Animation shows a map of the United States and each of the 8 individual regions that resulted from Amazon's regionalization effort
Amazon's regionalization plan, which resulted in the eight regions seen here, has already proven successful: The percentage of customer orders being fulfilled entirely from FCs within each region has jumped to 76% — and is expected to continue to climb.

Sizing down to scale up: How Amazon reworked its fulfillment network to meet customer demand

The pandemic turbo-charged retail growth — teams of scientists at Amazon forged a path forward to handle the scale.

In 2020, Amazon’s retail fulfillment network in the U.S. expanded at a rapid clip. What followed was a dramatic — and swift — operational pivot.

This is the story of how Amazon’s national network of U.S. fulfillment centers (FCs), intermediate sorting centers, “last mile” delivery hubs, and transportation fleet were successfully restructured into eight largely self-sufficient regional networks, while retaining national coverage. The transformation was dubbed “regionalization.”

Operations research at Amazon
How Amazon’s scientists developed a first-of-its-kind multi-echelon system for inventory buying and placement.

The COVID pandemic was a key factor in two ways. Due to lockdowns or otherwise, people were staying home and ordering more online than ever before.

“Our focus moved from trying to figure out how to make customer deliveries as fast as possible to trying to meet exceptional customer demand by pushing as much volume as we could through our network,” says Adam Baker, Amazon’s vice president of global transportation.

It was in late 2020 that a long-term planning science team led by research director Amitabh Sinha sent up a warning flare: the fast-growing network risked becoming overcomplicated and unwieldy.

“We projected our scenario out to three or four years and took this to Amazon’s leadership with an idea of how to do things differently,” he says. That idea contained the seed that would grow into regionalization.

Joining the dots

The crux of the issue was that Amazon was trying to connect too many physical dots. Its fulfillment infrastructure made sense when it had fewer FCs, because it meant customers across the U.S. could tap into Amazon’s full product range. And with fewer FCs, the trucks carrying the products across the country were fuller, so it was cost-effective.

As the number of FCs and other fulfillment buildings in the U.S. rose sharply, that approach started to look like it might not be the right long-term path. “We would fulfill customer orders from the FCs near them until we couldn’t anymore, and then — okay, it's coming from wherever we still have capacity,” says Russell Allgor, Amazon’s chief scientist for worldwide operations. That “wherever” was the problem.

Operations research at Amazon
The SCOT science team used lessons from the past — and improved existing tools — to contend with “a peak that lasted two years”.

It meant each of Amazon’s FCs was serving not only its locality, but also customer locations all over the U.S. To illustrate the problem, imagine you had to deliver 10,000 products nationwide, quickly, to 100 distant locations, from 10 FCs across the country. You could have each FC dispatch 100 trucks, each carrying 10 items, to each of the locations. That’s 1,000 long-haul trucks and a lot of rubber on the road — clearly an unsustainable idea on all fronts.

Now imagine that you could partition the 100 customer locations into 10 regions of 10 locations apiece, with each region served by a dedicated FC. In this scenario, each region’s FC can dispatch 10 trucks, each carrying 100 packages a piece. That would require just 100 trucks nationwide, driving much shorter distances. That’s faster for customers and more sustainable: a win-win situation. That’s regionalization in a nutshell, and by mid-2021, Amazon threw its full weight behind the idea.

Picking the number

For about a year, Sinha and his team used state-of-the-art network-optimization tools to model and simulate the many potential ways customer orders might flow through a regionalized system, and what effect different configurations would have on delivery speeds and transport costs. There was an enormous number of potential scenarios to explore.

Operations research at Amazon
How the Amazon Logistics Research Science team guides important decisions related to last-mile delivery.

“We were dealing with millions of variables and constraints, and a lot of uncertainty,” says Cristiana Lara, a senior research scientist who worked on estimating the financial impacts of the initiative. “That’s not surprising, because we were completely shifting the paradigm of how we fulfill customer orders.”

