The eviction of tenants is a pressing problem, which is prevalent among low-income renters in the USA, and has devastating consequences. Despite the presence of various measures to combat evictions, identifying high-need regions and tenant groups is highly challenging in many regions due to a lack of access to eviction records (partly because of some infrastructural/policy constraints). In response to this information gap, this paper proposes a solution driven by Machine Learning (ML) to monitor eviction status at various spatial resolutions using Airbnb data when ground-truth eviction data is inaccessible. In particular, we begin by demonstrating the potential of utilizing Airbnb data to build ML-driven methods for distinguishing different neighborhoods across different spatial resolutions with respect to eviction status. We then proceed to develop an ML model capable of learning eviction status levels from Airbnb data, even in the absence of ground-truth labels. Empirical evidence is presented, showcasing the model's performance on par with several robust fully-supervised ML models that had access to ground-truth labels during training. Finally, we conduct a set of cross-region tests to comprehensively study the generalizability of the achieved performance across various unseen regions in the USA that were not used during model training. The code of this project can be accessed via https://github.com/maryam-tabar/Airbnb-Eviction.

Recent studies have shown that a small number of buildings account for a significant portion of evictions in major U.S. cities, suggesting targeted policy interventions for these hotspots. However, focusing solely on eviction volumes can mislead policymakers by implying that property owners are the primary drivers of high eviction rates. This study investigates the spatial structure of eviction filings at the Census Block Group (CBG) level to determine if high eviction rates are due to neighborhood characteristics or other factors like landlords’ practices. We addressed three research questions: 1) the relationship between eviction filings due to nonpayment of rent and neighborhood characteristics, 2) the differences between eviction filings due to nonpayment and those for other reasons, and 3) the extent to which high rates of eviction filings in certain CBGs can be attributed to neighborhood characteristics versus unexplained spatial effects. We used Restricted Spatial Generalized Linear Mixed Models (RSGLMMs) with Hamiltonian Monte Carlo (HMC) sampling to estimate neighborhood fixed effects and spatial random effects, using data from Dallas County. Our findings confirm that important neighborhood factors identified in previous studies are consistently significant. Our spatial analysis revealed a noticeable difference between raw eviction filing counts and those adjusted for neighborhood characteristics, identifying CBGs with excessive eviction filings even after accounting for the neighborhood context. Based on these results, we propose a dual-track policy intervention: for hotspot buildings in CBGs with moderate spatial effects, we recommend tenant support measures like rental assistance and legal aid; for those with high spatial effects, we suggest prioritizing in-depth investigations of these buildings and landlord-focused interventions such as education on fair housing laws and landlord-tenant mediation services. All relevant code and data from this project are available in the GitHub repository: https://github.com/yilmajung/eviction2024repo.

African smallholder farmers have struggled with low agricultural productivity for decades, partly due to their inability to proactively assess irrigation needs in their farms in the face of long-term climate change. In this paper, we tackle this challenge by employing data-driven techniques to develop forecasting tools for three widely used crop-productivity related variables (i.e., actual evapotranspiration, reference evapotranspiration, and net primary production), which can then be used by farmers to take corrective actions on their farms. Prior work in this domain, despite using data-driven methods, suffers from two major limitations: (i) they mainly focus on estimating variable values (as opposed to forecasting the future); and (ii) they mostly use classical Machine Learning (ML) prediction models, despite the abundance of data sufficient to train sophisticated deep learning models. To fill this research gap, we collaborate with PlantVillage, the world’s leading non-profit agricultural knowledge delivery platform for African farmers, to identify ∼2,200 smallholder farm locations, and gather remote-sensed data of these farms over a period of five years. Next, we propose CLIMATES, a meta-algorithm leveraging structural insights about temporal patterns of this time-series data to accurately forecast their future values. We conduct extensive experiments to evaluate its performance in this domain. Our experimental results show that CLIMATES outperforms several state-of-the-art time-series forecasting models. We also provide insights about the poor performance of some competing models. Our work is being evaluated by officials at PlantVillage for potential future deployment as an early warning system in East Africa. We release the code at https://github.com/maryam-tabar/CLIMATES.

The widespread eviction of tenants across the United States has metamorphosed into a challenging public-policy problem. In particular, eviction exacerbates several income-based, educational, and health inequities in society, e.g., eviction disproportionately affects low-income renting families, many of whom belong to underrepresented minority groups. Despite growing interest in understanding and mitigating the eviction crisis, there are several legal and infrastructural obstacles to data acquisition at scale that limit our understanding of the distribution of eviction across the United States. To circumvent existing challenges in data acquisition, we propose WARNER, a novel Machine Learning (ML) framework that predicts eviction filing hotspots in US counties from unlabeled satellite imagery dataset. We account for the lack of labeled training data in this domain by leveraging sociological insights to propose a novel approach to generate probabilistic labels for a subset of an unlabeled dataset of satellite imagery, which is then used to train a neural network model to identify eviction filing hotspots. Our experimental results show that WARNER acheives a higher predictive performance than several strong baselines. Further, the superiority of WARNER can be generalized to different counties across the United States. Our proposed framework has the potential to assist NGOs and policymakers in designing well-informed (data-driven) resource allocation plans to improve the nationwide housing stability. This work is conducted in collaboration with The Child Poverty Action Lab (a leading non-profit leveraging data-driven approaches to inform actions for relieving poverty and relevant problems in Dallas County, TX). The code can be accessed via https://github.com/maryam-tabar/WARNER.

