Events & Conferences
Why a lack of diversity hurts economics—and economists
Howard University’s recent announcement that it will host the American Economic Association Summer Training and Scholarship Program (AEASP) comes at a time when the economics profession finds itself grappling with a decades-old problem: a lack of diversity.
Four economists from diverse and underrepresented backgrounds, two each from Amazon and Howard University, recently shared their perspectives on the challenges and potential solutions.
Gerald E. Daniels Jr., associate professor of economics and associate director of undergraduate studies in the Department of Economics at Howard University; Jevay Grooms, assistant professor in the Department of Economics at Howard University; Muthoni Ngatia, a current Amazon and former World Bank economist; and Henrique Romero, a senior economist with Amazon’s Supply Chain Optimization Technologies division, addressed questions on why the problem of diversity within the economics field persists, what can be done, and how their life experiences have influenced their work as economists.
Why does the economics profession still struggle with diversity?
Muthoni Ngatia: The lack of diversity in economics becomes self-reinforcing when potential students don’t see themselves represented in the profession. It’s difficult to imagine yourself succeeding in a profession when you can’t find models in people with your lived experience.
There’s also an information barrier about what economics is, the type of work economists do, and how to prepare for a career in economics. Even in college, many of my classmates saw economics as a pathway to a career in investment banking or management consulting, which it certainly can be, however, there many more career opportunities available.
Jevay Grooms: There are many reasons. One that I found challenging, and almost prevented me from pursuing it, is very few people in the profession look like me. If you don’t see anyone who looks like you in the profession, it could be difficult to imagine yourself in the domain. I also think there is a misconception about the scope of work economists do. As an undergraduate student, I didn’t realize economists did work on social policies and disparities, the work that I do now.
Henrique Romero: The process of becoming an economist is long, arduous and rife with potential barriers to diversity. It takes a conscious effort to fight the inertia of the status quo at all steps along the way. For instance, economics departments mostly recruit talent from top PhD programs, which in turn tend to recruit PhD students from elite undergraduate institutions, which already suffer from a lack of representation. A forthcoming paper by Chetty et al. shows that at top-ranked universities, more students come from families in the top 1% than the bottom half of the income distribution.
What needs to happen to get individuals from more diverse backgrounds both interested in—and working—in economics?
Gerald E. Daniels Jr.: Outreach at every level of a student’s education is required to get more folks interested and working in economics. If a company, think tank, university, etc. has a sincere interest in diverse candidates, they should make a conscious effort to speak with and train the various candidates that they need. Therefore, if a company is searching for economists from underrepresented groups, create internships dedicated to universities that actively recruit and support these students. This approach can be extended to any diverse group. I would encourage anyone who needs help, to ask or hire folks like myself to support you.
Ngatia: More information about what economics is, the type of work economists do, and how to prepare for a career in economics. I think there’s a lot to be learned from programs working to get more diversity in STEM. Nurturing programs starting in high school and continuing into college can introduce a more diverse set of students to economics and how economists use data to understand and find potential solutions for social problems. Mentoring programs are also incredibly important to help students and economists throughout the pipeline advance.
Oscar Merrida IV
Grooms: I think the onus needs to be on the entire profession. It cannot just be underrepresented groups pushing for more diversity. All economists need to acknowledge the importance of diverse backgrounds and a diversity of thought, and see it as a benefit and not a threat. Race disparities, racial inequality, systemic racism, and systems of oppression need not be taboo words but rather, words that we, as economists, acknowledge play a role in societal outcomes. For too long, economists have taken the “I don’t see race” approach in research and this undermines the fight to address systemic racism.
Romero: I was the direct beneficiary of AEASP, which provides intensive training in microeconomics, math, econometrics, and research methods with the explicit goal of increasing racial and ethnic diversity. The program seems to be effective at increasing the likelihood of participants to apply to —and attend — a PhD program in economics, complete such programs, and work in an economics-related academic job (Becker et al., 2016). Although I will forever be indebted to this program, I must recognize that programs like this are difficult and costly to scale and can only be one part of a much broader solution. Bayer and Rouse (2016) provide an excellent overview of the state of diversity in the profession and discuss some promising initiatives. A full solution will likely require more equal access to education, from pre-k to PhD.