A critical early question was how many regions to form. The smaller the regions, the faster the customer deliveries, because Amazon’s inventory would be closer to customers. “In addition to speedy deliveries, the crucial thing was that each region must carry the breadth of selection that customers expect” says Sinha.

The ambitious aim? To have a high proportion of the tens of millions of products offered in the store available to customers within each region, with the rest shipped from further afield only when needed.

Amazon's regionalization map, with 8 regions overlaid over a map of the United States, is seen here
A critical piece of regionalization was using the insights to map out more efficient, shorter routes for orders. As soon as a customer clicks the "buy now" button, Amazon's Adaptive TRansportation OPtimization Service (ATROPS) assigns the optimal route for the purchased item.

With this goal in mind, the collaborators alighted on the number: eight regions. That was as high as they could go without sacrificing speed or requiring excessive inter-regional movement of inventory to meet customer orders, which would defeat the purpose of the exercise.

“We ran extensive, fine-grained analysis for pretty much the entirety of 2022, examining in turn the different aspects of how it would all work,” says Sinha, whose team worked closely with Amazon’s Global Transportation Service (GTS) – which designs, plans, and executes the Amazon Transportation network.

Before long, a timeline was put in place. Come January 18, 2023, the newly minted Northeast and Mid-Atlantic Amazon regions would pioneer this new fulfillment pattern, with the other six regions slated to follow thereafter.

Flipping the switch

A critical piece of regionalization was using the insights supplied to map out more efficient, shorter routes for orders. As soon as a customer clicks the "buy now" button, Amazon's Adaptive TRansportation OPtimization Service (ATROPS) assigns the optimal route for the purchased item. The transportation team devoted the latter part of 2022 to overhauling and testing a completely new set of ATROPS routes designed specifically for this regionalization plan.

Operations research at Amazon
INFORMS talk explores techniques Amazon’s Supply Chain Optimization Technologies organization is testing to fulfill customer orders more efficiently.

On January 18, with the 2022 holiday rush safely in the rearview mirror, it was time to make the leap. The transportation team had contingency plans in place, and colleagues in different global time zones were standing by to offer around-the-clock support if something went wrong.

“We flipped the switch overnight, and immediately started to see the results we were hoping for. It changed faster than any of us expected. It was delightful,” says Nick McCabe, senior manager of GTS network design.

“We had some minor concerns to work through,” Baker adds, “but our delivery speed instantly picked up and our customers saw the benefit in their orders right away.”

Overall, the transition went so well, Amazon brought forward the complete activation of the other regions by a full month.

Rapid results

Regionalization is working. Before the switch, the percentage of customer orders being fulfilled entirely from FCs within what would become each region was 62%. That figure has already surged to 76% — a stunning efficiency gain — and is expected to continue to climb.

Delivery speeds have also picked up, says Sinha, because more goods are travelling shorter distances. And this effect will only strengthen as regionalization continues to take root.

Another quick success of regionalization was how much fuller a subset of Amazon’s trucks has become. Most customer orders leave an FC and are transported to a sorting center, which receives and consolidates customer orders, filling up the trucks that take them to delivery stations for the “last mile” of their journey. Sometimes, for logistical reasons, FCs send trucks directly to delivery stations. Post-regionalization, because there are fewer FCs shipping more packages to each destination, there is greater opportunity to operate these FC-to-delivery station direct trucks, resulting in more efficient delivery routes.

“Suddenly, 70 to 80 per cent of the order volume is not coming from FCs scattered around the country, but from, say, 10 FCs inside the region, so trucks on these short-distance direct lanes are now showing a great fill rate,” says senior applied scientist Semih Atakan, who models how products flow between Amazon’s FCs and delivery stations.

Regionalization has also transformed how the wider national network is managed.

“Before, it was difficult to control the whole network because of our sheer number of trucking lanes,” says Baker. “It was like pushing on a giant spiderweb.” Post-regionalization, he says, that number of lanes reduced markedly, making it much easier to make choices about when and how much to ship between regions.

