Social
Vancouver, Canada
Machine learning

3 important themes from Amazon's 2019 NeurIPS papers

Time series forecasting, bandit problems, and optimization are integral to Amazon's efforts to deliver better value for its customers.

By Larry Hardesty
November 25, 2019
14 min read
Share

Last year, the first 2,000-2,500 publicly released tickets to the Conference on Neural Information Processing Systems, or NeurIPS, sold out in 12 minutes.

This year, the conference organizers moved to a lottery system, allowing aspiring attendees to register in advance and randomly selecting invitees from the pool of registrants. But they also bumped the number of public-release tickets up from around 2,000 to 3,500, testifying to the conference’s continued popularity.

At NeurIPS this year, there are 26 papers with Amazon coauthors. They cover a wide range of topics, but surveying their titles, Alex Smola, a vice president and distinguished scientist in the Amazon Web Services organization, discerns three prominent themes, all tied to Amazon’s efforts to deliver better value for its customers.

Those three themes are time series forecasting (and causality), bandit problems, and optimization.

1. Time series forecasting

Time series forecasting involves measuring some quantity over time — such as the number of deliveries in a particular region in the past six months, or the number of cloud servers required to support a particular site over the past two years — and attempting to project that quantity into the future.

“That’s something that is very dear to Amazon’s heart,” Smola says. “For anything that Amazon does, it’s really beneficial to have a good estimate of what our customers will expect from us ahead of time. Only by being able to do that will we be able to satisfy customers’ demands, be it for products or services.”

A sequence of basis time series, forecast into the near future and summed together to approximate a new time series.
The paper “Think Globally, Act Locally” examines data sets with many correlated time series, such as the demand curves for millions of products sold online. The researchers describe a method for constructing a much smaller set of “basis time series”; the time series for any given product can be approximated by a weighted sum of the bases.
Courtesy of the researchers

The basic mathematical framework for time series forecasting is a century old, but the scale of modern forecasting problems calls for new analytic techniques, Smola says.

“Problems are nowadays highly multivariate,” Smola says. “If you look at the many millions of products that we offer, you want to be able to predict fairly well what will sell, where and to whom.

“You need to make reasonable assumptions on how this very large problem can be decomposed into smaller, more tractable pieces. You make structural approximations, and sometimes those structural approximations are what leads to very different algorithms.

“So you might, for instance, have a global model, and then you have local models that address the specific items or address the specific sales. If you look at ‘Think Globally, Act Locally’” — a NeurIPS paper whose first author is Rajat Sen, an applied scientist in the Amazon Search group — “it’s already in the title. Or look at ‘High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes’. In this case, you have a global structure, but it’s only in a small subspace where interesting things happen.”

Side-by-side images depict correlations between taxi traffic at different points in Manhattan at different times of day
The paper "High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes" describes a method for predicting correlations among many parallel time series. In one example, the researchers forecast correlations between the taxi traffic at different points in New York City at different times of day. Red lines indicate strong correlations; blue lines indicate strong negative correlations. Weekend midday traffic patterns (left) show negative correlations between locations near the Empire State Building, suggesting that taxis tend to prefer different routes depending on traffic conditions. Weekend evening traffic patterns show positive correlations between the vicinity of the Empire State Building and areas with high concentrations of hotels.
Courtesy of the researchers

An aspect of forecasting that has recently been drawing more attention, Smola says, is causality. Where traditional machine learning models merely infer statistical correlations between data points, “it is ultimately the causal relationship that matters,” Smola says.

“I think that causality is one of the most interesting conceptual developments affecting modern machine learning,” says Bernhard Schölkopf, like Smola a vice president and distinguished scientist in Amazon Web Services. “This is the main topic that I have been interested in for the last decade.”

Two of Schölkopf’s NeurIPS papers — “Perceiving the Arrow of Time in Autoregressive Motion” and “Selecting Causal Brain Features with a Single Conditional Independence Test per Feature” — address questions of causality, as does “Causal Regularization”, a paper by Dominik Janzing, a senior research scientist in Smola’s group.

“Normal machine learning builds on correlations of other statistical dependences,” Schölkopf explains. “This is fine as long as the source of the data doesn't change. For example, if in the training set of an image recognition system, all cows are standing on green pasture, then it is fine for an ML system to use the green as a useful feature in recognizing cows, as long as the test set looks the same. If in the test set, the cows are standing on the beach, then such a purely statistical system can fail.

“More generally: causal learning and inference attempts to understand how systems respond to interventions and other changes, and not just how to predict data that looks more or less the same as the training data.”

2. Bandit problems

The second major theme that Smola discerns in Amazon scientists’ NeurIPS papers is a concern with bandit problems, a phrase that shows up in the titles of Amazon papers such as “MaxGap Bandit: Adaptive Algorithms for Approximate Ranking” and “Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing”. Bandit problems take their name from one-armed bandits, or slot machines.

“It used to be that those bandits were all mechanical, so there would be slight variations between them, and some would have maybe a slightly a higher return than others,” Smola explains. “I walk into a den of iniquity, and I want to find the one-armed bandit where I will lose the least money or maybe make some money. And the only feedback I have is that I pull arms, and I get money or lose money. These are very unreliable, noisy events.”