Why are diverse perspectives important to economics? How does the lack of them hinder economics?
Ngatia: Economic models require assumptions about how individuals and communities behave, those models are only as valid as they are representative of the diversity of human experience. The way we think about how humans behave necessarily depends on the humans we interact with, so a lack of diversity limits perspectives that could inform economic models. Advances in economics, or in any science really, are made by challenging existing modes of thinking. Having the same group of people in the profession limits the set problems they look at, and the tools they use.
Grooms: We have seen what a lack of diverse perspectives results in. To name a few: mass incarceration, the over-criminalization of crack cocaine relative to powdered cocaine, redlining, the overrepresentation of Black children in the foster care system, segregated schooling well after Brown v. Board of Education, and the Tuskegee experiment. Economists help shape social policy, and if we strive to be inclusive in our policymaking, we much also be inclusive in our research.
Daniels: If we allow ourselves to assume that policymakers and researchers prioritize topics that relate to their lived experience, then a lack of diversity inherently produces a lack of prioritization of research areas impacting those not represented. This is clear in the lack of research on a host of topics related to racial, gender, and LGBTQIA+ inequities. Diversity is our vehicle for producing innovative work, and a lack of diversity hinders our ability to innovate efficiently. In addition, innovating with a diverse group of people helps us to address issues that affect everyone.
How has your work as an economist been influenced by your life experiences?
Ngatia: Growing up in Kenya, I always knew I wanted to work in a capacity that would improve people’s livelihoods. When I came to college in the US, I wanted to pursue computer science. I was convinced (and still am) that the digital revolution would change the lives of many in Africa and I wanted to be a part of bringing that about. However, the first time I’d ever used a computer was when I was 16 and came to the US on an exchange program. My first semester in college, I felt completely out of my depth in my computer class.
Economics helped give me a framework to understand some of the development challenges facing Kenya and much of sub-Saharan Africa.
My economics class was the complete opposite. Whereas my CS class seemed abstract, economics—with a focus on decision making with scarce resources—made more sense to me. Economics helped give me a framework to understand some of the development challenges facing Kenya and much of sub-Saharan Africa. Perhaps most importantly, I found an incredible mentor in Michael Kremer, one of my professors (and recent Nobel Laureate in Economics) who took a personal interest in me. Much of his research was in Kenya, and his work inspired me to see how economics could be a force for improving people’s lives.
Grooms: My work as an economist has always been motivated by racial and ethnic equality. I imagine a lot of this has to do with growing up a Black girl in a predominantly white society. As an undergraduate, I learned that economics could help solve — or bring to light — issues that impact vulnerable and historically oppressed communities, and I think that has been the underlining theme in my work today.
Romero: Having grown up in one of the most unequal countries in the world (Brazil), equity concerns are always salient to me. Luckily, this aligns very well with Amazon’s Customer Obsession and Earns Trust leadership principles. For instance, we will refrain from enacting changes that would improve the customer experiences of a group of customers at the cost of disproportionally degrading the experience of another group, even if the changes result in an overall improvement in short-term metrics.
In an effort to be a small part of the solution in increasing diversity, I have also devoted time to being involved in the hiring, recruiting, and development process at Amazon, from participating in over 150 interviews, becoming a Bar Raiser in Training, managing the Economist Mentoring program, to representing Amazon at university campus visits and diversity-focused conferences such as SACNAS.
- We’re sharing how Meta is applying machine learning (ML) and diversity algorithms to improve notification quality and user experience.
- We’ve introduced a diversity-aware notification ranking framework to reduce uniformity and deliver a more varied and engaging mix of notifications.
- This new framework reduces the volume of notifications and drives higher engagement rates through more diverse outreach.