Scanning the horizon

And this is just the beginning, says research scientist Xiaoyan Si, who is modeling how the fulfillment network might evolve over the next three years.

“Eight regions is our starting point. As we move forward, we will have the opportunity create smaller geographic regions with as much demand per region as we have today,” says Si. “Using the data we have now, we can place future fulfillment buildings more strategically, and we are working with other researchers on the team to design new regions more scientifically.”

Smaller regions will enable Amazon to deliver even faster to customers, while making each region even more efficient in terms of distance travelled, inventory management and truck fill.

Amazon’s Day One culture places great value on horizon scanning, innovation, and risk-taking to deliver customer benefits. The regionalization initiative that sprang from this mindset is a testament not only to the vision and enormous team effort required to pull it off, but also to the flexibility of Amazon’s infrastructure.

Because despite being Amazon’s biggest operational transformation in a decade, it was completely reversible had it misfired. After all, says Si, in what might be the understatement of the year: “When you boil it right down, regionalization is just a software setting.”

Related content

IN, KA, Bengaluru
Do you want to join an innovative team of scientists who use machine learning and statistical techniques to create state-of-the-art solutions for providing better value to Amazon’s customers? Do you want to build and deploy advanced algorithmic systems that help optimize millions of transactions every day? Are you excited by the prospect of analyzing and modeling terabytes of data to solve real world problems? Do you like to own end-to-end business problems/metrics and directly impact the profitability of the company? Do you like to innovate and simplify? If yes, then you may be a great fit to join the Machine Learning and Data Sciences team for India Consumer Businesses. If you have an entrepreneurial spirit, know how to deliver, love to work with data, are deeply technical, highly innovative and long for the opportunity to build solutions to challenging problems that directly impact the company's bottom-line, we want to talk to you. Major responsibilities - Use machine learning and analytical techniques to create scalable solutions for business problems - Analyze and extract relevant information from large amounts of Amazon’s historical business data to help automate and optimize key processes - Design, development, evaluate and deploy innovative and highly scalable models for predictive learning - Research and implement novel machine learning and statistical approaches - Work closely with software engineering teams to drive real-time model implementations and new feature creations - Work closely with business owners and operations staff to optimize various business operations - Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation - Mentor other scientists and engineers in the use of ML techniques
US, MA, Boston
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Applied Scientist with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Applied Scientist with the AGI team, you will work with talented peers to lead the development of novel algorithms and modeling techniques, to advance the state of the art with LLMs. Your work will directly impact our customers in the form of products and services that make use of speech and language technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in spoken language understanding. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, WA, Seattle
The Global Cross-Channel and Cross- Category Marketing (XCM) org are seeking an experienced Economist to join our team. XCM’s mission is to be the most measurably effective and creatively breakthrough marketing organization in the world in order to strengthen the brand, grow the business, and reduce cost for Amazon overall. We achieve this through scaled campaigning in support of brands, categories, and audiences which aim to create the maximum incremental impact for Amazon as a whole by driving the Amazon flywheel. This is a high impact role with the opportunities to lead the development of state-of-the-art, scalable models to measure the efficacy and effectiveness of a new marketing channel. In this critical role, you will leverage your deep expertise in causal inference to design and implement robust measurement frameworks that provide actionable insights to drive strategic business decisions. Key Responsibilities: Develop advanced econometric and statistical models to rigorously evaluate the causal incremental impact of marketing campaigns on customer perception and customer behaviors. Collaborate cross-functionally with marketing, product, data science and engineering teams to define the measurement strategy and ensure alignment on objectives. Leverage large, complex datasets to uncover hidden patterns and trends, extracting meaningful insights that inform marketing optimization and investment decisions. Work with engineers, applied scientists and product managers to automate the model in production environment. Stay up-to-date with the latest research and methodological advancements in causal inference, causal ML and experiment design to continuously enhance the team's capabilities. Effectively communicate analysis findings, recommendations, and their business implications to key stakeholders, including senior leadership. Mentor and guide junior economists, fostering a culture of analytical excellence and innovation.