Eviction of tenants has reached a crisis level in the U.S. and its consequences pose significant challenges to society. To tackle this eviction crisis, policymakers have been allocating financial resources but a more efficient resource allocation would need an accurate forecast of the number of tenants at-risk of evictions ahead of time. To help enhance the existing eviction prevention/diversion programs, in this work, we propose a multi-view deep neural network model, named as MARTIAN, that forecasts the number of tenants at-risk of getting formally evicted (at the census tract level) n months into the future. Then, we evaluate MARTIAN’s predictive performance under various conditions using real-world eviction cases filed across Dallas County, TX. The results of empirical evaluation show that MARTIAN outperforms an extensive set of baseline models in terms of predictive performance. Additionally, MARTIAN’s superior predictive performance is generalizable to unseen census tracts, for which no labeled data is available in the training set. This research has been done in collaboration with Child Poverty Action Lab (CPAL), which is a pioneering non-governmental organization (NGO) working for tackling poverty-related issues across Dallas County, TX. The usability of MARTIAN is under review by subject matter experts. We release our codebase at https://github.com/maryam-tabar/MARTIAN.

East Africa is experiencing the worst locust infestation in over 25 years, which has severely threatened the food security of millions of people across the region. The primary strategy adopted by human experts at the United Nations Food and Agricultural Organization (UN-FAO) to tackle locust outbreaks involves manually surveying at-risk geographical areas, followed by allocating and spraying pesticides in affected regions. In order to augment and assist human experts at the UN-FAO in this task, we utilize crowdsourced reports of locust observations collected by PlantVillage (the world's leading knowledge delivery system for East African farmers) and develop PLAN, a Machine Learning (ML) algorithm for forecasting future migration patterns of locusts at high spatial and temporal resolution across East Africa. PLAN's novel spatio-temporal deep learning architecture enables representing PlantVillage's crowdsourced locust observation data using novel image-based feature representations, and its design is informed by several unique insights about this problem domain. Experimental results show that PLAN achieves superior predictive performance against several baseline models - it achieves an AUC score of 0.9 when used with a data augmentation method. PLAN represents a first step in using deep learning to assist and augment human expertise at PlantVillage (and UN-FAO) in locust prediction, and its real-world usability is currently being evaluated by domain experts (including a potential idea to use the heatmaps created by PLAN in a Kenyan TV show). The source code is available at https://github.com/maryam-tabar/PLAN.

To provide accurate and explainable misinformation detection, it is often useful to take an auxiliary source (e.g., social context and knowledge base) into consideration. Existing methods use social contexts such as users' engagements as complementary information to improve detection performance and derive explanations. However, due to the lack of sufficient professional knowledge, users seldom respond to healthcare information, which makes these methods less applicable. In this work, to address these shortcomings, we propose a novel knowledge guided graph attention network for detecting health misinformation better. Our proposal, named as DETERRENT, leverages on the additional information from medical knowledge graph by propagating information along with the network, incorporates a Medical Knowledge Graph and an Article-Entity Bipartite Graph, and propagates the node embeddings through Knowledge Paths. In addition, an attention mechanism is applied to calculate the importance of entities to each article, and the knowledge guided article embeddings are used for misinformation detection. DETERRENT addresses the limitation on social contexts in the healthcare domain and is capable of providing useful explanations for the results of detection. Empirical validation using two real-world datasets demonstrated the effectiveness of DETERRENT. Comparing with the best results of eight competing methods, in terms of F1 Score, DETERRENT outperforms all methods by at least 4.78% on the diabetes dataset and 12.79% on cancer dataset. We release the source code of DETERRENT at: https://github.com/cuilimeng/DETERRENT.

Substance Use Disorder (SUD) is a devastating disease that leads to significant mental and behavioral impairments. Its negative effects damage the homeless youth population more severely (as compared to stably housed counterparts) because of their high-risk behaviors. To assist policymakers in devising effective and accurate long-term strategies to mitigate SUD, it is necessary to critically analyze environmental, psychological, and other factors associated with SUD among homeless youth. Unfortunately, there is no definitive data-driven study on analyzing factors associated with SUD among homeless youth. While there have been a few prior studies in the past, they (i) do not analyze variation in the associated factors for SUD with geographical heterogeneity in their studies; and (ii) only consider a few contributing factors to SUD in relatively small samples. This work aims to fill this gap by making the following three contributions: (i) we use a real-world dataset collected from ~1,400 homeless youth (across six American states) to build accurate Machine Learning (ML) models for predicting the susceptibility of homeless youth to SUD; (ii) we find a representative set of factors associated with SUD among this population by analyzing feature importance values associated with our ML models; and (iii) we investigate the effect of geographical heterogeneity on the factors associated with SUD. Our results show that our system using adaptively boosted decision trees achieves the best predictive accuracy out of several algorithms on the SUD prediction task, achieving an Area Under the ROC Curve of 0.85. Further, among other things, we also find that both Post-Traumatic Stress Disorder (PTSD) and depression are very strongly associated with SUD among homeless youth because of their propensity to self-medicate to alleviate stress. This work is done in collaboration with social work scientists, who are currently evaluating the results for potential future deployment.