Bandit problems present what’s known as an explore-exploit trade-off. The gambler must simultaneously explore the environment — determine which machines pay out the most — and exploit the resulting knowledge — concentrate as much money as possible on the high-return machines. Early work on bandit problems concerned identifying the high-return machines with minimal outlays.

“That problem was solved about 20 years ago,” Smola says. “What hasn’t been solved — and this is where things get a lot more interesting — is once you start adding context. Imagine that I get to show you various results as you’re searching for your next ugly Christmas sweater. The unfortunate thing is that the creativity of sweater designers is larger than what you can fit on a page. Now the context is essentially, what time, where from, which user, all those things. We want to find and recommend the ugly Christmas sweater that works specifically for you. This is an example where context is immediately relevant.”

It’s really beneficial to have a good estimate of what our customers will expect from us ahead of time. Only by being able to do that will we be able to satisfy customers’ demands.
Alex Smola, VP and distinguished scientist, Amazon

In the bandit-problem framework, in other words, the high-payout machines change with every new interaction. But there may be external signals that indicate how they’re changing.

Distributed computing, which is inescapable for today’s large websites, changes the structure of the bandit problem, too.

“Say you go to a restaurant, and the cook wants to improve the menu,” Smola says. “You can try out lots of new menu items, and that’s a good way to improve the menu overall. But if you start offering a lot of undercooked dishes because you’re experimenting, then at some point your loyal customers will stay away.

“Now imagine you have 100 restaurants, and they all do the same thing at the same time. They can’t necessarily communicate at the per-second level; maybe every day or every week they chat with each other. Now this entire exploration problem becomes a little more challenging, because if two restaurants try out the same undercooked dish, you make the customer less happy than you could have.

“So how does this map back into Amazon land? Well, if you have many servers doing this recommendation, the explore-exploit trade-off might be too aggressive if every one of them works on their own.”

3. Optimization

Finally, Smola says, “There is a third category of results that has to do with making algorithms faster. If you look at ‘Primal-Dual Block Frank-Wolfe’, ‘Communication-Efficient Distributed SGD with Sketching’, ‘Qsparse-Local-SGD’ — those are the workhorses that run underneath all of this. Making them more efficient is obviously something that we care about, so we can respond to customer requests faster, train algorithms faster.”

Bird’s-eye view

NeurIPS is a huge conference, with more than 1,400 accepted papers that cover a bewildering variety of topics. Beyond the Amazon papers, Caltech professor and Amazon fellow Pietro Perona identifies three research areas as growing in popularity.

“One is understanding how deep networks work, so that we can better design architectures and optimization algorithms to train models,” Perona says. “Another is low-shot learning. Machines are still much less efficient than humans at learning, in that they need more training examples to achieve the same performance. And finally, AI and society — identifying opportunities for social good, sustainable development, and the like.”

NeurIPS is being held this year at the Vancouver Convention Center, and the main conference runs from Dec. 8 to Dec. 12. The Women in Machine Learning Workshop, for which Amazon is a gold-level sponsor, takes place on Dec. 9; the Third Conversational AI workshop, whose organizers include Alexa AI principal scientist Dilek Hakkani-Tür, will be held on Dec. 14.

Amazon's involvement at NeurIPS

Paper and presentation schedule

Tuesday, 12/10 | 10:45-12:45pm | East Exhibition Hall B&C

A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning | #192
Francisco Garcia (UMass Amherst/Amazon) · Philip Thomas (UMass Amherst)

Blocking Bandits | #17
Soumya Basu (UT Austin) · Rajat Sen (UT Austin/Amazon) · Sujay Sanghavi (UT Austin/Amazon) · Sanjay Shakkottai (UT Austin)

Causal Regularization | #180
Dominik Janzing (Amazon)

Communication-Efficient Distributed SGD with Sketching | #81
Nikita Ivkin (Amazon) · Daniel Rothchild (University of California, Berkeley) · Md Enayat Ullah (Johns Hopkins University) · Vladimir Braverman (Johns Hopkins University) · Ion Stoica (UC Berkeley) · Raman Arora (Johns Hopkins University)

Learning Distributions Generated by One-Layer ReLU Networks | #49
Shanshan Wu (UT Austin) ·Alexandros G. Dimakis (UT Austin) · Sujay Sanghavi (UT Austin/Amazon)

Tuesday, 12/10 | 5:30-7:30pm | East Exhibition Hall B&C

Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control | #195
Sai Qian Zhang (Harvard University) · Qi Zhang (Amazon) · Jieyu Lin (University of Toronto)

Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products | #37
Tharun Kumar Reddy Medini (Rice University) · Qixuan Huang (Rice University) · Yiqiu Wang (Massachusetts Institute of Technology) · Vijai Mohan (Amazon) · Anshumali Shrivastava (Rice University/Amazon)

Iterative Least Trimmed Squares for Mixed Linear Regression | #50
Yanyao Shen (UT Austin) · Sujay Sanghavi (UT Austin/Amazon)