IL, Haifa
We’re looking for a Principal Applied Scientist in the Personalization team with experience in generative AI and large models. You will be responsible for developing and disseminating customer-facing personalized recommendation models. This is a hands-on role with global impact working with a team of world-class engineers and scientists across the wider organization. You will lead the design of machine learning models that scale to very large quantities of data, and serve high-scale low-latency recommendations to all customers worldwide. You will embody scientific rigor, designing and executing experiments to demonstrate the technical efficacy and business value of your methods. You will work alongside a science team to delight customers by aiding in recommendations relevancy, and raise the profile of Amazon as a global leader in machine learning and personalization. Successful candidates will have strong technical ability, focus on customers by applying a customer-first approach, excellent teamwork and communication skills, and a motivation to achieve results in a fast-paced environment. Our position offers exceptional opportunities for every candidate to grow their technical and non-technical skills. If you are selected, you have the opportunity to make a difference to our business by designing and building state of the art machine learning systems on big data, leveraging Amazon’s vast computing resources (AWS), working on exciting and challenging projects, and delivering meaningful results to customers world-wide. Key job responsibilities Develop machine learning algorithms for high-scale recommendations problem Rapidly design, prototype and test many possible hypotheses in a high-ambiguity environment, making use of both quantitative analysis and business judgement. Collaborate with software engineers to integrate successful experimental results into large-scale, highly complex Amazon production systems capable of handling 100,000s of transactions per second at low latency. Report results in a manner which is both statistically rigorous and compellingly relevant, exemplifying good scientific practice in a business environment.
DE, Aachen
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Applied Scientist with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As an Applied Scientist with the AGI team, you will work with talented peers to lead the development of novel algorithms and modeling techniques, to advance the state of the art with LLMs. Your work will directly impact our customers in the form of products and services that make use of speech and language technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in spoken language understanding. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, WA, Seattle
Are you a brilliant mind seeking to push the boundaries of what's possible with intelligent robotics? Join our elite team of researchers and engineers - led by Pieter Abeel, Rocky Duan, and Peter Chen - at the forefront of applied science, where we're harnessing the latest advancements in large language models (LLMs) and generative AI to reshape the world of robotics and unlock new realms of innovation. As an Applied Science Intern, you'll have the unique opportunity to work alongside world-renowned experts, gaining invaluable hands-on experience with cutting-edge robotics technologies. You'll dive deep into exciting research projects at the intersection of AI and robotics. This internship is not just about executing tasks – it's about being a driving force behind groundbreaking discoveries. You'll collaborate with cross-functional teams, leveraging your expertise in areas such as deep learning, reinforcement learning, computer vision, and motion planning to tackle real-world problems and deliver impactful solutions. Throughout your journey, you'll have access to unparalleled resources, including state-of-the-art computing infrastructure, cutting-edge research papers, and mentorship from industry luminaries. This immersive experience will not only sharpen your technical skills but also cultivate your ability to think critically, communicate effectively, and thrive in a fast-paced, innovative environment where bold ideas are celebrated. Join us at the forefront of applied robotics and AI, where your contributions will shape the future of intelligent systems and propel humanity forward. Seize this extraordinary opportunity to learn, grow, and leave an indelible mark on the world of technology. Amazon has positions available in San Francisco, CA and Seattle, WA. The ideal candidate should possess: - Strong background in machine learning, deep learning, and/or robotics - Publication record at science conferences such as NeurIPS, CVPR, ICRA, RSS, CoRL, and ICLR. - Experience in areas such as multimodal LLMs, world models, image/video