Notifications are one of the most powerful tools for bringing people back to Instagram and enhancing engagement. Whether it’s a friend liking your photo, another close friend posting a story, or a suggestion for a reel you might enjoy, notifications help surface moments that matter in real time.
Instagram leverages machine learning (ML) models to decide who should get a notification, when to send it, and what content to include. These models are trained to optimize for user positive engagement such as click-through-rate (CTR) – the probability of a user clicking a notification – as well as other metrics like time spent.
However, while engagement-optimized models are effective at driving interactions, there’s a risk that they might overprioritize the product types and authors someone has previously engaged with. This can lead to overexposure to the same creators or the same product types while overlooking other valuable and diverse experiences.
This means people could miss out on content that would give them a more balanced, satisfying, and enriched experience. Over time, this can make notifications feel spammy and increase the likelihood that people will disable them altogether.
The real challenge lies in finding the right balance: How can we introduce meaningful diversity into the notification experience without sacrificing the personalization and relevance people on Instagram have come to expect?
To tackle this, we’ve introduced a diversity-aware notification ranking framework that helps deliver more diverse, better curated, and less repetitive notifications. This framework has significantly reduced daily notification volume while improving CTR. It also introduces several benefits:
- The extensibility of incorporating customized soft penalty (demotion) logic for each dimension, enabling more adaptive and sophisticated diversity strategies.
- The flexibility of tuning demotion strength across dimensions like content, author, and product type via adjustable weights.
- The integration of balancing personalization and diversity, ensuring notifications remain both relevant and varied.
The Risks of Notifications without Diversity
The issue of overexposure in notifications often shows up in two major ways:
Overexposure to the same author: People might receive notifications that are mostly about the same friend. For example, if someone often interacts with content from a particular friend, the system may continue surfacing notifications from that person alone – ignoring other friends they also engage with. This can feel repetitive and one-dimensional, reducing the overall value of notifications.
Overexposure to the same product surface: People might mostly receive notifications from the same product surface such as Stories, even when Feed or Reels could provide value. For example, someone may be interested in both reel and story notifications but has recently interacted more often with stories. Because the system heavily prioritizes past engagement, it sends only story notifications, overlooking the person’s broader interests.
Introducing Instagram’s Diversity-Aware Notification Ranking Framework
Instagram’s diversity-aware notification ranking framework is designed to enhance the notification experience by balancing the predicted potential for user engagement with the need for content diversity. This framework introduces a diversity layer on top of the existing engagement ML models, applying multiplicative penalties to the candidate scores generated by these models, as figure1, below, shows.
The diversity layer evaluates each notification candidate’s similarity to recently sent notifications across multiple dimensions such as content, author, notification type, and product surface. It then applies carefully calibrated penalties—expressed as multiplicative demotion factors—to downrank candidates that are too similar or repetitive. The adjusted scores are used to re-rank the candidates, enabling the system to select notifications that maintain high engagement potential while introducing meaningful diversity. In the end, the quality bar selects the top-ranked candidate that passes both the ranking and diversity criteria.
Mathematical Formulation
Within the diversity layer, we apply a multiplicative demotion factor to the base relevance score of each candidate. Given a notification candidate 𝑐, we compute its final score as the product of its base ranking score and a diversity demotion multiplier:
where R(c) represents the candidate’s base relevance score, and D(c) ∈ [0,1] is a penalty factor that reduces the score based on similarity to recently sent notifications. We define a set of semantic dimensions (e.g., author, product type) along which we want to promote diversity. For each dimension i, we compute a similarity signal pi(c) between candidate c and the set of historical notifications H, using a maximal marginal relevance (MMR) approach:
where simi(·,·) is a predefined similarity function for dimension i. In our baseline implementation, pi(c) is binary: it equals 1 if the similarity exceeds a threshold 𝜏i and 0 otherwise.