Meta-Surrogate Benchmarking for Hyperparameter Optimization | #6
Aaron Klein (Amazon) · Zhenwen Dai (Spotify) · Frank Hutter (University of Freiburg) · Neil Lawrence (University of Cambridge) · Javier Gonzalez (Amazon)

Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations | #32
Debraj Basu (Adobe) · Deepesh Data (UCLA) · Can Karakus (Amazon) · Suhas Diggavi (UCLA)

Selecting Causal Brain Features with a Single Conditional Independence Test per Feature | #139
Atalanti Mastakouri (Max Planck Institute for Intelligent Systems) · Bernhard Schölkopf (MPI for Intelligent Systems/Amazon) · Dominik Janzing (Amazon)

Wednesday, 12/11 | 10:45-12:45pm | East Exhibition Hall B&C

On Single Source Robustness in Deep Fusion Models | #93
Taewan Kim (Amazon) · Joydeep Ghosh (UT Austin)

Perceiving the Arrow of Time in Autoregressive Motion | #155
Kristof Meding (University Tübingen) · Dominik Janzing (Amazon) · Bernhard Schölkopf (MPI for Intelligent Systems/Amazon) · Felix A. Wichmann (University of Tübingen)

Wednesday, 12/11 | 5:00-7:00pm | East Exhibition Hall B&C

Compositional De-Attention Networks | #127
Yi Tay (Nanyang Technological University) · Anh Tuan Luu (MIT) · Aston Zhang (Amazon) · Shuohang Wang (Singapore Management University) · Siu Cheung Hui (Nanyang Technological University)

Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing | #3
Jonas Mueller (Amazon) · Vasilis Syrgkanis (Microsoft Research) · Matt Taddy (Amazon)

MaxGap Bandit: Adaptive Algorithms for Approximate Ranking | #4
Sumeet Katariya (Amazon/University of Wisconsin-Madison) · Ardhendu Tripathy (UW Madison) · Robert Nowak (UW Madison)

Primal-Dual Block Generalized Frank-Wolfe | #165
Qi Lei (UT Austin) · Jiacheng Zhuo (UT Austin) · Constantine Caramanis (UT Austin) · Inderjit S Dhillon (Amazon/UT Austin) · Alexandros Dimakis (UT Austin)

Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling | #208
Tengyang Xie (University of Illinois at Urbana-Champaign) · Yifei Ma (Amazon) · Yu-Xiang Wang (UC Santa Barbara)

Thursday, 12/12 | 10:45-12:45pm | East Exhibition Hall B&C

AutoAssist: A Framework to Accelerate Training of Deep Neural Networks | #155
Jiong Zhang (UT Austin) · Hsiang-Fu Yu (Amazon) · Inderjit S Dhillon (UT Austin/Amazon)

Exponentially Convergent Stochastic k-PCA without Variance Reduction | #200 (oral, 10:05-10:20 W Ballroom C)
Cheng Tang (Amazon)

Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift | #54
Stephan Rabanser (Technical University of Munich/Amazon) · Stephan Günnemann (Technical University of Munich) · Zachary Lipton (Carnegie Mellon University/Amazon)

High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes | #107
David Salinas (Naverlabs) · Michael Bohlke-Schneider (Amazon) · Laurent Callot (Amazon) · Jan Gasthaus (Amazon) · Roberto Medico (Ghent University)

Learning Search Spaces for Bayesian Optimization: Another View of Hyperparameter Transfer Learning | #30
Valerio Perrone (Amazon) · Huibin Shen (Amazon) · Matthias Seeger (Amazon) · Cedric Archambeau (Amazon) · Rodolphe Jenatton (Amazon)

Mo’States Mo’Problems: Emergency Stop Mechanisms from Observation | #227
Samuel Ainsworth (University of Washington) · Matt Barnes (University of Washington) · Siddhartha Srinivasa (University of Washington/Amazon)

Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting | #113
Rajat Sen (Amazon) · Hsiang-Fu Yu (Amazon) · Inderjit S Dhillon (UT Austin/Amazon)

Thursday, 12/12 | 5:00-7:00pm | East Exhibition Hall B&C

Dynamic Local Regret for Non-Convex Online Forecasting | #20
Sergul Aydore (Stevens Institute of Technology) · Tianhao Zhu (Stevens Institute of Technology) · Dean Foster (Amazon)

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space | #47
Suo Yang (UT Austin), Yanyao Shen (UT Austin), Sujay Sanghavi (UT Austin/Amazon)

Inverting Deep Generative Models, One Layer at a Time |#48
Qi Lei (University of Texas at Austin) · Ajil Jalal (UT Austin) · Inderjit S Dhillon (UT Austin/Amazon) · Alexandros Dimakis (UT Austin)

Provable Non-linear Inductive Matrix Completion| #215
Kai Zhong (Amazon) · Zhao Song (UT Austin) · Prateek Jain (Microsoft Research) · Inderjit S Dhillon (UT Austin/Amazon)

Amazon researchers on NeurIPS committees and boards

  • Bernhard Schölkopf – Advisory Board
  • Michael I. Jordan – Advisory Board
  • Thorsten Joachims – senior area chair
  • Anshumali Shrivastava – area chair
  • Cedric Archambeau – area chair
  • Peter Gehler – area chair
  • Sujay Sanghavi – committee member