tokenization, real2Sim/Sim2real transfer, bimanual manipulation, open-vocabulary panoptic scene understanding, scaling up multi-modal LLMs, and end-to-end vision-language-action models. - Proficiency in Python, Experience with PyTorch or JAX - Excellent problem-solving skills, attention to detail, and the ability to work collaboratively in a team Join us at the forefront of applied robotics and AI, and be a part of the team that's reshaping the future of intelligent systems. Apply now and embark on an extraordinary journey of discovery and innovation! Key job responsibilities - Develop novel, scalable algorithms and modeling techniques that advance the state-of-the-art in areas at the intersection of LLMs and generative AI for robotics - Tackle challenging, groundbreaking research problems on production-scale data, with a focus on robotic perception, manipulation, and control - Collaborate with cross-functional teams to solve complex business problems, leveraging your expertise in areas such as deep learning, reinforcement learning, computer vision, and motion planning - Demonstrate the ability to work independently, thrive in a fast-paced, ever-changing environment, and communicate effectively with diverse stakeholders
US, WA, Seattle
Join the next revolution in robotics at Amazon's Frontier AI & Robotics team, where you'll work alongside world-renowned AI pioneers like Pieter Abbeel, Rocky Duan, and Peter Chen to lead key initiatives in robotic intelligence. As a Senior Applied Scientist, you'll spearhead the development of breakthrough foundation models that enable robots to perceive, understand, and interact with the world in unprecedented ways. You'll drive technical excellence in areas such as perception, manipulation, scence understanding, sim2real transfer, multi-modal foundation models, and multi-task learning, designing novel algorithms that bridge the gap between cutting-edge research and real-world deployment at Amazon scale. In this role, you'll combine hands-on technical work with scientific leadership, ensuring your team delivers robust solutions for dynamic real-world environments. You'll leverage Amazon's vast computational resources 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 - Lead technical initiatives in robotics foundation models, driving breakthrough approaches through hands-on research and development in areas like 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 - Guide technical direction for specific research initiatives, ensuring robust performance in production environments - Mentor fellow scientists while maintaining strong individual technical contributions - Collaborate with engineering teams to optimize and scale models for real-world applications - Influence technical decisions and implementation strategies within your area of focus A day in the life - Develop and implement novel foundation model architectures, working hands-on with our extensive compute infrastructure - Guide fellow scientists in solving complex technical challenges, from sim2real transfer to efficient multi-task learning - Lead focused technical initiatives from conception through deployment, ensuring successful integration with production systems - Drive technical discussions within your team and with key stakeholders - Conduct experiments and prototype new ideas using our massive compute cluster - Mentor team members while maintaining significant hands-on contribution to technical solutions Amazon offers a full range of benefits that support you and eligible family members, including domestic partners and their children. Benefits can vary by location, the number of regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include: 1. Medical, Dental, and Vision Coverage 2. Maternity and Parental Leave Options 3. Paid Time Off (PTO) 4. 401(k) Plan If you are not sure that every qualification on the list above describes you exactly, we'd still love to hear from you! At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you’re passionate about this role and want to make an impact on a global scale, please apply! About the team At Frontier AI & Robotics, we're not just advancing robotics – we're reimagining it from the ground up. Our team, led by pioneering AI researchers Pieter Abbeel, Rocky Duan, and Peter Chen, is building the future of intelligent robotics through groundbreaking 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.
US, WA, Seattle
The Private Brands Discovery team designs innovative machine learning solutions to drive customer awareness for Amazon’s own brands and help customers discover products they love. Private Brands Discovery is an interdisciplinary team of Scientists and Engineers, who incubate and build disruptive solutions using cutting-edge technology to solve some of the toughest science problems at Amazon. To this end, the team employs methods from Natural Language Processing, Deep learning, multi-armed bandits and reinforcement learning, Bayesian Optimization, causal and statistical inference, and econometrics to drive discovery across the customer journey. Our solutions are crucial for the success of Amazon’s own brands and serve as a beacon for discovery solutions across Amazon. This is a high