The final demotion multiplier is defined as:
where each wi ∈ [0,1] controls the strength of demotion for its respective dimension. This formulation ensures that candidates similar to previously delivered notifications along one or more dimensions are proportionally down-weighted, reducing redundancy and promoting content variation. The use of a multiplicative penalty allows for flexible control across multiple dimensions, while still preserving high-relevance candidates.
The Future of Diversity-Aware Ranking
As we continue evolving our notification diversity-aware ranking system, a next step is to introduce more adaptive, dynamic demotion strategies. Instead of relying on static rules, we plan to make demotion strength responsive to notification volume and delivery timing. For example, as a user receives more notifications—especially of similar type or in rapid succession—the system progressively applies stronger penalties to new notification candidates, effectively mitigating overwhelming experiences caused by high notification volume or tightly spaced deliveries.
Longer term, we see an opportunity to bring large language models (LLMs) into the diversity pipeline. LLMs can help us go beyond surface-level rules by understanding semantic similarity between messages and rephrasing content in more varied, user-friendly ways. This would allow us to personalize notification experiences with richer language and improved relevance while maintaining diversity across topics, tone, and timing.
Every day, millions of customers search for books in various formats (audiobooks, e-books, and physical books) across Amazon and Audible. Traditional keyword autocomplete suggestions, while helpful, usually require several steps before customers find their desired content. Audible took on the challenge of making book discovery more intuitive and personalized while reducing the number of steps to purchase.
We developed an instant visual autocomplete system that enhances the search experience across Amazon and Audible. As the user begins typing a query, our solution provides visual previews with book covers, enabling direct navigation to relevant landing pages instead of the search result page. It also delivers real-time personalized format recommendations and incorporates multiple searchable entities, such as book pages, author pages, and series pages.
Our system needed to understand user intent from just a few keystrokes and determine the most relevant books to display, all while maintaining low latency for millions of queries. Using historical search data, we match keystrokes to products, transforming partial inputs into meaningful search suggestions. To ensure quality, we implemented confidence-based filtering mechanisms, which are particularly important for distinguishing between general queries like “mystery” and specific title searches. To reflect customers’ most recent interests, the system applies time-decay functions to long historical user interaction data.
To meet the unique requirements of each use case, we developed two distinct technical approaches. On Audible, we deployed a deep pairwise-learning-to-rank (DeepPLTR) model. The DeepPLTR model considers pairs of books and learns to assign a higher score to the one that better matches the customer query.
The DeepPLTR model’s architecture consists of three specialized towers. The left tower factors in contextual features and recent search patterns using a long-short-term-memory model, which processes data sequentially and considers its prior decisions when issuing a new term in the sequence. The middle tower handles keyword and item engagement history. The right tower factors in customer taste preferences and product descriptions to enable personalization. The model learns from paired examples, but at runtime, it relies on books’ absolute scores to assemble a ranked list.
For Amazon, we implemented a two-stage modeling approach involving a probabilistic information-retrieval model to determine the book title that best matches each keyword and a second model that personalizes the book format (audiobooks, e-books, and physical books). This dual-strategy approach maintains low latency while still enabling personalization.
In practice, a customer who types “dungeon craw” in the search bar now sees a visual recommendation for the book Dungeon Crawler Carl, complete with book cover, reducing friction by bypassing a search results page and sending the customer directly to the product detail page. On Audible, the system also personalizes autocomplete results and enriches the discovery experience with relevant connections. These include links to the author’s complete works (Matt Dinniman’s author page) and, for titles that belong to a series, links to the full collection (such as the Dungeon Crawler Carl series).
On Amazon, when the customer clicks on the title, the model personalizes the right book-format (audiobooks, e-books, physical books) recommendation and directs the customer to the right product detail page.
In both cases, after the customer has entered a certain number of keystrokes, the system employs a model to detect customer intent (e.g., book title intent for Amazon or author intent for Audible) and determine which visual widget should be displayed.
Audible and Amazon books’ visual autocomplete provides customers with more relevant content more rapidly than traditional autocomplete, and its direct navigation reduces the number of steps to find and access desired books — all while handling millions of queries at low latency.