Workshops

Learning with Rich Experience: Integration of Learning Paradigms

Paper: "Meta-Q-Learning" | Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola

Human-Centric Machine Learning

Paper: "Learning Fair and Transferable Representations" | Luco Oneto, Michele Donini, Andreas Maurer, Massimiliano Pontil

Bayesian Deep Learning

Paper: "Online Bayesian Learning for E-Commerce Query Reformulation" | Gaurush Hiranandani, Sumeet Katariya, Nikhil Rao, Karthik Subbian

Meta-Learning

Paper: "Constrained Bayesian Optimization with Max-Value Entropy Search" | Valerio Perrone, Iaroslav Shcherbatyi, Rodolphe Jenatton, Cedric Archambeau, Matthias Seeger

Paper: "A Quantile-Based Approach to Hyperparameter Transfer Learning" | David Salinas, Huibin Shen, Valerio Perrone

Paper: "A Baseline for Few-Shot Image Classification" | Guneet Singh Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto

Conversational AI

Organizer: Dilek Hakkani-Tür

Paper: "The Eighth Dialog System Technology Challenge" | Seokhwan Kim, Michel Galley, Chulaka Gunasekara, Sungjin Lee, Adam Atkinson, Baolin Peng, Hannes Schulz, Jianfeng Gao, Jinchao Li, Mahmoud Adada, Minlie Huang, Luis Lastras, Jonathan K. Kummerfeld, Walter S. Lasecki, Chiori Hori, Anoop Cherian, Tim K. Marks, Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta

Paper: “Just Ask: An Interactive Learning Framework for Vision and Language Navigation” | Ta-Chung Chi, Minmin Shen, Mihail Eric, Seokhwan Kim, Dilek Hakkani-Tur

Paper: “MA-DST: Multi-Attention-Based Scalable Dialog State Tracking” | Adarsh Kumar, Peter Ku, Anuj Kumar Goyal, Angeliki Metallinou, Dilek Hakkani-Tür

Paper: “Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery” | Maryam Fazel-Zarandi, Longshaokan Wang, Aditya Tiwari, Spyros Matsoukas

Paper: “Towards Personalized Dialog Policies for Conversational Skill Discovery”| Maryam Fazel-Zarandi, Sampat Biswas, Ryan Summers, Ahmed Elmalt, Andy McCraw, Michael McPhillips, John Peach

Paper: “Conversation Quality Evaluation via User Satisfaction Estimation” | Praveen Kumar Bodigutla, Spyros Matsoukas, Lazaros Polymenakos

Paper: “Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering” | Li Zhou, Kevin Small

Science Meets Engineering of Deep Learning

Paper: "X-BERT: eXtreme Multi-label Text Classification using Bidirectional Encoder from Transformers" Wei-Cheng Chang, Hsiang-Fu Yu, Kai Zhong, Yiming Yang, Inderjit S. Dhillon

Machine Learning with Guarantees

Organizers: Ben London, Thorsten Joachims
Program Committee: Kevin Small, Shiva Kasiviswanathan, Ted Sandler

MLSys: Workshop on Systems for ML

Paper: "Block-Distributed Gradient Boosted Trees" | Theodore Vasiloudis, Hyunsu Cho, Henrik Boström

Women in Machine Learning

Gold sponsor: Amazon

Research areas
Tags
About the Author
Larry Hardesty
Larry Hardesty is the editor of the Amazon Science blog. Previously, he was a senior editor at MIT Technology Review and the computer science writer at the MIT News Office.

