operations research and optimization www.amazon.science
An application of causal bandit to content optimization - Amazon Science
Amazon encompasses a large number of discrete businesses such as Retail, Advertising, Fresh, Business (B2B e-commerce), and Prime Video, most of which maintain a presence across its e-commerce website. They produce content for our customers that belong to diverse content types such as merchandising…
ColdGuess: A general and effective relational graph convolutional network to tackle cold start cases - Amazon Science
Low-quality listings and bad actor behavior in online retail websites threatens e-commerce business as these result in sub-optimal buying experience and erode customer trust. When a new listing is created, how to tell it has good quality? Is the method effective, fast, and scalable? Previous…
Adaptive experimental design and counterfactual inference - Amazon Science
Adaptive experimental design methods are increasingly being used in industry as a tool to boost testing throughput or reduce experimentation cost relative to traditional A/B/N testing methods. This paper shares lessons learned regarding the challenges and pitfalls of naively using adaptive…
News and features - Amazon Science
Discover the latest news about scientific innovation at Amazon. Find articles from scientists and researchers about artificial intelligence, machine learning, and more.
Search & Information Retrieval | Research Areas - Amazon Science
Developing advanced techniques to analyze behavioral patterns, lexical matches, and semantic matches to surface the most relevant recommendations in response to your queries.
Awards and recognitions - Amazon Science
Learn about the ways Amazon’s scientists and researchers are being recognized around the world.
Amazon Research Awards (ARA) - Amazon Science
Amazon Research Awards was founded in 2015 and merged with AWS Machine Learning Research Awards (MLRA) in 2020. The ARA program oﬀers unrestricted cash awards and AWS Promotional Credits to fund research at academic institutions and non-profit organizations in areas that align with our mission to advance customer-obsessed science.
Sustainability | Research Areas - Amazon Science
Taking a broad, science-based approach to reach net zero carbon by 2040.
Security, Privacy & Abuse Prevention | Research Areas - Amazon Science
Creating a secure suite of hardware, software, and services with privacy, while giving you control over your information.
Robotics | Research Areas - Amazon Science
Delivering a more convenient and consistent customer experience through a variety of technologies, including autonomous mobile robots, sophisticated control software, language perception, power management, computer vision, depth sensing, machine learning, object recognition, and semantic understanding of commands.
Automated Reasoning | Research Areas - Amazon Science
Focusing on the automation of formal logical reasoning to raise the bar on the security, durability, availability, and quality of Amazon’s products and services.
Information & Knowledge Management | Research Areas - Amazon Science
Developing machine learning techniques to enrich product-related information from Amazon detail pages and the Internet at large.
Quantum Technologies | Research Areas - Amazon Science
By harnessing the laws of quantum physics, quantum computers have the potential to solve problems that are beyond the reach of today's computers.
Research areas - Amazon Science
Science at Amazon enables new customer experiences and addresses existing customer challenges whenever there is limited or no existing prior art. It complements the company’s engineering and product disciplines, and is critical to all Amazon businesses focused on delivering increased customer value.
Economics | Research Areas - Amazon Science
Developing sophisticated approaches and systems to deliver the broadest selection of products and services at the lowest prices.
Operations Research & Optimization | Research Areas - Amazon Science
Streamlining operations to deliver orders to you faster, more conveniently, and more economically.
Conversational AI & Natural-Language Processing | Research Areas - Amazon Science
Building software and systems that help people communicate with computers naturally, as if communicating with family and friends.
Cloud & Systems | Research Areas - Amazon Science
Developing new technologies that offer increased computing power, expanded database storage, faster content delivery, and other capabilities.
Computer Vision | Research Areas - Amazon Science
Helping devices see and understand our visual world.
Machine Learning | Research Areas - Amazon Science
Developing algorithms and statistical models that computer systems use to perform tasks without explicit instructions, relying on patterns and inference instead.
Automatically optimizing execution of dynamic tensor operations - Amazon Science
New auto-scheduler speeds optimization process sixfold while improving performance of resulting code up to 70%.
Ozge Sahin on the art and science of studying consumer behavior - Amazon Science
The Johns Hopkins business school professor and Amazon Scholar focuses on enhancing customer experiences.
KDD: Graph neural networks, fairness, and inclusivity - Amazon Science
The general chair of this year’s Conference on Knowledge Discovery and Data Mining on what excites him most about the conference program.
National Science Foundation and Amazon announce latest Fairness in AI grant projects - Amazon Science
Thirteen new projects focus on ensuring fairness in AI algorithms and the systems that incorporate them.
A hyperparameter optimization library for reproducible research - Amazon Science
Syne Tune supports multiple backends, single-fidelity and multi-fidelity (early-exit) optimization algorithms, and hyperparameter transfer learning.