的な内容になります。 ・需要予測 ・配車最適化 ・ダイナミックプライシング ・解約予測 ・レコメンド(ボリュームが多いので、次回説明) 本記事は連載4回目の投稿ですが、これまでの投稿は以下の通りです。 ・Uber徹底研究 -ビジネス概要編- ・Uber徹底研究 -UX改善編- ・Uber徹底研究 -ゲーミフィケーション・行動科学編- Uberのサービスは、まるで魔法を唱えてタクシーを召喚するかのように表現されますが、その魔法の裏にあるデータサイエンスを今回は紹介していきます。 ■需要予測昨今、様々な企業が需要予測を行っています。需要予測には、通常はいわゆる時系列モデル(ARIMA等)を活用した予測や、Xgboostやランダムフォレスト等の機械学習モデルを
ノーベル経済学賞でも注目の因果推論を俯瞰する｜Tack@データサイエンス
■2019年ノーベル経済学賞でも取り上げられたRCT2019年のノーベル経済学賞は ・アビジット・バナジー(MIT) ・エステール・デュフロ(MIT) ・マイケル・クレマー(ハーバード) の3名に授与されることになりました。 3人は貧困解消について理論よりも実践的な取り組みを優先し、数百万人の子どもを支援した功績が認められたとのことです。 また、ランダム化比較試験(RCT)という研究方法をいち早く開発経済学に応用し、漫然と教科書の提供や無料給食を実施しても効果が少ない一方、本当に手助けが必要な生徒に的を絞った支援をすると、全体の教育水準が大きく改善することなどをフィールドワークで突き止めた、とも記載されています。 https://www.newsweekjapan.jp/stories/world/2019/10/3-150.php 今回、注目されているRCTは、実証的根拠に基づく政策立案
Pyflame: Uber Engineering's Ptracing Profiler for Python
EngineeringPyflame: Uber Engineering’s Ptracing Profiler for PythonSeptember 27, 2016 / Global At Uber, we make an effort to write efficient backend services to keep our compute costs low. This becomes increasingly important as our business grows; seemingly small inefficiencies are greatly magnified at Uber’s scale. We’ve found flame graphs to be an effective tool for understanding the CPU and mem
GitHub - ludwig-ai/ludwig: Low-code framework for building custom LLMs, neural networks, and other AI models
Ludwig is a low-code framework for building custom AI models like LLMs and other deep neural networks. Key features: 🛠 Build custom models with ease: a declarative YAML configuration file is all you need to train a state-of-the-art LLM on your data. Support for multi-task and multi-modality learning. Comprehensive config validation detects invalid parameter combinations and prevents runtime failu
Introducing Athenadriver: An Open Source Amazon Athena Database Driver For Go
You’re seeing information for Japan . To see local features and services for another location, select a different city. Show more Data analytics play a critical part in Uber’s decision making, driving and shaping all aspects of the company, from improving our products to generating insights that inform our business. To ensure timely and accurate analytics, the aggregated, anonymous data that power
Designing a Production-Ready Kappa Architecture for Timely Data Stream Processing
Designing a Production-Ready Kappa Architecture for Timely Data Stream Processing At Uber, we use robust data processing systems such as Apache Flink and Apache Spark to power the streaming applications that helps us calculate up-to-date pricing, enhance driver dispatching, and fight fraud on our platform. Such solutions can process data at a massive scale in real time with exactly-once semantics,
Building Uber’s Go Monorepo with Bazel
You’re seeing information for Japan . To see local features and services for another location, select a different city. Show more In traditional industries such as automobile or aerospace, engineers first design the products and the manufacturing facilities produce the cars or aircrafts according to the design. In software development, a build system is similar to the manufacturing facilities that
Announcing a New Framework for Designing Optimal Experiments with Pyro
You’re seeing information for Japan . To see local features and services for another location, select a different city. Show more Experimentation is one of humanity’s principal tools for learning about our complex world. Advances in knowledge from medicine to psychology require a rigorous, iterative process in which we formulate hypotheses and test them by collecting and analyzing new evidence. At
Uber’s Data Platform in 2019: Transforming Information to Intelligence
You’re seeing information for Japan . To see local features and services for another location, select a different city. Show more Uber’s busy 2019 included our billionth delivery of an Uber Eats order, 24 million miles covered by bike and scooter riders on our platform, and trips to top destinations such as the Empire State Building, the Eiffel Tower, and the Golden Gate Bridge. Behind the scenes
GitHub - eugeneyan/applied-ml: 📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Curated papers, articles, and blogs on data science & machine learning in production. ⚙️ Figuring out how to implement your ML project? Learn how other organizations did it: How the problem is framed 🔎(e.g., personalization as recsys vs. search vs. sequences) What machine learning techniques worked ✅ (and sometimes, what didn't ❌) Why it works, the science behind it with research, literature, and
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
https://www.pinterestcareers.com/media/vv4bg1sj/prestoicde.pdf
YAML Generator for Funnel YAML Files: Streamlining the Mobile Data Workflow Process
GitHub - uber/orbit: A Python package for Bayesian forecasting with object-oriented design and probabilistic models under the hood.
Real world Python performance tuning
Editing Massive Geospatial Data Sets with nebula.gl
Monitoring Data Quality at Scale with Statistical Modeling
A Graph is a Graph is a Graph: Josh Shinavier at Data Day Texas / Global Graph Summit 2019
Joshua Shinavier – The Knowledge Graph Conference
Building an Enterprise Knowledge Graph at Uber: Lessons from Reality