Related content

Work with us

See more jobs See more jobs
Applied Scientist, Amzn Shipping-Prd & Tech
IN, HR, Gurugram
Our customers have immense faith in our ability to deliver packages timely and as expected. A well planned network seamlessly scales to handle millions of package movements a day. It has monitoring mechanisms that detect failures before they even happen (such as predicting network congestion, operations breakdown), and perform proactive corrective actions. When failures do happen, it has inbuilt redundancies to mitigate impact (such as determine other routes or service providers that can handle the extra load), and avoids relying on single points of failure (service provider, node, or arc). Finally, it is cost optimal, so that customers can be passed the benefit from an efficiently set up network. Amazon Shipping is hiring Applied Scientists to help improve our ability to plan and execute package movements. As an Applied Scientist in Amazon Shipping, you will work on multiple challenging machine learning problems spread across a wide spectrum of business problems. You will build ML models to help our transportation cost auditing platforms effectively audit off-manifest (discrepancies between planned and actual shipping cost). You will build models to improve the quality of financial and planning data by accurately predicting ship cost at a package level. Your models will help forecast the packages required to be pick from shipper warehouses to reduce First Mile shipping cost. Using signals from within the transportation network (such as network load, and velocity of movements derived from package scan events) and outside (such as weather signals), you will build models that predict delivery delay for every package. These models will help improve buyer experience by triggering early corrective actions, and generating proactive customer notifications. Your role will require you to demonstrate Think Big and Invent and Simplify, by refining and translating Transportation domain-related business problems into one or more Machine Learning problems. You will use techniques from a wide array of machine learning paradigms, such as supervised, unsupervised, semi-supervised and reinforcement learning. Your model choices will include, but not be limited to, linear/logistic models, tree based models, deep learning models, ensemble models, and Q-learning models. You will use techniques such as LIME and SHAP to make your models interpretable for your customers. You will employ a family of reusable modelling solutions to ensure that your ML solution scales across multiple regions (such as North America, Europe, Asia) and package movement types (such as small parcel movements and truck movements). You will partner with Applied Scientists and Research Scientists from other teams in US and India working on related business domains. Your models are expected to be of production quality, and will be directly used in production services. You will work as part of a diverse data science and engineering team comprising of other Applied Scientists, Software Development Engineers and Business Intelligence Engineers. You will participate in the Amazon ML community by authoring scientific papers and submitting them to Machine Learning conferences. You will mentor Applied Scientists and Software Development Engineers having a strong interest in ML. You will also be called upon to provide ML consultation outside your team for other problem statements. If you are excited by this charter, come join us!
Data Scientist, SAMBA
US, NJ, Newark
At Audible, we believe stories have the power to transform lives. It’s why we work with some of the world’s leading creators to produce and share audio storytelling with our millions of global listeners. We are dreamers and inventors who come from a wide range of backgrounds and experiences to empower and inspire each other. Imagine your future with us. ABOUT THIS ROLE We are seeking a Data Scientist to own our causal inference infrastructure and drive sophisticated modeling that measures the incremental impact of business decisions. This role requires deep expertise in advanced causal inference methodologies—including synthetic control methods, Synthetic Difference-in-Differences (SDID), and Bayesian approaches—to design rigorous experiments, estimate long-term customer behavior effects, and translate complex analytical results into clear business recommendations. You will own the development and continuous improvement of these causal inference models while being responsible for machine learning operations at scale to ensure our organization makes data-driven decisions with confidence. At Audible, you will have an opportunity to make the best of your skillsets to both develop advanced scientific solutions and drive critical customer and business impact. You will play a key role to drive end-to-end solutions from understanding our business and business requirements, identifying opportunities from a large amount of historical data and engaging in research to solve the business problems. You'll seek to create value for both stakeholders and customers and inform findings in a clear, actionable way to managers and senior leaders. You will be at the heart of an agile and growing area at Audible. ABOUT THE TEAM Audible Data Scientists are members of a global interdisciplinary insights and research team with an integral role in the design and integration of models to automate decision making throughout the business in every country. We empower the machine learning and deep learning techniques in many areas of the business. We translate business goals into agile, insightful analytics and seek to create value for both stakeholders and customers and convey findings in a clear, actionable way to managers and senior leaders. As a Data Scientist, you will... - Design and execute geo-level randomized experiments to measure incremental impact - Apply statistical techniques to evaluate causal impact in quasi-experimental settings - Ensure experiments are statistically valid by evaluating sampling strategies, statistical power, and potential sources of bias - Develop models that estimate long-term effects from short-term experiments using machine learning - Estimate how changes in customer behavior persist and decay over time - Own and maintain the geo-testing codebase, including deployment and scalability - Implement machine learning models at scale with focus on performance optimization - Partner with stakeholders to ensure models align with real business dynamics - Engage deeply with business problems through curiosity-driven questioning and brainstorming - Translate experimental results into financial impact and investment recommendations - Analyze marginal and average revenue impacts relative to costs - Communicate complex quantitative ideas clearly to non-technical stakeholders - Demonstrate understanding of Audible's business model and customer experience ABOUT AUDIBLE Audible is the leading producer and provider of audio storytelling. We spark listeners’ imaginations, offering immersive, cinematic experiences full of inspiration and insight to enrich our customers daily lives. We are a global company with an entrepreneurial spirit. We are dreamers and inventors who are passionate about the positive impact Audible can make for our customers and our neighbors. This spirit courses throughout Audible, supporting a culture of creativity and inclusion built on our People Principles and our mission to build more equitable communities in the cities we call home.
