skip to main content


Title: PittGrub: A Frustration-Free System to Reduce Food Waste by Notifying Hungry College Students
The amount of food waste generated by the U.S. is staggering, both expensive in economic cost and environmental side effects. Surplus food, which could be used to feed people facing food insecurity, is instead discarded and placed in landfills. Institutions, universities, and non-profits have noticed this issue and are beginning to take action to reduce surplus food waste, typically by redirecting it to food banks and other organizations or having students transport or eat the food. These approaches present challenges such as transportation, volunteer availability, and lack of prioritization of those in need. In this paper, we introduce PittGrub, a notification system to intelligently select users to invite to events that have leftover food. PittGrub was invented to help reduce food waste at the University of Pittsburgh. We use reinforcement learning to determine how many notifications to send out and a valuation model to determine whom to prioritize in the notifications. Our goal is to produce a system that prioritizes feeding students in need while simultaneously eliminating food waste and maintaining a fair distribution of notifications. As far as we are aware, PittGrub is unique in its approach to eliminating surplus food waste while striving for social good. We compare our proposed techniques to multiple baselines on simulated datasets to demonstrate effectiveness. Experimental results among various algorithms show promise in eliminating food waste while helping those facing food insecurity and treating users fairly. Our prototype is currently in beta and coming soon to the Apple App Store.  more » « less
Award ID(s):
1739413
NSF-PAR ID:
10074574
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2018)
Page Range / eLocation ID:
754 to 763
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Food waste and food insecurity are two challenges that coexist in many communities. To mitigate the problem, food rescue platforms match excess food with the communities in need, and leverage external volunteers to transport the food. However, the external volunteers bring significant uncertainty to the food rescue operation. We work with a large food rescue organization to predict the uncertainty and furthermore to find ways to reduce the human dispatcher's workload and the redundant notifications sent to volunteers. We make two main contributions. (1) We train a stacking model which predicts whether a rescue will be claimed with high precision and AUC. This model can help the dispatcher better plan for backup options and alleviate their uncertainty. (2) We develop a data-driven optimization algorithm to compute the optimal intervention and notification scheme. The algorithm uses a novel counterfactual data generation approach and the branch and bound framework. Our result reduces the number of notifications and interventions required in the food rescue operation. We are working with the organization to deploy our results in the near future. 
    more » « less
  2. Abstract

    In the United States, food banks play an important role in helping to reduce the rate of food insecurity by distributing donated food among the population in need. One of the challenges that food banks face is to equitably distribute food donations among their clients such that, ideally, each recipient receives the same amount of food. They aim to do so while minimizing waste that occurs due to spoilage and capacity limitations. Perishable food items present specific challenges since they are susceptible to spoilage and need to be distributed before their expiry dates. Based on our longstanding partnership with a large food bank located in the southeastern United States, we present a capacitated, multiperiod, multiproduct network flow model to help them equitably and effectively distribute perishable food donations among the food‐insecure population in their service region. The model is applied within the context of a case study and reveals managerial insights that would be useful to practitioners. Our findings show that although equity is one of the food bank's highest priorities, inequities cannot be eliminated completely. Given the inevitability of inequitable food allocations in practice, this paper provides food banks guidance on how to strategically control inequities using two approaches: (i) by increasing the number of periods for which equity should be satisfied or () by allowing deviations from a perfectly equitable distribution. The results show that modest deviations from perfect equity using either approach can lead to significant improvements in both the quality and quantity of food distributed and can also reduce food waste. While approach () is preferable, the most desirable outcomes occur when both are applied simultaneously. We also find that county capacities inhibit a food bank's ability to achieve balance between equity and effectiveness when distributing perishables. Our framework provides food banks the flexibility to balance the trade‐off between effectiveness and equity based on their preferences.