This technology is not just about making book discovery easier; it is laying the foundation for future improvements in search personalization and visual discovery across Amazon’s ecosystem.
Acknowledgements: Jiun Kim, Sumit Khetan, Armen Stepanyan, Jack Xuan, Nathan Brothers, Eddie Chen, Vincent Lee, Soumy Ladha, Justine Luo, Yuchen Zeng, David Torres, Gali Deutsch, Chaitra Ramdas, Christopher Gomez, Sharmila Tamby, Melissa Ma, Cheng Luo, Jeffrey Jiang, Pavel Fedorov, Ronald Denaux, Aishwarya Vasanth, Azad Bajaj, Mary Heer, Adam Lowe, Jenny Wang, Cameron Cramer, Emmanuel Ankrah, Lydia Diaz, Suzette Islam, Fei Gu, Phil Weaver, Huan Xue, Kimmy Dai, Evangeline Yang, Chao Zhu, Anvy Tran, Jessica Wu, Xiaoxiong Huang, Jiushan Yang
Modern warehouses rely on complex networks of sensors to enable safe and efficient operations. These sensors must detect everything from packages and containers to robots and vehicles, often in changing environments with varying lighting conditions. More important for Amazon, we need to be able to detect barcodes in an efficient way.
The Amazon Robotics ID (ARID) team focuses on solving this problem. When we first started working on it, we faced a significant bottleneck: optimizing sensor placement required weeks or months of physical prototyping and real-world testing, severely limiting our ability to explore innovative solutions.
To transform this process, we developed Sensor Workbench (SWB), a sensor simulation platform built on NVIDIA’s Isaac Sim that combines parallel processing, physics-based sensor modeling, and high-fidelity 3-D environments. By providing virtual testing environments that mirror real-world conditions with unprecedented accuracy, SWB allows our teams to explore hundreds of configurations in the same amount of time it previously took to test just a few physical setups.
Camera and target selection/positioning
Sensor Workbench users can select different cameras and targets and position them in 3-D space to receive real-time feedback on barcode decodability.
Three key innovations enabled SWB: a specialized parallel-computing architecture that performs simulation tasks across the GPU; a custom CAD-to-OpenUSD (Universal Scene Description) pipeline; and the use of OpenUSD as the ground truth throughout the simulation process.
Parallel-computing architecture
Our parallel-processing pipeline leverages NVIDIA’s Warp library with custom computation kernels to maximize GPU utilization. By maintaining 3-D objects persistently in GPU memory and updating transforms only when objects move, we eliminate redundant data transfers. We also perform computations only when needed — when, for instance, a sensor parameter changes, or something moves. By these means, we achieve real-time performance.
Visualization methods
Sensor Workbench users can pick sphere- or plane-based visualizations, to see how the positions and rotations of individual barcodes affect performance.
This architecture allows us to perform complex calculations for multiple sensors simultaneously, enabling instant feedback in the form of immersive 3-D visuals. Those visuals represent metrics that barcode-detection machine-learning models need to work, as teams adjust sensor positions and parameters in the environment.
CAD to USD
Our second innovation involved developing a custom CAD-to-OpenUSD pipeline that automatically converts detailed warehouse models into optimized 3-D assets. Our CAD-to-USD conversion pipeline replicates the structure and content of models created in the modeling program SolidWorks with a 1:1 mapping. We start by extracting essential data — including world transforms, mesh geometry, material properties, and joint information — from the CAD file. The full assembly-and-part hierarchy is preserved so that the resulting USD stage mirrors the CAD tree structure exactly.
To ensure modularity and maintainability, we organize the data into separate USD layers covering mesh, materials, joints, and transforms. This layered approach ensures that the converted USD file faithfully retains the asset structure, geometry, and visual fidelity of the original CAD model, enabling accurate and scalable integration for real-time visualization, simulation, and collaboration.