Research Scientist, Modeling and Optimization (MOP)
US, WA, Bellevue
Do you enjoy solving challenging problems and driving innovations in research? Are you seeking for an environment with a group of motivated and talented scientists like yourself? Do you want to create scalable optimization models and apply machine learning techniques to guide real-world decisions? Do you want to play a key role in the future of Amazon transportation and operations? Come and join us at Amazon's Modeling and Optimization team (MOP). Key job responsibilities A Research Scientist in the Modeling and Optimization (MOP) team - provides analytical decision support to Amazon planning teams via applying advanced mathematical and statistical techniques. - collaborates effectively with Amazon internal business customers, and is their trusted partner - is proactive and autonomous in discovering and resolving business pain-points within a given scope - is able to identify a suitable level of sophistication in resolving the different business needs - is confident in leveraging existing solutions to new problems where appropriate and is independent in designing and implementing new solutions where needed - is aware of the limitations of their proposed solutions and is proactive in communicating them to the business, and advances the application of sciences towards Amazon business problems by bringing new methods, ideas, and practices to the team and scientific community. A day in the life - Your will be developing model-based optimization, simulation, and/or predictive tools to identify and evaluate opportunities to improve customer experience, network speed, cost, and efficiency of capital investment. - You will quantify the improvements resulting from the application of these tools and you will evaluate the trade-offs between potentially competing objectives. - You will develop good communication skills and ability to speak at a level appropriate for the audience, will collaborate effectively with fellow scientists, software development engineers, and product managers, and will deliver business value in a close partnership with many stakeholders from operations, finance, IT, and business leadership. About the team - At the Modeling and Optimization (MOP) team, we use mathematical optimization, algorithm design, statistics, and machine learning to improve decision-making capabilities across WW Operations and Amazon Logistics. - We focus on transportation topology, labor and resource planning for fulfillment facilities, routing science, visualization research, data science and development, and process optimization. - We create models to simulate, optimize, and control the fulfillment network with the objective of reducing cost while improving speed and reliability. - We support multiple business lanes, therefore maintain a comprehensive and objective view, coordinating solutions across organizational lines where possible.
Applied Scientist, Demand Forecasting
US, WA, Bellevue
What does it take to build a foundation model that can forecast demand for hundreds of millions of products — including ones that have never been sold before? At Amazon, our Demand Forecasting team is tackling one of the most ambitious challenges in applied time series research: designing and building large-scale foundation models that generalize across an enormous and diverse catalog of products, geographies, and business contexts. This is not incremental modeling work. We are redefining what's possible in demand forecasting through novel architectures, training strategies, and data generation techniques. Our team operates at a scale that is unmatched in industry or academia. You'll design experiments across millions of products simultaneously, developing new model architectures and training methodologies that push the boundaries of what foundation models can learn from vast, heterogeneous time series data. You'll explore techniques in transfer learning, zero-shot forecasting, and synthetic data generation. The models you design here will ship to production and directly influence hundreds of millions of dollars in automated inventory decisions every week. Beyond operational impact, you'll publish your work at top-tier conferences and contribute to advancing the state of the art in time series foundation models for the broader scientific community. If you are a scientist who wants to work at the frontier of time series research, design novel solutions to problems no one else has solved at this scale, and see your research deployed to real-world impact — this is the team for you. Key job responsibilities 1. Design and implement novel deep learning architectures (e.g., Transformers, SSMs, or Graph Neural Networks) for time-series foundation models that generalize across hundreds of millions of products and diverse global contexts. 2. Drive the full development cycle - from whiteboarding new algorithmic approaches to overseeing production-scale deployments. 3. Collaborate with SDEs to build high-performance, distributed training and inference pipelines; translate complex scientific concepts into scalable, production-grade code in Python and Scala. 4. Leverage and develop agentic GenAI workflows to automate the end-to-end research cycle from synthesizing state-of-the-art literature and auto-generating experimental code to rapidly iterating on model architectures across millions of products. 5. Maintain a high bar for scientific excellence by publishing novel research in top-tier venues (e.g., NeurIPS, ICLR, KDD) and contributing to Amazon’s internal patent and science community. A day in the life No two days look the same, but most will involve a high-velocity blend of deep architectural work, distributed system design, and frontier scientific thinking at a scale you won’t find anywhere else. You might start the morning by designing a synthetic data pipeline to stress-test your foundation model. You’ll use generative techniques to simulate rare "black swan" supply chain events, ensuring your model remains robust where historical data is thin. You'll then lead a Scientific Design Review, walking senior leaders through your model’s architecture, defending your choice of loss functions with data-driven rigor. You’ll write high-performance code often paired with AI-coding assistants to handle the heavy lifting of boilerplate and unit testing. You’ll collaborate across a "Two-Pizza Team" of scientists and engineers, pushing the boundaries of research with a clear goal: contributing to work that will be published at top-tier venues (ICLR, NeurIPS) while simultaneously driving multi-million dollar automated decisions. The work is hard, the math is complex, and the tools are state-of-the-art. If you want to build the models that actually ship—this is where you do it. About the team The Demand Forecasting team sits at the heart of Amazon's supply chain, building the science that determines what products are available, when, and at what cost — for hundreds of millions of customers around the world. Our mission is to push the frontier of what's possible in large-scale time series forecasting, and to deploy that science where it creates real, measurable impact. We are a team of scientists who care deeply about both research rigor and real-world outcomes. We don't just publish — we ship. And we don't just ship — we measure, iterate, and raise the bar. Our work spans the full lifecycle: from foundational research and large-scale experimentation to production deployment and downstream impact measurement across supply chain, inventory, and financial planning.