     
    more » « less
  3. null (Ed.)
    University food pantries have been opened on-campus to reduce food insecurity among students. However, they are relatively self-governed and receive a limited amount of support. This study aims to resolve the inventory management issue at university food pantries using the combination of the Model-View-Controller (MVC) software pattern and data visualization. As a result, a foundation is established to predict the food choices of clients and to manage food waste effectively. The benefits of visualization on decision making through the use of a resourceful inventory system are outlined. The focus of this research is on university pantries, in particular, the Aggie Source Food Pantry at North Carolina Agricultural & Technical State University. A sample of 50 clients' food choices was acquired from picklists for June and July of 2019. The inventory tracking system implemented is a client-server mobile application used for data collection. Data visualization was applied to evaluate the food donations and distributions. Students preferred essential foods (e.g., pasta, canned vegetables), over unhealthy foods (e.g., Pop-Tarts, cookies). The data consisted of 338 pounds of distributed food and almost 2,473 pounds of donations. Data was simplified into comprehensive visual diagrams. The MVC structure established a program interface that grouped application functions and managed data objects. The solution allowed the staff to understand pantry status and the trends in production. It is anticipated that the prototype will be implemented in the daily activities of the pantry. 
    more » « less
  4. null (Ed.)
    CONTEXT With the onset of the COVID-19 pandemic, and the resulting response from universities, engineering students find themselves in an unprecedented situation. In addition to stressors related to the curriculum, residential students across the United States are being asked to relocate away from campus and engage in distance learning. At the same time, social distancing requirements are limiting students’ ability to socialize, procure food and supplies, exercise, and remain employed and financially solvent. Some students will fall ill while others face the prospect of sick family members, and even deaths in the family. Prior research suggests that individuals living through this pandemic are likely to face stress, uncertainty, and fear that affects their mental health and academic performance for years to come. PURPOSE OR GOAL The purpose of this study was to understand the ways in which the COVID-19 pandemic is affecting engineering students’ mental wellness, specifically stress, and how the effects differ for different groups of students. The research questions addressed are: 1) What effects has the pandemic had on baseline stress levels, and how do those vary by demographic group? 2) What effects has the pandemic had on quality of life, such as sleep habits and financial security, and how do those vary by demographic group? METHODS An online survey was conducted in the United States in May and June of 2020. More than 800 4-year engineering students who represented many engineering disciplines and universities responded. The survey used a modified version of the Holmes-Rahe Social Readjustment Rating Scale, which is a widely used and validated instrument to measure the effects of certain life events on stress. The data was analysed to determine the average increase in stress levels for students resulting from COVID-19, and which demographic groups have seen the most negative impact. We also report on which stress-inducing life-events were experienced most. OUTCOMES Latinx individuals and international students report statistically significantly higher levels of stress than the baseline population. Engineering students from other historically excluded identities, however,are not facing statistically significantly worse stress than their peers from historically over represented identities. Veterans fare better than the majority population on this metric.The data also indicates that different groups are more likely to experience different negative life-events because of COVID. CONCLUSIONS No previous research has examined the impacts of a global pandemic on engineering student stress and mental wellness. Our findings show that stress and mental wellness need to be understood intersectionally and that some underrepresented groups are disproportionately impacted by COVID-19. Understanding the impacts on students can help universities strategize and allocate limited resources most effectively to support student success. KEYWORDS Mental wellness; COVID-19; stress 
    more » « less
  5. Abstract

    Systems‐level approaches are required for addressing the world's major challenges at the food–energy–water nexus. Taking on complex issues, such as rising food insecurity, malnutrition, and food waste, concomitant with unprecedented levels of stress on environmental systems, will necessitate that future scholars and decision makers be prepared through transdisciplinary student training. However, in higher education, students tend to be siloed within their discipline. In this study, we present a case for the development of transdisciplinary graduate student training based on an inter‐institutional and fully remote group of graduate students who assembled during the COVID‐19 pandemic to address the issue of food waste. We use our wide‐ranging disciplinary backgrounds, high‐performance transdisciplinary team training, and stakeholder feedback to develop and conduct a weeklong social media campaign to share educational resources for reducing household food waste. This work offers valuable lessons learned through the student's lens to those seeking to create or improve future transdisciplinary training methods for tackling food waste and other global grand challenges. Key insights from this process include the importance of accountability and open communication when conducting collaborative teamwork, the utility of various mobile and online tools for effectively facilitating remote group work, and the vital role of transdisciplinarity in devising creative solutions.

     
    more » « less