visibility opportunity for someone who wants to have business impact, dive deep into large-scale problems, enable measurable actions on the consumer economy, and work closely with scientists and engineers. As a scientist, you bring business and industry context to science and technology decisions. You set the standard for scientific excellence and make decisions that affect the way we build and integrate algorithms. Your solutions are exemplary in terms of algorithm design, clarity, model structure, efficiency, and extensibility. You tackle intrinsically hard problems, acquiring expertise as needed. You decompose complex problems into straightforward solutions.. With a focus on bias for action, this individual will be able to work equally well with Science, Engineering, Economics and business teams. Key job responsibilities - 5+ yrs of relevant, broad research experience after PhD degree or equivalent. - Advanced expertise and knowledge of applying observational causal interference methods - Strong background in statistics methodology, applications to business problems, and/or big data. - Ability to work in a fast-paced business environment. - Strong research track record. - Effective verbal and written communications skills with both economists and non-economist audiences.
US, WA, Seattle
The AWS Marketplace & Partner Services Science team is hiring an Applied Scientist to develop science products that support AWS initiatives to grow AWS Partners. The team is seeking candidates with strong background in machine learning and engineering, creativity, curiosity, and great business judgment. As an applied scientist on the team, you will work on targeting and lead prioritization related AI/ML products, recommendation systems, and deliver them into the production ecosystem. You are comfortable with ambiguity and have a deep understanding of ML algorithms and an analytical mindset. You are capable of summarizing complex data and models through clear visual and written explanations. You thrive in a collaborative environment and are passionate about learning. Key job responsibilities - Work with scientists, product managers and engineers to deliver high-quality science products - Experiment with large amounts of data to deliver the best possible science solutions - Design, build, and deploy innovative ML solutions to impact AWS Co-Sell initiatives About the team The AWS Marketplace & Partner Services team is the center of Analytics, Insights, and Science supporting the AWS Specialist Partner Organization on its mission to provide customers with an outstanding experience while working with AWS partners. The Science team supports science models and recommendation systems that are deployed directly to AWS Customers, AWS partners, and internal AWS Sellers.
CA, ON, Toronto
Conversational AI ModEling and Learning (CAMEL) team is part of Amazon Device organization where our mission is to create a best-in-class Conversational AI that is intuitive, intelligent, and responsive, by developing superior Large Language Models (LLM) solutions and services which increase the capabilities built into the model and which enable utilizing thousands of APIs and external knowledge sources to provide the best experience for each request across millions of customers and endpoints. We are looking for a passionate, talented, and resourceful science leader in the field of LLM, Artificial Intelligence (AI), Natural Language Processing (NLP), Recommender Systems and/or Information Retrieval, to invent and build scalable solutions for a state-of-the-art context-aware conversational AI. A successful candidate will have solid technical background and extensive experience in leading projects and technical teams. The ideal candidate would also have experiences in developing natural language processing systems (particularly LLM based systems) for industry applications, enjoy operating in highly dynamic and ambiguous environments, be self-motivated to take on challenging problems to deliver customer impact. In this role, you will lead a team of scientists to fine tune and evaluate the LLM to improve instruction following capabilities, align human preferences with RLHF, enhance conversation responses with RAG techniques, and various other. You will use your management, research and production experience to develop the team, communicate direction and achieve the results in a fast-paced environment. You will have significant influence on our overall LLM strategy by helping define product features, drive the system architecture, and spearhead the best practices that enable a quality product. Key job responsibilities Key job responsibilities Build a strong and coherent team with particular focus on sciences and innovations in LLM technologies for conversation AI applications Own the strategic planning and project management for technical initiatives in your team with the help of technical leads. Provide technical and scientific guidance to your team members. Collaborate effectively with multiple cross-organizational teams. Communicate effectively with senior management as well as with colleagues from science, engineering and business backgrounds. Support the career development of your team members.