Member of Technical Staff - Applied Science , AGI Autonomy Lab
US, CA, San Francisco
Amazon has launched a new research lab in San Francisco to develop foundational capabilities for useful AI agents. We’re enabling practical AI to make our customers more productive, empowered, and fulfilled. Our work leverages large vision language models (VLMs) with reinforcement learning (RL) and world modeling to solve perception, reasoning, and planning to build useful enterprise agents. Our lab is a small, talent-dense team with the resources and scale of Amazon. Each team in the lab has the autonomy to move fast and the long-term commitment to pursue high-risk, high-payoff research. We’re entering an exciting new era where agents can redefine what AI makes possible. Key job responsibilities You will contribute directly to AI agent development in an applied research role to improve the multi-model perception and visual-reasoning abilities of our agent. Daily responsibilities including model training, dataset design, and pre- and post-training optimization. You will be hired as a Member of Technical Staff.
Data Scientist II, Amazon Stores Finance Science
US, WA, Seattle
WW Amazon Stores Finance Science (ASFS) works to leverage science and economics to drive improved financial results, foster data backed decisions, and embed science within Finance. ASFS is focused on developing products that empower controllership, improve business decisions and financial planning by understanding financial drivers, and innovate science capabilities for efficiency and scale. We are looking for a data scientist to lead high visibility initiatives for forecasting Amazon Stores' financials. You will develop new science-based forecasting methodologies and build scalable models to improve financial decision making and planning for senior leadership up to VP and SVP level. You will build new ML and statistical models from the ground up that aim to transform financial planning for Amazon Stores. We prize creative problem solvers with the ability to draw on an expansive methodological toolkit to transform financial decision-making with science. The ideal candidate combines data-science acumen with strong business judgment. You have versatile modeling skills and are comfortable owning and extracting insights from data. You are excited to learn from and alongside seasoned scientists, engineers, and business leaders. You are an excellent communicator and effectively translate technical findings into business action. Key job responsibilities Demonstrating thorough technical knowledge, effective exploratory data analysis, and model building using industry standard ML models Working with technical and non-technical stakeholders across every step of science project life cycle Collaborating with finance, product, data engineering, and software engineering teams to create production implementations for large-scale ML models Innovating by adapting new modeling techniques and procedures Presenting research results to our internal research community
Senior Applied Scientist, People eXperience & Technology Central Science (PXTCS)
US, WA, Seattle
Are you motivated to explore research in ambiguous spaces? Are you interested in conducting research that will improve the employee and manager experience at Amazon? Do you want to work on an interdisciplinary team of scientists that collaborate rather than compete? Join us at PXT Central Science! The People eXperience and Technology Central Science Team (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, wellbeing, and the value of work to Amazonians. We are an interdisciplinary team that combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. We are seeking a senior Applied Scientist with expertise in more than one or more of the following areas: machine learning, natural language processing, computational linguistics, algorithmic fairness, statistical inference, causal modeling, reinforcement learning, Bayesian methods, predictive analytics, decision theory, recommender systems, deep learning, time series modeling. In this role, you will lead and support research efforts within all aspects of the employee lifecycle: from candidate identification to recruiting, to onboarding and talent management, to leadership and development, to finally retention and brand advocacy upon exit. The ideal candidate should have strong problem-solving skills, excellent business acumen, the ability to work independently and collaboratively, and have an expertise in both science and engineering. The ideal candidate is not methods-driven, but driven by the research question at hand; in other words, they will select the appropriate method for the problem, rather than searching for questions to answer with a preferred method. The candidate will need to navigate complex and ambiguous business challenges by asking the right questions, understanding what methodologies to employ, and communicating results to multiple audiences (e.g., technical peers, functional teams, business leaders). About the team We are a collegial and multidisciplinary team of researchers in People eXperience and Technology (PXT) that combines the talents of science and engineering to develop innovative solutions to make Amazon Earth's Best Employer. We leverage data and rigorous analysis to help Amazon attract, retain, and develop one of the world’s largest and most talented workforces.
Data Scientist, Digital Acceleration
IN, TN, Chennai
Are you excited about the digital media revolution and passionate about designing and delivering advanced analytics that directly influence the product decisions of Amazon's digital businesses. Do you see yourself as a champion of innovating on behalf of the customer by turning data insights into action? The Amazon Digital Acceleration Analytics team is looking for an analytical and technically skilled individual to join our team. In this role, you will invent, build and deploy state of the art machine-learning models and systems to enable and enhance the team's mission This role offers wide scope, autonomy, and ownership. You will work closely with software engineers & data engineers to put algorithms into practice. You should have strong business judgement, excellent written and verbal communication skills. The candidate should be willing to take on challenging initiatives and be capable of working both independently and with others as a team. Key job responsibilities We are looking for an experienced data scientist with strong foundations in mathematics, statistics & machine learning with exceptional communication and leadership skills, and a proven track record of delivery. In this role, You will Define a long-term science vision and roadmap for the team, driven fundamentally from our customers' needs, translating those directions into specific plans for engineering teams. Design and execute machine learning projects/products end-to-end: from ideation, analysis, prototyping, development, metrics, and monitoring. Drive end-to-end statistical analysis that have a high degree of ambiguity, scale, and complexity. Research and develop advanced Generative AI based solutions to solve diverse customer problems. About the team The MIDAS team operates within Amazon's Digital Analytics (DA) engineering organization, building analytics and data engineering solutions that support cross-digital teams. Our platform delivers a wide range of capabilities, including metadata discovery, data lineage, customer segmentation, compliance automation, AI-driven data access through generative AI and LLMs, and advanced data quality monitoring. Today, more than 100 Amazon business and technology teams rely on MIDAS, with over 20,000 monthly active users leveraging our mission-critical tools to drive data-driven decisions at Amazon scale.