OpenUSD as ground truth
The third important factor was our novel approach to using OpenUSD as the ground truth throughout the entire simulation process. We developed custom schemas that extend beyond basic 3-D-asset information to include enriched environment descriptions and simulation parameters. Our system continuously records all scene activities — from sensor positions and orientations to object movements and parameter changes — directly into the USD stage in real time. We even maintain user interface elements and their states within USD, enabling us to restore not just the simulation configuration but the complete user interface state as well.
This architecture ensures that when USD initial configurations change, the simulation automatically adapts without requiring modifications to the core software. By maintaining this live synchronization between the simulation state and the USD representation, we create a reliable source of truth that captures the complete state of the simulation environment, allowing users to save and re-create simulation configurations exactly as needed. The interfaces simply reflect the state of the world, creating a flexible and maintainable system that can evolve with our needs.
Application
With SWB, our teams can now rapidly evaluate sensor mounting positions and verify overall concepts in a fraction of the time previously required. More importantly, SWB has become a powerful platform for cross-functional collaboration, allowing engineers, scientists, and operational teams to work together in real time, visualizing and adjusting sensor configurations while immediately seeing the impact of their changes and sharing their results with each other.
New perspectives
In projection mode, an explicit target is not needed. Instead, Sensor Workbench uses the whole environment as a target, projecting rays from the camera to identify locations for barcode placement. Users can also switch between a comprehensive three-quarters view and the perspectives of individual cameras.
Due to the initial success in simulating barcode-reading scenarios, we have expanded SWB’s capabilities to incorporate high-fidelity lighting simulations. This allows teams to iterate on new baffle and light designs, further optimizing the conditions for reliable barcode detection, while ensuring that lighting conditions are safe for human eyes, too. Teams can now explore various lighting conditions, target positions, and sensor configurations simultaneously, gleaning insights that would take months to accumulate through traditional testing methods.
Looking ahead, we are working on several exciting enhancements to the system. Our current focus is on integrating more-advanced sensor simulations that combine analytical models with real-world measurement feedback from the ARID team, further increasing the system’s accuracy and practical utility. We are also exploring the use of AI to suggest optimal sensor placements for new station designs, which could potentially identify novel configurations that users of the tool might not consider.
Additionally, we are looking to expand the system to serve as a comprehensive synthetic-data generation platform. This will go beyond just simulating barcode-detection scenarios, providing a full digital environment for testing sensors and algorithms. This capability will let teams validate and train their systems using diverse, automatically generated datasets that capture the full range of conditions they might encounter in real-world operations.
By combining advanced scientific computing with practical industrial applications, SWB represents a significant step forward in warehouse automation development. The platform demonstrates how sophisticated simulation tools can dramatically accelerate innovation in complex industrial systems. As we continue to enhance the system with new capabilities, we are excited about its potential to further transform and set new standards for warehouse automation.
-
Business1 week agoThe Guardian view on Trump and the Fed: independence is no substitute for accountability | Editorial
-
Tools & Platforms4 weeks ago
Building Trust in Military AI Starts with Opening the Black Box – War on the Rocks
-
Ethics & Policy1 month agoSDAIA Supports Saudi Arabia’s Leadership in Shaping Global AI Ethics, Policy, and Research – وكالة الأنباء السعودية
-
Events & Conferences4 months agoJourney to 1000 models: Scaling Instagram’s recommendation system
-
Jobs & Careers2 months agoMumbai-based Perplexity Alternative Has 60k+ Users Without Funding
-
Education2 months agoVEX Robotics launches AI-powered classroom robotics system
-
Funding & Business2 months agoKayak and Expedia race to build AI travel agents that turn social posts into itineraries
-
Podcasts & Talks2 months agoHappy 4th of July! 🎆 Made with Veo 3 in Gemini
-
Podcasts & Talks2 months agoOpenAI 🤝 @teamganassi
-
Education2 months agoMacron says UK and France have duty to tackle illegal migration ‘with humanity, solidarity and firmness’ – UK politics live | Politics