Applied Scientist, AI Automation, Prime Video
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video technologist, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! We are forming a new organization within Prime Video to redefine our operational landscape through the power of artificial intelligence. As a Applied Scientist within this initiative, you will be a technical leader helping to design and build the intelligent systems that power our vision. You will tackle complex and ambiguous problems, designing and delivering scalable and resilient agentic AI and ML solutions from the ground up. You will not only write high-quality, maintainable software and models, but also mentor other scientists, influence our technical strategy, and drive engineering best practices across the team. Your work will directly contribute to making Prime Video's operations more efficient and will set the technical foundation for years to come. We're seeking candidates with strong experience in computer vision and generative AI technologies. In this role, you'll apply cutting-edge techniques in image and video understanding, visual content generation, and multimodal AI systems to transform how Prime Video operates at scale. Key job responsibilities • Lead the design and architecture of highly scalable, available, and resilient services for our AI automation platform. • Write high-quality, maintainable, and robust code to solve complex business problems, building flexible systems without over-engineering. • Act as a technical leader and mentor for other engineers on the team, assisting with career growth and encouraging excellence. • Work through ambiguous requirements, cut through complexity, and translate business needs into scalable technical solutions. • Take ownership of the full software development lifecycle, including design, testing, deployment, and operations. • Work closely with product managers, scientists, and other engineers to build and launch new features and systems. About the team This role offers a unique opportunity to shape the future of one of Amazon's most exciting businesses through the application of AI technologies. If you're passionate about leveraging AI to drive real-world impact at massive scale, we want to hear from you.
Applied Scientist, Frontier AI & Robotics (FAR)
US, CA, San Francisco
Join the next revolution in robotics at Amazon's Frontier AI & Robotics team, where you'll work alongside world-renowned AI pioneers to push the boundaries of what's possible in robotic intelligence. As an Applied Scientist, you'll be at the forefront of developing breakthrough foundation models that enable robots to perceive, understand, and interact with the world in unprecedented ways. You'll drive independent research initiatives in areas such as perception, manipulation, science understanding, locomotion, manipulation, sim2real transfer, multi-modal foundation models and multi-task robot learning, designing novel frameworks that bridge the gap between state-of-the-art research and real-world deployment at Amazon scale. In this role, you'll balance innovative technical exploration with practical implementation, collaborating with platform teams to ensure your models and algorithms perform robustly in dynamic real-world environments. You'll have access to Amazon's vast computational resources, enabling you to tackle ambitious problems in areas like very large multi-modal robotic foundation models and efficient, promptable model architectures that can scale across diverse robotic applications. Key job responsibilities - Drive independent research initiatives across the robotics stack, including robotics foundation models, focusing on breakthrough approaches in perception, and manipulation, for example open-vocabulary panoptic scene understanding, scaling up multi-modal LLMs, sim2real/real2sim techniques, end-to-end vision-language-action models, efficient model inference, video tokenization - Design and implement novel deep learning architectures that push the boundaries of what robots can understand and accomplish - Lead full-stack robotics projects from conceptualization through deployment, taking a system-level approach that integrates hardware considerations with algorithmic development, ensuring robust performance in production environments - Collaborate with platform and hardware teams to ensure seamless integration across the entire robotics stack, optimizing and scaling models for real-world applications - Contribute to the team's technical strategy and help shape our approach to next-generation robotics challenges A day in the life - Design and implement novel foundation model architectures and innovative systems and algorithms, leveraging our extensive infrastructure to prototype and evaluate at scale - Collaborate with our world-class research team to solve complex technical challenges - Lead technical initiatives from conception to deployment, working closely with robotics engineers to integrate your solutions into production systems - Participate in technical discussions and brainstorming sessions with team leaders and fellow scientists - Leverage our massive compute cluster and extensive robotics infrastructure to rapidly prototype and validate new ideas - Transform theoretical insights into practical solutions that can handle the complexities of real-world robotics applications About the team At Frontier AI & Robotics, we're not just advancing robotics – we're reimagining it from the ground up. Our team is building the future of intelligent robotics through innovative foundation models and end-to-end learned systems. We tackle some of the most challenging problems in AI and robotics, from developing sophisticated perception systems to creating adaptive manipulation strategies that work in complex, real-world scenarios. What sets us apart is our unique combination of ambitious research vision and practical impact. We leverage Amazon's massive computational infrastructure and rich real-world datasets to train and deploy state-of-the-art foundation models. Our work spans the full spectrum of robotics intelligence – from multimodal perception using images, videos, and sensor data, to sophisticated manipulation strategies that can handle diverse real-world scenarios. We're building systems that don't just work in the lab, but scale to meet the demands of Amazon's global operations. Join us if you're excited about pushing the boundaries of what's possible in robotics, working with world-class researchers, and seeing your innovations deployed at unprecedented scale.
See more jobs
View from space of a connected network around planet Earth representing the Internet of Things.
Get more from Amazon Science
Subscribe to our monthly newsletter

Amazon.com | Conditions of Use | Privacy | © 1996-2026 Amazon.com, Inc. or its affiliates

Social